Intelligent monitoring system for construction environment pollution

Abstract

The invention discloses an intelligent monitoring system for construction environment pollution, particularly relates to the field of tunnel construction environment pollution monitoring, is used for solving the problems of pollution diffusion and risk assessment, and accurately calculates an air flow vector field through an intelligent air pollution monitoring system in combination with a fluid dynamics principle and a Navier-Stokes equation. Air flow and pollutant diffusion paths in a tunnel are disclosed. And constructing a pressure gradient field, quantifying the pressure difference and air exchange capacity between regions, and providing driving force analysis of pollutant diffusion. Calculating a pollutant transmission coefficient through nonlinear coupling calculation in combination with an air flow correlation degree, a pressure gradient field and an air exchange capability coefficient, and quantifying the pollutant transmission capability of adjacent regions; and then real-time evaluation and grading are carried out on pollution risks, high-risk areas are identified in time, and early warning information is pushed through the intelligent terminal. Therefore, the ventilation strategy is optimized, the energy consumption is reduced, and the health of constructors and the construction safety are guaranteed.

Description

Technical Field

[0001] The present invention relates to the field of tunnel construction environmental pollution monitoring, and more specifically, to an intelligent monitoring system for construction environmental pollution. Background Art

[0002] In tunnel construction environments, due to the closed or semi-closed characteristics of the space, a large amount of dust, exhaust gas, volatile organic compounds (VOCs) and other pollutants generated during the construction process are very likely to accumulate in local areas, causing serious deterioration of air quality and posing huge risks to the health and safety of construction workers. In this environment, air flow is restricted, pollutants diffuse slowly, and highly polluted areas are formed. At the same time, the complex structure of the tunnel and the uneven dynamic characteristics of air flow further increase the unpredictability of pollutant diffusion. Effectively monitoring air quality and taking timely pollution control measures are the key to ensuring construction safety.

[0003] Existing air pollution monitoring technologies mainly rely on decentralized sensor networks and simple threshold alarm mechanisms, which are difficult to cope with the complex air flow characteristics and pollution diffusion behaviors in tunnel construction. Due to the lack of dynamic evaluation of the complex relationship between air flow, pressure difference and pollutant concentration, it is difficult for existing systems to accurately identify areas with actual severe pollution and redundant pollution areas, resulting in excessive monitoring and unnecessary ventilation treatment in some areas. Insufficient identification of redundant pollution areas not only wastes monitoring resources and energy, but also makes it difficult to achieve precise control of highly polluted areas. In addition, the existing system is unable to adjust the monitoring strategy in real time, ignores the dynamic changes in pollutant diffusion, exacerbates the misjudgment of redundant pollution areas, and cannot provide accurate risk assessment and early warning information, resulting in low monitoring efficiency, untimely early warning, increased energy consumption and control costs, and difficulty in meeting the precise management needs of complex construction environments.

[0004] In order to solve the above problems, a technical solution is now provided. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, the embodiment of the present invention provides an intelligent monitoring system for construction environment pollution. Through the intelligent air pollution monitoring system, dynamic and accurate management of air pollution in the tunnel construction environment is achieved. By combining the boundary of the fused pollution area with the internal pollutant concentration distribution, the system can accurately calculate the air flow vector field and reveal the air flow situation and pollutant diffusion path in the tunnel. By constructing a pressure gradient model, the pressure difference and air exchange capacity between each fused pollution area are quantified, providing an important driving force analysis for the diffusion behavior of pollutants; in addition, the present invention comprehensively considers the air flow correlation, pressure gradient field and air exchange capacity coefficient through a nonlinear coupling calculation model, accurately calculates the pollutant transmission coefficient, and quantifies the actual transmission capacity of pollutants between adjacent areas. Through real-time calculation and analysis of the pollutant transmission coefficient, the system can dynamically evaluate and grade the pollution risk according to the preset threshold, and timely identify high pollution risk areas. Early warning information is pushed in real time through smart terminals, enabling relevant personnel to respond quickly and take countermeasures; overall, the present invention effectively improves the accuracy and response speed of air pollution monitoring, optimizes the ventilation strategy in the tunnel, reduces energy consumption, ensures the rapid dilution and safe diffusion of pollutants, and protects the health of construction workers and the safety of the construction site, so as to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] An intelligent monitoring system for construction environment pollution, comprising: a fusion area module, a correlation analysis module, a pressure modeling module, a risk calculation module, a risk classification module and an early warning push module;

[0008] Fusion area module: obtains pollution data of each air delivery point, fuses similar and adjacent pollution areas, and obtains fused pollution areas; outputs fused pollution areas and transmits them to the correlation analysis module and pressure modeling module;

[0009] Correlation analysis module: constructs air flow correlation matrix based on fused pollution areas; outputs correlation matrix and transmits it to risk calculation module;

[0010] Pressure modeling module: collects air supply pressure data, establishes pressure gradient field, analyzes and calculates air exchange capacity coefficient; outputs pressure gradient field and air exchange capacity coefficient, and transmits them to risk calculation module;

[0011] Risk calculation module: Calculate the pollutant transmission coefficient between each fused pollution area according to the correlation matrix, pressure gradient field and air exchange capacity coefficient to quantify the risk of pollutant transmission; output the pollutant transmission coefficient and pass it to the risk classification module;

[0012] Risk classification module: using risk assessment algorithm, based on pollutant transmission coefficient, classify the risk level of the fusion area and generate early warning information; output the early warning information and transmit it to the early warning push module;

[0013] Early warning push module: Update early warning information in real time and push it to relevant personnel through smart terminals to achieve dynamic monitoring of high-risk areas.

[0014] In a preferred embodiment, the fusion region module includes the following processing steps:

[0015] S1.1, using multi-dimensional pollution sensors deployed at each air delivery point to collect real-time data on pollutants in the air;

[0016] S1.2, based on the real-time collection of pollutant data in the air, a multi-dimensional pollution matrix is ​​constructed, where each dimension corresponds to the type and concentration value of pollutants at an air delivery point;

[0017] S1.3, similarity calculation is performed on the pollution data of each air delivery point, and comparison is made using the difference threshold of pollutant concentration, type combination and time series change; the pollution similarity between adjacent air delivery points is evaluated by weighted similarity algorithm, and the calculation results generate a set of pollution similarity indicators to determine the similarity degree of pollution in each area;

[0018] S1.4, based on the geographical location data and pollution similarity index of the air delivery points, determine whether each air delivery point belongs to a bordering area; use a spatial geometric analysis algorithm to calculate the relative distance between the air delivery points and determine whether the point pairs within the preset threshold range are bordering;

[0019] S1.5, the pollution areas covered by the air delivery points that meet the similarity standards and are adjacent to each other are merged to generate a merged pollution area.

[0020] In a preferred embodiment, the fusion region module further comprises the following processing steps:

[0021] S1.6, generating the boundary of the fused pollution area based on the geographical location data and pollutant data of the fused pollution area; the specific process is as follows:

[0022] Based on the geographical location of the air delivery point, a two-dimensional spatial layout matrix is ​​constructed. Each point in the matrix corresponds to the coordinates of an air delivery point. Let the elements in the matrix be L(x i ,y i ), represents the coordinate position of the ith air delivery point, where x i and i are the horizontal and vertical coordinates of the corresponding air delivery points respectively;

[0023] According to the pollutant concentration at each air delivery point, a pollutant concentration gradient field G(x,y) is established; each position point C(x,y) in the pollutant concentration gradient field is calculated through concentration gradient to reflect the change of pollutant concentration at the air delivery point; the gradient calculation formula is: Where C(x,y) represents the pollutant concentration at the air delivery point (x,y), is the concentration gradient, which indicates the rate of change of concentration in the x and y directions;

[0024] The boundary fitting algorithm is used to determine the boundary of the polluted area using the spatial layout matrix and the pollutant concentration gradient field. The boundary condition is determined by the concentration gradient threshold G threshold Control, when the concentration gradient satisfies: It is regarded as the critical point of the regional boundary; by fitting the change of pollutant concentration, the effective boundary range B(x,y) of the polluted area is calculated;

[0025] The boundaries of similar and adjacent polluted areas are merged to generate a new polluted area boundary, that is, the boundary B of the merged polluted area fusion (x,y): in and The adjacent polluted areas are 1 and r 2 The boundary of the contaminated area is generated by the union operation of the boundary.

[0026] In a preferred embodiment, the association analysis module includes the following processing steps:

[0027] S2.1, based on the boundary of the fused pollution area and the internal pollutant concentration distribution, using the principles of fluid dynamics, calculate the air flow vector field V(x,y) in each area;

[0028] S2.2, for each pair of adjacent fused contaminated areas I and J, calculate the air flow correlation A between the two IJ ; The air flow correlation is the ratio of the air flow across the regional boundary, and the calculation formula is: Among them, B IJ To merge the common boundary of polluted areas I and J, V n is the air velocity component along the normal direction, dl is the boundary element length, B I is the total boundary of the fused pollution area I, |V| is the modulus of the air velocity;

[0029] S2.3, organize the air flow correlations between all fused pollution areas into a correlation matrix, and obtain the air flow correlation matrix A. The elements of the air flow correlation matrix A IJRepresents the air flow correlation between the fused pollution areas I and J; the air flow correlation matrix is ​​a symmetric matrix that satisfies A IJ =A JI ;

[0030] S2.4, using the air flow correlation matrix and the pollutant concentration gradient, calculate the propagation path of pollutants between the fused pollution areas;

[0031] S2.5, for each pair of adjacent fused contaminated areas, based on the air flow correlation and concentration difference ΔC IJ =C I -C J , where C I and C J Respectively represent the fusion contaminated area R I and R J The average pollutant concentration is calculated to calculate the pollutant transfer coefficient T IJ :T IJ =A IJ ×f(ΔC IJ ), where f(ΔC IJ ) concentration difference influence factor, take f(ΔC IJ )=ΔC IJ .

[0032] In a preferred embodiment, the pressure modeling module includes the following processing steps:

[0033] S3.1, using the pressure sensors deployed at each air delivery point to collect air supply pressure data P in real time s (x i ,y i ), where (x i ,y i ) is the spatial position of the i-th air delivery point, P s Indicates the air supply pressure value of the corresponding air delivery point;

[0034] S3.2, constructing a pressure distribution model P(x, y) in the tunnel based on the collected air supply pressure data and the spatial position of the air delivery point; using a spatial interpolation algorithm to generate a continuous pressure distribution function in the entire tunnel space;

[0035] S3.3, calculate the gradient of the pressure distribution model and obtain the pressure gradient field Indicates the direction and rate of pressure change at each point in the tunnel; the pressure gradient field calculation formula is: in, and are the partial derivatives of pressure along the x and y directions respectively;

[0036] S3.4, using the boundaries of the fused contaminated areas, calculate the average pressure inside each fused contaminated area and the pressure difference between the regions ΔP IJ , where I and J represent two adjacent fused contaminated areas respectively; the average pressure calculation formula is: Among them, A I is the area of ​​fusion region I; the regional pressure difference calculation formula is:

[0037] S3.5, calculate the air exchange capacity coefficient E between adjacent fusion areas based on the pressure gradient field and the pressure difference between the areas IJ ; Combined with the ventilation cross-sectional area S between regions IJ And aerodynamic parameters, the air exchange capacity coefficient is calculated as: Among them, C d is the flow resistance coefficient, ρ is the air density, |ΔP rs | is the absolute value of the pressure difference.

[0038] In a preferred embodiment, the risk calculation module includes the following processing steps:

[0039] Based on the pollutant transmission coefficient T IJ , pressure gradient field and air exchange capacity coefficient E IJ , the pollutant transport coefficient is obtained by combining the hyperbolic tangent function with the cross term for nonlinear coupling.

[0040] In a preferred embodiment, the risk classification module includes the following processing steps:

[0041] The pollutant transfer coefficient is compared with the low-level threshold and the high-level threshold respectively. When the pollutant transfer coefficient is less than or equal to the low-level threshold, it is designated as a low-risk area and a low-risk signal is generated; when the pollutant transfer coefficient is greater than the low-level threshold and less than or equal to the high-level threshold, it is designated as a medium-risk area and a medium-risk signal is generated; when the pollutant transfer coefficient is greater than the high-level threshold, it is designated as a high-risk area and a high-risk signal is generated.

[0042] In a preferred embodiment, the warning push module includes the following processing steps:

[0043] The early warning information includes low-risk signals, medium-risk signals and high-risk signals; the risk signals, medium-risk signals or high-risk signals output by the risk classification module are pushed to relevant personnel through smart terminals.

[0044] The technical effects and advantages of the intelligent monitoring system for construction environment pollution of the present invention are as follows:

[0045] The present invention realizes dynamic and precise management of air pollution in tunnel construction environment through intelligent air pollution monitoring system. By integrating the boundary of pollution area and internal pollutant concentration distribution, combined with fluid dynamics principle and Navier-Stokes equation, the system can accurately calculate the air flow vector field, revealing the air flow and pollutant diffusion path in the tunnel. By constructing pressure gradient model, the pressure difference and air exchange capacity between each fused pollution area are quantified, providing important driving force analysis for the diffusion behavior of pollutants.

[0046] In addition, the present invention uses a nonlinear coupling calculation model to comprehensively consider the air flow correlation, pressure gradient field and air exchange capacity coefficient, accurately calculate the pollutant transmission coefficient, and quantify the actual transmission capacity of pollutants between adjacent areas. Through real-time calculation and analysis of the pollutant transmission coefficient, the system can dynamically evaluate and grade the pollution risk according to the preset threshold value, and timely identify high pollution risk areas. Early warning information is pushed in real time through smart terminals, allowing relevant personnel to respond quickly and take countermeasures.

[0047] Overall, the present invention effectively improves the accuracy and response speed of air pollution monitoring, optimizes the ventilation strategy in the tunnel, reduces energy consumption, ensures the rapid dilution and safe diffusion of pollutants, and protects the health of construction workers and the safety of the construction site. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 The present invention is a structural schematic diagram of an intelligent monitoring system for construction environment pollution. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0050] Example 1

[0051] Figure 1 The present invention provides an intelligent monitoring system for construction environment pollution, including: a fusion area module, a correlation analysis module, a pressure modeling module, a risk calculation module, a risk classification module and an early warning push module;

[0052] Fusion area module: obtains pollution data of each air delivery point, fuses similar and adjacent pollution areas, and obtains fused pollution areas; outputs fused pollution areas and transmits them to the correlation analysis module and pressure modeling module;

[0053] Correlation analysis module: constructs air flow correlation matrix based on fused pollution areas; outputs correlation matrix and transmits it to risk calculation module;

[0054] Pressure modeling module: collects air supply pressure data, establishes pressure gradient field, analyzes and calculates air exchange capacity coefficient; outputs pressure gradient field and air exchange capacity coefficient, and transmits them to risk calculation module;

[0055] Risk calculation module: Calculate the pollutant transmission coefficient between each fused pollution area according to the correlation matrix, pressure gradient field and air exchange capacity coefficient to quantify the risk of pollutant transmission; output the pollutant transmission coefficient and pass it to the risk classification module;

[0056] Risk classification module: using risk assessment algorithm, based on pollutant transmission coefficient, classify the risk level of the fusion area and generate early warning information; output the early warning information and transmit it to the early warning push module;

[0057] Early warning push module: Update early warning information in real time and push it to relevant personnel through smart terminals to achieve dynamic monitoring of high-risk areas.

[0058] Air pollution is a particularly prominent problem in tunnel construction environments, especially in closed or semi-closed tunnels. Dust, exhaust gas, volatile organic compounds (VOCs) and other pollutants generated during construction are difficult to disperse effectively and can easily accumulate to dangerous levels. Due to the complex internal structure of the tunnel, limited air flow, uneven distribution of pollutants in various areas, and the phenomenon that pollution sources change with the progress of construction, an intelligent air monitoring and control system that can monitor in real time and respond dynamically is needed.

[0059] During the construction process, air pollution in different areas is affected by many factors, such as emissions from construction equipment, volatilization of materials, and uneven air supply, which cause local pollution to intensify or spread slowly. Traditional ventilation methods are difficult to deal with this complex environment in a targeted manner, resulting in some areas being in a state of high pollution for a long time, while other areas are over-ventilated, resulting in a waste of resources. By building a multi-point monitoring and regional fusion mechanism, the air quality of each polluted area can be accurately identified and effectively controlled.

[0060] After the air pollution areas are merged, the air flow relationship between different areas, the pollutant dilution effect and the air supply pressure will affect the diffusion and transmission of pollutants. These factors need to be comprehensively analyzed through an intelligent control system to achieve dynamic management and risk warning of polluted areas.

[0061] The fused region module includes the following processing steps:

[0062] S1.1 uses multi-dimensional pollution sensors deployed at each air delivery point to collect real-time pollutant data in the air, including particle concentration, gaseous pollutant concentration, volatile organic compound concentration, etc. Each air delivery point independently records the pollutant values ​​in its area and transmits the data to the central processing system through a wireless transmission module.

[0063] S1.2, based on the real-time collection of pollutant data in the air, a multidimensional pollution matrix is ​​constructed, where each dimension corresponds to the type and concentration value of pollutants at an air delivery point. The multidimensional matrix reflects the type, concentration and spatial location of pollutants at different air delivery points, forming a preliminary data structure of the polluted area.

[0064] S1.3, similarity calculation is performed on the pollution data of each air delivery point, and the difference threshold, type combination and time series change of pollutant concentration are used for comparison. The pollution similarity between adjacent air delivery points is evaluated through a weighted similarity algorithm, and the calculation results generate a set of pollution similarity indicators to determine the similarity degree of pollution in each area.

[0065] S1.4, based on the geographical location data and pollution similarity index of the air delivery points, determine whether each air delivery point belongs to the bordering area. Use the spatial geometry analysis algorithm to calculate the relative distance between the air delivery points and determine whether the point pairs within the preset threshold range are bordering.

[0066] S1.5, the polluted areas covered by the air transport points that meet the similarity standards and are adjacent to each other are merged to generate a merged polluted area. The fusion process is based on the pollutant concentration weighted average algorithm, which weights and synthesizes the pollutant concentrations of adjacent areas and updates the pollutant type and pollutant concentration information of the area. The merged polluted area has a new pollutant concentration and geographical range.

[0067] S1.6, based on the geographical location data and pollutant data of the fused pollution area, the boundary of the fused pollution area is generated. It is determined by the spatial boundary calculation model. The model determines the boundary of the fused pollution area based on the spatial layout of the air delivery point and the pollutant concentration gradient. The specific process is as follows:

[0068] Based on the geographical location of the air delivery point, a two-dimensional spatial layout matrix is ​​constructed. Each point in the matrix corresponds to the coordinates of an air delivery point. Let the elements in the matrix be L(x i ,y i ), represents the coordinate position of the ith air delivery point, where x i and i They are the horizontal and vertical coordinates of the corresponding air delivery points respectively.

[0069] According to the pollutant concentration at each air delivery point, a pollutant concentration gradient field G(x,y) is established. Each position point C(x,y) in the gradient field is calculated through the concentration gradient to reflect the change in pollutant concentration at the air delivery point. The gradient calculation formula is:

[0070] Where C(x,y) represents the pollutant concentration at the air delivery point (x,y), is the concentration gradient, which represents the rate of change of concentration in the x and y directions.

[0071] The pollutant concentration gradient field is used to represent and quantify the spatial variation of pollutant concentrations between different areas in the tunnel, reflecting the trend of pollutant concentrations changing with spatial position. By calculating the concentration gradient, the direction and rate of pollutant diffusion from high-concentration areas to low-concentration areas can be intuitively reflected. The larger the value of the pollutant concentration gradient field, the more drastic the concentration change and the stronger the driving force for pollutant diffusion; the smaller the value, the gentler the concentration change and the weaker the diffusion force. The concentration gradient field is not only used to track the diffusion path of pollutants, but also provides a key basis for evaluating the impact of air flow on pollutant distribution and optimizing ventilation strategies.

[0072] Using the spatial layout matrix and the pollutant concentration gradient field, the boundary fitting algorithm is used to determine the boundary of the polluted area. The boundary condition is determined by the concentration gradient threshold G threshold Control, when the concentration gradient satisfies:

[0073] It is regarded as the critical point of the regional boundary. By fitting the change of pollutant concentration, the effective boundary range B(x,y) of the polluted area is calculated.

[0074] Combined with the spatial location of each air delivery point and the effective boundary range of the pollution area, the boundaries of similar and adjacent pollution areas are merged to generate a new pollution area boundary, that is, the boundary B of the fused pollution area. fusion (x,y):

[0075] in and The adjacent polluted areas are 1 and r 2 The boundary of the contaminated area is generated by the union operation of the boundary.

[0076] In a complex tunnel construction environment, the diffusion behavior of pollutants is significantly affected by air flow characteristics, especially the air exchange and pollutant concentration differences between regions, which directly determine the transmission path and risk level of pollutants. In order to effectively monitor and evaluate the transmission dynamics of pollutants in tunnels, the correlation analysis module systematically calculates the boundaries, air flow characteristics and concentration distribution of the fused pollution area, establishes an air flow correlation model, and combines the pollutant concentration gradient to accurately quantify the transmission capacity of pollutants between regions.

[0077] First, based on the principles of fluid dynamics, the correlation analysis module uses the air flow vector field to simulate the air flow in each contaminated area, taking into account the tunnel structure and air physical properties to reflect the air flow direction and speed in actual working conditions. Subsequently, by calculating the air flow correlation between adjacent fusion areas, the air exchange in each area is further evaluated, and these correlations are organized into an air flow correlation matrix to construct an air exchange network between regions. Combining this matrix with the distribution of pollutant concentrations in the region, the correlation analysis module uses advanced algorithms to calculate the propagation paths and main diffusion pathways of pollutants between different areas in the tunnel, ensuring that the diffusion trend and transmission risk of pollutants can be tracked in real time.

[0078] The association analysis module includes the following processing steps:

[0079] S2.1, based on the boundary of the fused pollution area and the internal pollutant concentration distribution, the air flow vector field V(x,y) in each area is calculated using the principles of fluid dynamics. The Navier-Stokes equations are used to simulate the flow state of air in the tunnel, and the speed and direction of air flow are obtained by considering factors such as tunnel structure, air density, viscosity, etc.

[0080] Assume that in a complex tunnel construction environment, the cross-section of the tunnel is irregularly shaped, and air enters the tunnel through multiple air delivery points. In order to evaluate the flow of air in the tunnel and the propagation path of pollutants, the fluid dynamics method is used to calculate the air flow vector field.

[0081] Specific example: Consider a tunnel area with a length of 100 meters, a rectangular cross section, a width of 10 meters, and a height of 5 meters. Air enters through three air delivery points, located at the beginning, middle, and end of the tunnel. Air density ρ = 1.2 kg / m 3 , viscosity coefficient μ = 1.81 × 10 -5 Pa\cdotps, the inlet air speed is v 1 =5m / s(starting point), v 2 =3m / s(middle),v 3=4m / s (end). First, based on the geometric structure of the tunnel, the boundary conditions of air flow are defined: the wall of the tunnel is a no-slip boundary condition, and the air velocity at the wall is zero. Then, using the Navier-Stokes equation: Calculations are performed. Since there are multiple air input points in the tunnel, the flow of air will form a complex velocity field between the various air delivery points. Through numerical solution, combined with initial conditions and boundary conditions, the equations are discretized using the finite element method or the finite volume method, and the entire length and cross-section of the tunnel are meshed to gradually iterate and solve the air velocity and pressure field.

[0082] The final calculation results show that at the beginning of the tunnel, the air enters at a relatively fast speed of 5m / s. The air flow is restricted by the tunnel wall, and the speed gradually slows down as the air advances in the tunnel. In the middle of the tunnel, the air flow is disturbed due to the input of the second air delivery point, and the velocity vector field shows that the air forms a local turbulent zone in the middle area. At the end of the tunnel, the air is accelerated again through the third delivery point to form a more uniform flow. The final air flow vector field shows the speed and direction distribution of the air at various locations in the tunnel, providing an accurate basis for evaluating the diffusion of pollutants in the tunnel.

[0083] S2.2, for each pair of adjacent fused contaminated areas I and J, calculate the air flow correlation A between the two IJ The air flow correlation is the ratio of the air flow across the regional boundary, and the calculation formula is:

[0084] Among them, B IJ To merge the common boundary of polluted areas I and J, V n is the air velocity component along the normal direction, dl is the boundary element length, B I is the total boundary of the fused pollution area I, and |V| is the modulus of the air velocity.

[0085] S2.3, organize the air flow correlations between all fused pollution areas into a correlation matrix, and obtain the air flow correlation matrix A. The elements of the air flow correlation matrix A IJ represents the air flow correlation between the fused pollution areas I and J. The air flow correlation matrix is ​​a symmetric matrix that satisfies A IJ =A JI .

[0086] S2.4, using the air flow correlation matrix and the pollutant concentration gradient, calculate the propagation path of pollutants between the fused pollution areas. Use the shortest path algorithm or the maximum flow algorithm to determine the main path for pollutants to spread from high-concentration areas to low-concentration areas.

[0087] S2.5, for each pair of adjacent fused contaminated areas, based on the air flow correlation and concentration difference ΔC IJ =C I -C J , where C I and C J Represent the fused contaminated area R I and R J The average pollutant concentration is calculated to calculate the pollutant transfer coefficient T IJ :T IJ =A IJ ×f(ΔC IJ ), where f(ΔC IJ ) concentration difference influence factor, take f(ΔC IJ )=ΔC IJ .

[0088] The pollutant transfer coefficient is used to represent and quantify the actual transmission capacity of pollutants between adjacent areas, reflecting the potential for pollutant transmission under the combined effects of air flow, pressure gradient, and air exchange capacity. By combining these factors, the pollutant transfer coefficient reflects the efficiency of pollutant diffusion from high-pollution areas to low-pollution areas. The larger the transfer coefficient, the faster and more widely pollutants can diffuse to adjacent areas, and the air flow has a significant role in promoting the diffusion of pollutants; on the contrary, the smaller the transfer coefficient, the weaker the transmission capacity of pollutants, the insufficient driving effect of air flow, and the pollutants may be retained in local areas and their diffusion is restricted. This coefficient is not only used to predict the diffusion trend of pollutants in the tunnel, but also provides a data basis for dynamically adjusting ventilation strategies and preventing and controlling pollution accumulation in high-risk areas.

[0089] In a tunnel construction environment, the balance of air supply and the pressure difference between regions directly affect the diffusion speed and diffusion path of pollutants. In order to accurately evaluate the air flow conditions and pollutant transmission capacity of each area in the tunnel, the pressure modeling module conducts a refined analysis of the real-time pressure data of the air delivery point, establishes a pressure distribution model in the tunnel, and further calculates the air exchange capacity between regions. This module not only captures the air pressure dynamics inside each fused pollution area, but also analyzes the pressure difference between regions through the pressure gradient field, providing the key physical driving force for the diffusion of pollutants.

[0090] First, high-precision pressure sensors are used to collect real-time pressure data from each air delivery point in the tunnel to ensure real-time monitoring of air pressure conditions in different areas. Subsequently, a spatial interpolation algorithm is used to construct a pressure distribution model for the entire tunnel to generate a continuous pressure field. On this basis, the pressure gradient field is further calculated to quantify the rate and direction of pressure change at each point. Combined with the boundary information of the fused polluted area, the average pressure and pressure difference of each area are analyzed to provide an accurate basis for the air exchange capacity between regions. By combining aerodynamic parameters, the air exchange capacity coefficient of adjacent areas is finally determined, providing key parameter support for the calculation of the pollutant transmission coefficient.

[0091] The pressure modeling module includes the following processing steps:

[0092] S3.1, using high-precision pressure sensors deployed at each air delivery point to collect air supply pressure data P in real time s (x i ,y i ), where (x i ,y i ) is the spatial position of the i-th air delivery point, P s Indicates the air supply pressure value of the corresponding air delivery point. All pressure data are transmitted to the central processing unit via a high-speed data bus.

[0093] S3.2, based on the collected air supply pressure data and the spatial location of the air delivery point, a pressure distribution model P(x,y) in the tunnel is constructed. A spatial interpolation algorithm (such as Kriging interpolation or spline interpolation) is used to generate a continuous pressure distribution function in the entire tunnel space.

[0094] S3.3, calculate the gradient of the pressure distribution model and obtain the pressure gradient field Indicates the direction and rate of pressure change at each point in the tunnel. The pressure gradient field calculation formula is:

[0095] in, and are the partial derivatives of pressure along the x and y directions, respectively.

[0096] The pressure gradient field is used to represent and quantify the pressure change rate at each location in the tunnel, reflecting the pressure difference between different areas and the direction of change. By calculating the pressure gradient field, the driving force of air flow from high-pressure areas to low-pressure areas can be accurately reflected. The larger the value of the pressure gradient field, the more drastic the pressure change and the stronger the driving force of air flow; the smaller the value, the gentler the pressure change and the slower the air flow. The pressure gradient field is not only used to predict the direction and rate of air flow, but also provides a key basis for analyzing the driving effect of air flow on pollutant diffusion and optimizing ventilation systems.

[0097] S3.4, using the boundaries of the fused contaminated areas, calculate the average pressure inside each fused contaminated area and the pressure difference between the regions ΔP IJ , where I and J represent two adjacent fused contaminated areas. The average pressure calculation formula is:

[0098] Among them, A I is the area of ​​fusion region I. The regional pressure difference calculation formula is:

[0099] S3.5, calculate the air exchange capacity coefficient E between adjacent fusion areas based on the pressure gradient field and the pressure difference between the areas IJ . Combined with the ventilation cross-sectional area S between the areas IJ And aerodynamic parameters, the air exchange capacity coefficient is calculated as:

[0100] Among them, C d is the flow resistance coefficient, ρ is the air density, |ΔP rs | is the absolute value of the pressure difference.

[0101] The air exchange capacity coefficient is used to represent and quantify the air flow and exchange efficiency between adjacent areas, reflecting the ability of air to be transmitted across regional boundaries. This coefficient combines factors such as the pressure difference between regions, air flow velocity, and ventilation cross-sectional area. The larger the value, the smoother the air exchange between regions, and the more effectively the air flow can bring pollutants from one area to another; the smaller the value, the restricted air flow, insufficient air exchange, and increased risk of pollutants being retained in the area. The air exchange capacity coefficient is not only used to evaluate air mobility between regions, but also provides an important quantitative basis for optimizing ventilation strategies and improving pollutant diffusion control.

[0102] In a complex tunnel construction environment, the diffusion of pollutants depends not only on the intensity of air flow, but also on the multiple effects of pressure difference between regions and air exchange capacity. In order to accurately assess the risk of pollutant transmission between different regions, the risk calculation module establishes a set of nonlinear coupling calculation models by integrating pollutant transmission coefficients, pressure gradient fields and air exchange capacity coefficients. This module quantifies the pollutant transmission capacity between adjacent fused polluted areas and deeply analyzes the role of air flow in promoting pollutant diffusion, providing an important basis for the assessment of pollution risks.

[0103] The risk calculation module introduces nonlinear functions and cross terms to accurately capture the complex dynamics of pollutant transmission between regions. By combining the transmission potential coefficient with the air exchange capacity, the risk calculation module can not only limit the range of pollutant transmission coefficients and avoid over-amplification of calculation results, but also ensure the accuracy of pollutant transmission between regions. The output of this module not only reflects the actual transmission capacity of pollutants, but also provides reliable data support for subsequent risk level classification and optimization of ventilation control strategies.

[0104] The risk calculation module includes the following processing steps:

[0105] Based on the pollutant transmission coefficient T IJ , pressure gradient field and air exchange capacity coefficient E IJ For example, the following calculation formula is proposed, combining the hyperbolic tangent function (tanh) with the cross term for nonlinear coupling to obtain the pollutant transfer coefficient Φ IJ :

[0106] The hyperbolic tangent function tanh introduces nonlinear effects to limit the range of pollutant transfer coefficients, while enhancing the coupling effect between the transfer potential coefficient and the air exchange capacity to ensure that the calculated results will not be too large.

[0107] 1+|ΔP in the denominator IJ |Avoids calculation failure when the pressure difference is zero and smoothes the effect of pressure gradient.

[0108] Item 2 The regulation of air exchange capacity is introduced while avoiding linear superposition and increasing the complexity and flexibility of the transmission coefficient through cross-influence.

[0109] The pollutant transfer coefficient is used to represent and quantify the actual transmission capacity of pollutants between adjacent areas, reflecting the potential for pollutant transmission between different areas under the combined effects of air flow, pressure gradient and air exchange capacity. By combining multiple factors such as the intensity of air flow, pressure difference between areas and air exchange capacity, the diffusion efficiency of pollutants from one area to another is comprehensively evaluated. The larger the pollutant transfer coefficient, the stronger the transmission capacity of pollutants between adjacent areas, and the pollutants can diffuse from high-pollution areas to low-pollution areas at a faster speed and higher concentration, indicating that air flow and exchange have a significant promoting effect on pollutant diffusion; on the contrary, the smaller the coefficient, the weaker the pollutant transmission capacity, the poorer the effect of air flow on pollutant diffusion, and the higher the risk of pollutants being retained in local areas. Therefore, the pollutant transfer coefficient can not only be used to predict the diffusion trend of pollutants in the tunnel, but also provide a basis for dynamically controlling ventilation strategies to better prevent and control pollution accumulation in high-risk areas.

[0110] The risk segmentation module includes the following processing steps:

[0111] The pollutant transfer coefficient is compared with the low-level threshold and the high-level threshold respectively. When the pollutant transfer coefficient is less than or equal to the low-level threshold, it is delineated as a low-risk area and a low-risk signal is generated; when the pollutant transfer coefficient is greater than the low-level threshold and less than or equal to the high-level threshold, it is delineated as a medium-risk area and a medium-risk signal is generated; when the pollutant transfer coefficient is greater than the high-level threshold, it is delineated as a high-risk area and a high-risk signal is generated. In this way, the regional risks corresponding to different pollutant transfer coefficients are divided into levels, which can clarify the pollution diffusion risks of each area and facilitate the implementation of corresponding early warning and control measures.

[0112] The warning push module includes the following processing steps:

[0113] Early warning information includes low-risk signals, medium-risk signals and high-risk signals.

[0114] The risk signal, medium risk signal or high risk signal output by the risk classification module is pushed to relevant personnel through the smart terminal.

[0115] Through the intelligent air pollution monitoring system, dynamic and precise management of air pollution in the tunnel construction environment is achieved. By integrating the boundaries of the polluted area and the internal pollutant concentration distribution, combined with the principles of fluid dynamics and the Navier-Stokes equations, the system can accurately calculate the air flow vector field, revealing the air flow conditions and pollutant diffusion paths in the tunnel. By constructing a pressure gradient model, the pressure difference and air exchange capacity between each integrated pollution area are quantified, providing an important driving force analysis for the diffusion behavior of pollutants.

[0116] In addition, the present invention uses a nonlinear coupling calculation model to comprehensively consider the air flow correlation, pressure gradient field and air exchange capacity coefficient, accurately calculate the pollutant transmission coefficient, and quantify the actual transmission capacity of pollutants between adjacent areas. Through real-time calculation and analysis of the pollutant transmission coefficient, the system can dynamically evaluate and grade the pollution risk according to the preset threshold value, and timely identify high pollution risk areas. Early warning information is pushed in real time through smart terminals, allowing relevant personnel to respond quickly and take countermeasures.

[0117] Overall, the present invention effectively improves the accuracy and response speed of air pollution monitoring, optimizes the ventilation strategy in the tunnel, reduces energy consumption, ensures the rapid dilution and safe diffusion of pollutants, and protects the health of construction workers and the safety of the construction site.

[0118] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0119] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

[0120] It should be noted that, in this article, if there are relational terms such as first and second, etc., they are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "including a..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0121] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. An intelligent monitoring system for construction environment pollution, characterized in that: include: Integrate regional module, correlation analysis module, pressure modeling module, risk calculation module, risk classification module and early warning push module; Fusion area module: obtains pollution data of each air delivery point, merges similar and adjacent pollution areas, and obtains fused pollution areas; Output the fused pollution area and pass it to the correlation analysis module and pressure modeling module; Correlation analysis module: constructs air flow correlation matrix based on fused pollution areas; Output the correlation matrix and pass it to the risk calculation module; Pressure modeling module: collects air supply pressure data, establishes pressure gradient field, analyzes and calculates air exchange capacity coefficient; outputs pressure gradient field and air exchange capacity coefficient, and transmits them to risk calculation module; Risk calculation module: Calculate the pollutant transmission coefficient between each fused pollution area based on the correlation matrix, pressure gradient field and air exchange capacity coefficient to quantify the risk of pollutant transmission; Output pollutant transfer coefficient and pass it to the risk classification module; Risk classification module: using risk assessment algorithm, based on pollutant transmission coefficient, the risk level of the fusion area is classified and early warning information is generated; Output warning information and pass it to the warning push module; Early warning push module: Update early warning information in real time and push it to relevant personnel through smart terminals to achieve dynamic monitoring of high-risk areas.

2. The intelligent monitoring system for construction environment pollution according to claim 1 is characterized by: The fused region module includes the following processing steps: S1.1, using multi-dimensional pollution sensors deployed at each air delivery point to collect real-time data on pollutants in the air; S1.2, based on the real-time collection of pollutant data in the air, a multi-dimensional pollution matrix is ​​constructed, where each dimension corresponds to the type and concentration value of pollutants at an air delivery point; S1.3, similarity calculation is performed on the pollution data of each air delivery point, and comparison is made using the difference threshold of pollutant concentration, type combination and time series change; the pollution similarity between adjacent air delivery points is evaluated by weighted similarity algorithm, and the calculation results generate a set of pollution similarity indicators to determine the similarity degree of pollution in each area; S1.4, based on the geographical location data and pollution similarity index of the air delivery points, determine whether each air delivery point belongs to a bordering area; use a spatial geometric analysis algorithm to calculate the relative distance between the air delivery points and determine whether the point pairs within the preset threshold range are bordering; S1.5, the pollution areas covered by the air delivery points that meet the similarity standards and are adjacent to each other are merged to generate a merged pollution area.

3. The intelligent monitoring system for construction environment pollution according to claim 2 is characterized by: The fusion region module also includes the following processing steps: S1.6, generating the boundary of the fused pollution area based on the geographical location data and pollutant data of the fused pollution area; the specific process is as follows: Based on the geographical location of the air delivery point, a two-dimensional spatial layout matrix is ​​constructed. Each point in the matrix corresponds to the coordinates of an air delivery point. Let the elements in the matrix be L(x i ,y i ), represents the coordinate position of the ith air delivery point, where x i and i are the horizontal and vertical coordinates of the corresponding air delivery points respectively; According to the pollutant concentration at each air delivery point, a pollutant concentration gradient field G(x, y) is established; each position point C(x, y) in the pollutant concentration gradient field is calculated by concentration gradient to reflect the change of pollutant concentration at the air delivery point; the gradient calculation formula is: Where C(x, y) represents the pollutant concentration at the air delivery point (x, y), is the concentration gradient, which indicates the rate of change of concentration in the x and y directions; The boundary fitting algorithm is used to determine the boundary of the polluted area using the spatial layout matrix and the pollutant concentration gradient field. The boundary condition is determined by the concentration gradient threshold G threshold Control, when the concentration gradient satisfies: It is regarded as the critical point of the regional boundary; by fitting the change of pollutant concentration, the effective boundary range B(x, y) of the polluted area is calculated; The boundaries of similar and adjacent polluted areas are merged to generate a new polluted area boundary, that is, the boundary B of the merged polluted area fusion (x, y): in and They are the boundaries of adjacent polluted areas r1 and r2 respectively, and Union is the union operation of the boundaries to generate the boundaries of the complete fused polluted area.

4. The intelligent monitoring system for construction environment pollution according to claim 3 is characterized by: The association analysis module includes the following processing steps: S2.1, based on the boundary of the fused pollution area and the internal pollutant concentration distribution, using the principles of fluid dynamics, calculate the air flow vector field V(x, y) in each area; S2.2, for each pair of adjacent fused contaminated areas I and J, calculate the air flow correlation A between the two IJ ; The air flow correlation is the ratio of the air flow across the regional boundary, and the calculation formula is: Among them, B IJ To merge the common boundary of polluted areas I and J, V n is the air velocity component along the normal direction, dl is the boundary element length, B I is the total boundary of the fused pollution area I, |V| is the modulus of the air velocity; S2.3, organize the air flow correlations between all fused pollution areas into a correlation matrix, and obtain the air flow correlation matrix A. The elements of the air flow correlation matrix A are IJ Represents the air flow correlation between the fused polluted areas I and J; the air flow correlation matrix is ​​a symmetric matrix that satisfies A IJ =A JI ; S2.4, using the air flow correlation matrix and the pollutant concentration gradient, calculate the propagation path of pollutants between the fused pollution areas; S2.5, for each pair of adjacent fused contaminated areas, based on the air flow correlation and concentration difference ΔC IJ =C I -C J , where C I and C J Represent the fused contaminated area R I and R J The average pollutant concentration is calculated to calculate the pollutant transfer coefficient T IJ :T IJ =A IJ ×f(ΔC IJ ), where f(ΔC IJ ) concentration difference influence factor, take f(ΔC IJ )=ΔC IJ .

5. The intelligent monitoring system for construction environment pollution according to claim 4 is characterized by: The pressure modeling module includes the following processing steps: S3.1, using the pressure sensors deployed at each air delivery point to collect air supply pressure data P in real time s (x i ,y i ), where (x i ,y i ) is the spatial position of the i-th air delivery point, P s Indicates the air supply pressure value of the corresponding air delivery point; S3.2, constructing a pressure distribution model P(x, y) in the tunnel based on the collected air supply pressure data and the spatial position of the air delivery point; using a spatial interpolation algorithm to generate a continuous pressure distribution function in the entire tunnel space; S3.3, calculate the gradient of the pressure distribution model and obtain the pressure gradient field Indicates the direction and rate of pressure change at each point in the tunnel; the pressure gradient field calculation formula is: in, and are the partial derivatives of pressure along the x and y directions respectively; S3.4, using the boundaries of the fused contaminated areas, calculate the average pressure inside each fused contaminated area and the pressure difference between the regions ΔP IJ , where I and J represent two adjacent fused contaminated areas respectively; the average pressure calculation formula is: Among them, A I is the area of ​​fusion region I; the regional pressure difference calculation formula is: S3.5, calculate the air exchange capacity coefficient E between adjacent fusion areas based on the pressure gradient field and the pressure difference between the areas IJ ; Combined with the ventilation cross-sectional area S between regions IJ And aerodynamic parameters, the air exchange capacity coefficient is calculated as: Among them, C d is the flow resistance coefficient, ρ is the air density, |ΔP 仃 | is the absolute value of the pressure difference.

6. The intelligent monitoring system for construction environment pollution according to claim 5 is characterized by: The risk calculation module includes the following processing steps: Based on the pollutant transmission coefficient T IJ , pressure gradient field and air exchange capacity coefficient E IJ , the pollutant transport coefficient is obtained by combining the hyperbolic tangent function with the cross term for nonlinear coupling.

7. The intelligent monitoring system for construction environment pollution according to claim 6 is characterized by: The risk segmentation module includes the following processing steps: The pollutant transfer coefficient is compared with the low-level threshold and the high-level threshold respectively. When the pollutant transfer coefficient is less than or equal to the low-level threshold, it is defined as a low-risk area and a low-risk signal is generated; When the pollutant transfer coefficient is greater than the low-level threshold and less than or equal to the high-level threshold, it is delineated as a medium-risk area and a medium-risk signal is generated; When the pollutant transfer coefficient is greater than the advanced threshold, it is designated as a high-risk area and a high-risk signal is generated.

8. The intelligent monitoring system for construction environment pollution according to claim 7 is characterized by: The warning push module includes the following processing steps: The early warning information includes low-risk signals, medium-risk signals and high-risk signals; the risk signals, medium-risk signals or high-risk signals output by the risk classification module are pushed to relevant personnel through smart terminals.

Images