Pollution source dynamic tracing method and device for industrial park secret gas leakage

Abstract

The application discloses a kind of pollution source dynamic tracing methods and equipment for industrial park secret gas leakage;Including: by fixed monitoring equipment and / or mobile monitoring equipment, meteorological monitoring data is acquired at each observation point;Correct the coordinates of observation point;According to Gaussian plume diffusion model, the first gas pollutant prediction concentration corresponding to each observation point after correction coordinates is predicted;First gas pollutant prediction concentration, meteorological monitoring data are input into CatBoost model, and second gas pollutant prediction concentration is obtained;With the difference between actual gas pollutant concentration at each observation point and second gas pollutant prediction concentration as objective function, the objective function is solved to obtain pollutant source intensity, source location;Complete 1 iteration;Observation point is set in the vicinity of the current predicted pollutant source location, and so on, and after n iterations, the final pollutant source intensity, source location is obtained.

Description

Technical Field

[0001] This invention belongs to the field of environmental monitoring technology, and in particular relates to a method and equipment for dynamic source tracing of pollution sources for hidden gas leaks in industrial parks. Background Technology

[0002] In industrial parks, the emission of gaseous pollutants poses a serious threat to the ecological environment and human health. Traditional pollution source identification methods mainly rely on monitoring stations at fixed locations, which are insufficient to comprehensively and accurately capture the complex diffusion patterns of pollutants and cannot meet the need for rapid and accurate tracing of hidden gas leaks in industrial parks.

[0003] With the rapid development of industry, gas leaks occur frequently in industrial parks. These leaks may originate from hidden sources, and their source strength and location are difficult to determine. Therefore, a source tracing method is urgently needed to solve these problems. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides a method and equipment for dynamic source tracing of hidden gas leaks in industrial parks.

[0005] In a first aspect, embodiments of the present invention provide a method for dynamic source tracing of pollution sources for covert gas leaks in industrial parks, the method comprising:

[0006] Meteorological monitoring data are acquired at each observation point using fixed and / or mobile monitoring equipment.

[0007] Correct the coordinates of the observation points; predict the concentration of the first gaseous pollutant at each observation point after the coordinate correction based on the Gaussian plume diffusion model.

[0008] The predicted concentrations of the first gaseous pollutant and meteorological monitoring data are input into the CatBoost model to obtain the predicted concentrations of the second gaseous pollutant.

[0009] Using the difference between the actual gaseous pollutant concentration and the predicted concentration of the second gaseous pollutant at each observation point as the objective function, the objective function is solved to obtain the pollutant source strength and source location; the first iteration is completed.

[0010] By setting up observation points near the currently predicted pollutant source location using mobile monitoring equipment, and so on, the final pollutant source strength and location are obtained after n iterations.

[0011] Secondly, embodiments of the present invention provide an electronic device, including a memory and a processor, wherein the memory is coupled to the processor; wherein the memory is used to store program data, and the processor is used to execute the program data to realize the above-mentioned dynamic source tracing method for hidden gas leaks in industrial parks.

[0012] Thirdly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, wherein when the program is executed by a processor, it implements the above-described method for dynamic tracing of pollution sources for covert gas leaks in industrial parks.

[0013] Fourthly, embodiments of the present invention provide a computer program product, including a computer program / instruction, which, when executed by a processor, implements the above-described method for dynamic tracing of pollution sources for covert gas leaks in industrial parks.

[0014] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0015] This invention provides a dynamic source tracing method for hidden gas leaks in industrial parks. It acquires more comprehensive and accurate meteorological monitoring data through fixed and mobile monitoring equipment, providing a reliable basis for source tracing. By correcting the coordinates of observation points, the corrected coordinates are input into an improved Gaussian plume diffusion model to predict the initial predicted concentration of gaseous pollutants. This is then combined with meteorological monitoring data and a CatBoost model to simulate the diffusion of pollutants in the complex environment of the industrial park, further improving the accuracy of source tracing. The objective function is the difference between the actual gaseous pollutant concentration and the second predicted gaseous pollutant concentration at each observation point. This objective function is solved using wind direction factors, the GA algorithm, and the IPSO algorithm, effectively avoiding the problem of traditional algorithms easily getting trapped in local optima, and improving the accuracy and efficiency of pollution source location and intensity estimation. Furthermore, this invention can adjust the position of the mobile monitoring equipment. In each iteration, the position of the observation points is dynamically adjusted based on the pollution source location information obtained from the previous inversion calculation, further improving the accuracy of pollution source location and intensity estimation. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 A flowchart illustrating a method for dynamic source tracing of hidden gas leaks in industrial parks, provided in an embodiment of the present invention.

[0018] Figure 2 This is a schematic diagram of a method for dynamic source tracing of hidden gas leaks in industrial parks, provided by an embodiment of the present invention.

[0019] Figure 3 This is a schematic diagram of coordinate system transformation provided in an embodiment of the present invention;

[0020] Figure 4 A schematic diagram illustrating the equivalent height of the observation point provided in an embodiment of the present invention;

[0021] Figure 5 A schematic diagram of the improved Gaussian-CatBoost diffusion model (IG-CatBoost) provided in an embodiment of the present invention;

[0022] Figure 6 The flowchart of the hybrid wind direction factor-GA-IPSO algorithm provided in the embodiments of the present invention;

[0023] Figure 7 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0024] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0025] It should be noted that, unless otherwise specified, the features in the following embodiments and implementation methods can be combined with each other.

[0026] like Figure 1 and Figure 2 As shown, this embodiment of the invention provides a method for dynamic source tracing of pollution sources for covert gas leaks in industrial parks. The method includes the following steps:

[0027] Step S1: Obtain meteorological monitoring data at each observation point using fixed monitoring equipment and / or mobile monitoring equipment.

[0028] Specifically, in this example, fixed ground monitoring stations are deployed in the industrial park to be monitored to obtain basic meteorological monitoring data by utilizing their long-term stable monitoring characteristics; at the same time, mobile monitoring vehicles and drone monitoring equipment are equipped to flexibly adjust the monitoring positions according to the actual situation in the industrial park and to conduct intensified monitoring of key areas or suspected pollution areas.

[0029] Step S2: Correct the coordinates of the observation points; predict the first gaseous pollutant concentration corresponding to each observation point after the coordinate correction based on the Gaussian plume diffusion model.

[0030] Specifically, such as Figure 3 As shown, the process of correcting the coordinates of the observation point includes:

[0031] Perform a coordinate transformation on the observation point (x, y) in the geographic coordinate system to the observation point (x, y) in a coordinate system with wind direction as the abscissa. ′ ,y ′ The expression is as follows:

[0032]

[0033] In the formula, α is the angle between the wind direction and due north, (x0,y0) represents the pollution source point, and (x,y) represents the observation point;

[0034] like Figure 4 As shown, the equivalent height of the observation point is obtained based on the terrain elevation of the pollution source, the terrain elevation of the observation point, and the height of the gas sensor installed at the observation point from the ground; the expression is as follows:

[0035] z ′ [x,y]=z0[x0,y0]-z[x,y]+h z

[0036] In the formula, z ′ [x,y] represents the equivalent height of the observation point (x,y), z0[x0,y0] represents the topographic height of the pollution source point (x0,y0), z[x,y] represents the topographic height of the observation point (x,y), and h z This indicates the height of the gas sensor above the ground.

[0037] It should be noted that the improved Gaussian plume model significantly enhances the accuracy of pollutant diffusion simulation through coordinate transformation and equivalent height calculation. On one hand, the coordinates of observation points in the geographic coordinate system are transformed into a new coordinate system with wind direction as the abscissa, making the pollutant diffusion process under wind field influence more intuitive in the mathematical model and facilitating parameter calculation and physical law analysis. On the other hand, the equivalent height comprehensively considers the terrain height difference between the pollution source and the observation point, as well as the sensor's ground clearance, quantifying complex terrain factors into unified parameters and incorporating them into the model, effectively correcting the impact of terrain undulations on the vertical diffusion path of pollutants. These two improvements jointly optimize the applicability of the Gaussian plume model, enabling it to more realistically reflect the three-dimensional diffusion law of pollutants in the actual environment, providing a more accurate concentration prediction basis for subsequent pollution source location and source intensity inversion. Regarding the improvement of the wind direction coordinate axis, a geographic coordinate system is constructed with the gas release source as the origin. The midpoint of the geographic coordinate system is transformed to a coordinate system with wind direction as the abscissa through a rotation matrix, transforming the coordinates of point A(x,y) in the geographic coordinate system to a point A in the new wind-direction coordinate system. ′ (x ′ ,y ′ This makes calculating and simulating the wind diffusion process more intuitive and accurate.

[0038] like Figure 5As shown, the corrected coordinates of the observation points are input into the improved Gaussian plume diffusion model to predict the predicted concentration of the first gaseous pollutant corresponding to each observation point after coordinate correction; the expression of the improved Gaussian plume diffusion model is as follows:

[0039]

[0040] In the formula, C(x,y,z) represents the concentration at (x,y,z), and σ′ y σ′ represents the diffusion coefficient in the horizontal direction. z The vertical diffusion coefficient is represented by H, where H is the vertical height of the emission source from the ground, q represents the pollution source strength, and u represents the wind speed.

[0041] Step S3: Input the predicted concentration of the first gaseous pollutant and meteorological monitoring data into the CatBoost model to obtain the predicted concentration of the second gaseous pollutant.

[0042] Furthermore, the CatBoost model is based on the gradient boosting algorithm. Let the training dataset be... Where, x i Let y represent the feature vector of the i-th sample, which includes meteorological parameters (such as wind speed, wind direction, temperature, atmospheric stability, etc.), topographic parameters, and parameters related to the pollution source (such as release height, release rate, etc.). i Let N be the target value (i.e., gas concentration) and N be the total number of samples. This represents the initial prediction value of the CatBoost model. Typically, this is set to a constant (such as the mean), representing the predicted value of the CatBoost model in the t-th iteration. The predicted values ​​of the CatBoost model in the first t-1 iterations With the t-th decision tree h t (x i The sum of predicted values ​​is expressed as follows:

[0043]

[0044] Where, α t The weight of the t-th decision tree is determined by minimizing the loss function L. Commonly used loss functions include mean squared error (MSE). In each iteration, the prediction error (negative gradient) of the current CatBoost model is used as the basis for calculation. A new decision tree is fitted onto the residuals to gradually approximate the true model and improve prediction accuracy.

[0045] In gas diffusion problems, there are many categorical features, such as atmospheric stability level, wind direction, wind speed, and temperature. For the j-th category of categorical feature c, its conversion into a numerical feature is calculated as follows:

[0046]

[0047] in, For indicator functions, when The value is 1 when it equals j, and 0 otherwise. Let be the gradient value of the k-th sample in the t-th iteration, and Prior be the prior value (which can be set according to the data distribution).

[0048] Meanwhile, CatBoost employs a series of advanced techniques to prevent overfitting. Regarding regularization, it penalizes the complexity of the decision tree, for example, by controlling parameters such as the depth d of the decision tree and the number of leaf nodes m, and adding a regularization term to the loss function, as shown below:

[0049]

[0050] Where γ and λ are regularization coefficients, ω j Let be the weight of leaf node j.

[0051] It should be noted that in the IG-CatBoost model, the improved Gaussian plume model provides the CatBoost model with a preliminary gas concentration prediction based on a physical mechanism. The CatBoost model then performs nonlinear fitting and optimization on these preliminary prediction results. Through continuous iterative training, it utilizes its ability to handle complex data relationships and prevent overfitting to output a more accurate gas concentration prediction.

[0052] Step S4: Using the difference between the actual gaseous pollutant concentration and the predicted concentration of the second gaseous pollutant at each observation point as the objective function, solve the objective function to obtain the pollutant source strength and source location; complete one iteration.

[0053] In this example, the pollutant source tracing problem is transformed into a problem without extreme value constraints, thus constructing the objective function, as shown in the following expression:

[0054]

[0055] In the formula, Q0 represents the source release rate of the pollutant, (x0,y0,z0) represents the location of the pollutant, and n is the number of gas sensors; This represents the concentration of gaseous pollutants detected by the i-th gas sensor; This represents the predicted concentration of the second gaseous pollutant at the i-th gas sensor point, based on the output of the CatBoost model.

[0056] Furthermore, such as Figure 6 As shown, the process of solving the objective function to obtain the pollutant source strength and source location includes:

[0057] (1) Initialize the population and set the initial position and velocity of the particles;

[0058] (2) Calculate the fitness of each particle;

[0059] (3) Based on the GA algorithm, select particles with low fitness to enter the crossover and mutation stage, and generate new particles through crossover and mutation operations to increase the diversity of the population;

[0060] (4) Update inertia weights, particle velocity, and particle position; including:

[0061] The update formula for the inertia weight ω is:

[0062]

[0063] Where, ω max and ω min These are the initial and minimum inertia weights, k, respectively. max Here, k is the maximum number of iterations, and k is the current number of iterations.

[0064] The formula for updating particle velocity is:

[0065]

[0066] In the formula, ω is the velocity of the i-th particle, c1 and c2 are the acceleration constants, r1 and r2 are random numbers, and pbest is the velocity of the i-th particle. i It is the best position in the history of the i-th particle, gbest is the best position of all particles, r3 is a random number, and ω is the best position in the history of all particles. v It is the wind speed correction weight. It's wind speed.

[0067] (5) Re-evaluate the fitness of each particle, update the historical best position and global best position of the particle, and output the global optimal solution, that is, the estimated source strength and source location of the pollution source.

[0068] It should be noted that in this example, the objective function is the difference between the actual gaseous pollutant concentration and the predicted concentration of the second gaseous pollutant at each observation point. The objective function is solved by combining the wind direction factor, the GA algorithm, and the IPSO algorithm. This effectively avoids the problem of traditional algorithms easily getting trapped in local optima, improving the accuracy and efficiency of pollution source location and intensity estimation. Because the wind direction factor is considered, the movement of particles in the search space more closely matches the actual pollutant diffusion path, allowing for a more comprehensive exploration of the search space rather than being limited to a local area. This significantly improves the accuracy of pollution source location and intensity estimation, making the estimated pollution source intensity and location closer to reality. Simultaneously, because it more reasonably simulates the pollutant propagation and search process, it also improves the efficiency of the solution, enabling faster and more accurate results.

[0069] Step S5: Set the observation point near the currently predicted pollutant source location, and so on, until the final pollutant source strength and source location are obtained after n iterations.

[0070] It should be noted that mobile monitoring platforms (such as drones and mobile vehicle-mounted platforms), as the carriers for deploying gas sensors, dynamically adjust the location of observation points in each iteration based on the pollution source location information obtained from the previous inversion calculation. For example, if a pollution source is initially estimated to exist in a small area but the data is not accurate enough, the mobile monitoring platform can be moved to that area in the next iteration to collect more accurate data.

[0071] Accordingly, this application also provides an electronic device, including: one or more processors; a memory for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the above-described method for dynamic source tracing of hidden gas leaks in industrial parks. Figure 7 The diagram shown is a hardware structure diagram of any device with data processing capabilities used in the dynamic source tracing method for hidden gas leaks in industrial parks, as provided in this embodiment of the invention. (Except for...) Figure 7 In addition to the processor, memory, and network interface shown, any data processing device in the embodiment may also include other hardware depending on the actual function of the data processing device, which will not be described in detail here.

[0072] Accordingly, this application also provides a computer-readable storage medium storing computer instructions, which, when executed by a processor, implement the aforementioned method for dynamic source tracing of hidden gas leaks in industrial parks. The computer-readable storage medium can be an internal storage unit of any data-processing device as described in any of the foregoing embodiments, such as a hard disk or memory. The computer-readable storage medium can also be an external storage device, such as a plug-in hard disk, smart media card (SMC), SD card, flash card, etc., equipped on the device. Furthermore, the computer-readable storage medium can include both internal storage units of any data-processing device and external storage devices. The computer-readable storage medium is used to store the computer program and other programs and data required by the data-processing device, and can also be used to temporarily store data that has been output or will be output.

[0073] The above embodiments are only used to illustrate the design concept and features of the present invention, and their purpose is to enable those skilled in the art to understand the content of the present invention and implement it accordingly. The protection scope of the present invention is not limited to the above embodiments. Therefore, all equivalent changes or modifications made based on the principles and design ideas disclosed in the present invention are within the protection scope of the present invention.

Claims

1. A pollution source dynamic tracing method for industrial park-oriented secret gas leakage, characterized in that, The method comprises: acquiring meteorological monitoring data at each observation point by fixed monitoring equipment and / or mobile monitoring equipment; correcting the coordinates of the observation points; predicting the first predicted concentration of the gas pollutant corresponding to each observation point after correction of the coordinates according to a Gaussian plume diffusion model; inputting the first predicted concentration of the gas pollutant and the meteorological monitoring data into a CatBoost model to obtain a second predicted concentration of the gas pollutant; taking the difference between the actual concentration of the gas pollutant at each observation point and the second predicted concentration of the gas pollutant as an objective function, solving the objective function to obtain the source strength and source location of the pollutant, and completing the first iteration; setting the observation point near the currently predicted source location of the pollutant by the mobile monitoring equipment, and iteratively setting the observation point near the predicted source location of the pollutant after each iteration, to obtain the final source strength and source location of the pollutant after n iterations.

2. The method according to claim 1, wherein, The process of correcting the coordinates of the observation points comprises: The observation point (x, y) in the geographical coordinate system is converted to the observation point (x ′ ,y ′ ) in the coordinate system with the wind direction as the horizontal coordinate; the expression is as follows: wherein a is the angle between the wind direction and the north direction, (x0, y0) represents the pollution source point, and (x, y) represents the observation point; According to the terrain height of the pollution source point, the terrain height of the observation point, and the height of the gas sensor set at the observation point from the ground, the equivalent height at the observation point is obtained; the expression is as follows: z ′ [x,y] = z0[x0,y0] - z[x,y] + h z where z ′ [x, y] represents the equivalent height of the observation point (x, y), z0[x0, y0] represents the terrain height of the pollution source point (x0, y0), z[x, y] represents the terrain height of the observation point (x, y), h z represents the height of the gas sensor from the ground.

3. The method according to claim 1, wherein, The meteorological monitoring data includes wind direction, wind speed, temperature, and atmospheric stability.

4. The method according to claim 1, wherein, The expression of the objective function is as follows: In the formula, Q0 represents the source release rate of the pollutant, (x0, y0, z0) represents the position of the pollutant, and n is the number of gas sensors; represents the concentration of the gas pollutant detected by the ith gas sensor; is the corresponding second gas pollutant predicted concentration at the ith gas sensor point based on the CatBoost model output.

5. The method of claim 1, wherein, The process of solving the objective function to obtain the source strength and source location of the pollutant comprises: initializing the population, setting the initial position and velocity of the particles; calculating the fitness of each particle; selecting particles with lower fitness to enter the crossover and mutation stage, and generating new particles through crossover and mutation operations; updating the inertia weight, particle velocity, and particle position; re-evaluating the fitness of each particle, updating the historical best position and global best position of the particle, and outputting the global optimal solution, i.e., the estimated source strength and source location of the pollution source.

6. The method according to claim 5, wherein, The update formula of the inertia weight ω is: where ω max and ω min are the initial and minimum inertia weights, respectively, k max is the maximum number of iterations, and k is the current iteration number.

7. The method according to claim 5, wherein, The update formula of the particle velocity is: wherein is the velocity of the i-th particle, ω is the inertia weight, c1, c2 are acceleration constants, r1, r2 are random numbers, pbest i is the best position of the i-th particle in history, gbest is the best position of the whole particles, r3 is a random number, ω v is the wind speed correction weight, is the wind speed.

8. An electronic device comprising a memory and a processor, characterized in that The memory is coupled with the processor; wherein the memory is used to store program data, and the processor is used to execute the program data to realize the pollution source dynamic tracing method for hidden gas leakage in an industrial park according to any one of claims 1-7.

9. A computer readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to realize the pollution source dynamic tracing method for hidden gas leakage in an industrial park according to any one of claims 1-7.

10. A computer program product comprising computer programs / instructions, characterized in that, The computer program / instructions are executed by the processor to realize the pollution source dynamic tracing method for hidden gas leakage in an industrial park according to any one of claims 1-7.

Images