Airport atmosphere monitoring station comprehensive layout method

Abstract

The invention provides a comprehensive layout method for airport atmosphere monitoring stations, relates to the technical field of airport construction and atmospheric environment monitoring, and solves the limitation problems that a current site selection method is too subjective and does not have related algorithm or theoretical support. The method comprises the following steps: combining geographic coordinates of a plurality of key points of an airport with a Gaussian-Kruger projection theory, constructing a site selection coordinate system of an airport atmosphere monitoring station, and converting the geographic coordinates of the key points into coordinates of the site selection coordinate system; dividing the area where the airport is located into a gridding area, determining an optimization target of the comprehensive layout of the air monitoring stations of the airport according to the site selection coordinate system and the gridding area, and constructing a site selection model; an elite genetic algorithm is adopted to solve the optimization problem of the airport atmosphere monitoring station site selection model, and an airport atmosphere monitoring station comprehensive layout scheme is obtained; according to the method, the'islanding 'effect such as limited coverage range of a single monitoring point is broken, so that the monitoring station layout is more scientific and effective, and the monitoring result is more accurate.

Description

Technical Field

[0001] The present invention relates to the technical field of airport construction and atmospheric environment monitoring, and in particular to a comprehensive layout method of airport atmospheric monitoring sites. Background Art

[0002] With the rapid development of my country's civil aviation industry, the demand for air transportation has shown a significant growth trend. Faced with this challenge, airports, as key infrastructure in the air transportation system, must not only meet the growing demand for aircraft operations, but also actively respond to the resulting environmental protection pressure and promote the construction of green airports. In this context, effective monitoring of the airport's atmospheric environment has become one of the important means to ensure flight safety, improve air quality, and promote sustainable development.

[0003] The reasonable site selection of airport atmospheric monitoring stations is directly related to the effectiveness and economy of monitoring results. The traditional manual experience method relies on the subjective judgment of airport operators and combines factors such as topography and meteorological conditions to select the location of monitoring stations. Although this method can meet basic needs to a certain extent, due to its strong subjectivity and low efficiency, it is difficult to adapt to the requirements of modern airports for precise and intelligent management. In addition, due to the lack of systematic scientific basis, manual experience methods are prone to unreasonable site selection when facing complex and changeable environmental conditions, affecting the accuracy and reliability of monitoring results.

[0004] In order to solve the above problems, researchers proposed a knowledge-driven method. This method constructs a physical model to simulate the atmospheric flow around the airport and then determines the most suitable location of the monitoring station. This method not only takes into account the influence of natural factors such as topography and meteorology, but also combines the principles of aerodynamics to improve the scientificity and rationality of site selection. However, the knowledge-driven method also faces some limitations, such as high complexity of model construction and high consumption of computing resources. Especially in the process of pursuing model accuracy, some simplified assumptions are often needed, which may lead to a certain deviation between the final site selection plan and the actual situation.

[0005] In recent years, with the development of big data technology and artificial intelligence, data-driven methods have gradually been applied to the site selection research of airport air monitoring stations. This method can automatically identify the optimal monitoring point location through deep learning and analysis of historical environmental data, achieving the goal of extracting valuable information from the data. Compared with the first two methods, the data-driven method has higher flexibility and adaptability, can respond quickly to environmental changes, and provide more accurate decision support. However, the existing data-driven methods are mainly aimed at the site selection of urban air monitoring stations. For applications in specific environments such as airports, further research and optimization are still needed to ensure that the site selection plan is more in line with actual needs.

[0006] It can be seen that although there are many methods available for the site selection of airport air monitoring stations, each method has its scope of application and limitations. Future research should develop a comprehensive site selection strategy suitable for the characteristics of airport environments to improve the efficiency and quality of air monitoring work and promote the green development of the civil aviation industry. Summary of the invention

[0007] Based on the current status of the background technology, the purpose of the present invention is to solve the limitation problems that the current airport atmospheric monitoring site selection method is too subjective and has no relevant algorithm or theoretical support, so a comprehensive layout method of airport atmospheric monitoring sites is proposed. The present invention determines the optimal site location of the atmospheric monitoring site through theoretical calculation and grid coverage; for the traditional subjective site selection method, the present invention will break the "island" effect such as the limited coverage of a single monitoring point, significantly enhance the overall efficiency of the monitoring network, realize the blind spot filling of multiple monitoring points, strengthen the linkage between monitoring points, make the layout of monitoring sites more scientific and effective, and the monitoring results more accurate, so it has good application prospects.

[0008] The present invention adopts the following technical solutions to achieve the purpose:

[0009] A comprehensive layout method for airport air monitoring sites comprises: combining the geographical coordinates of multiple key points of the airport with the Gauss-Kruger projection theory to construct a site selection coordinate system for the airport air monitoring sites, and converting the geographical coordinates of the key points into coordinates of the site selection coordinate system for the air monitoring sites; dividing the area where the airport is located into a gridded area containing multiple grids, determining the optimization target of the comprehensive layout of the airport air monitoring sites according to the site selection coordinate system and the gridded area, and constructing a site selection model for the airport air monitoring sites; and using an elite genetic algorithm to solve the optimization problem corresponding to the site selection model for the airport air monitoring sites, and obtaining a comprehensive layout plan for the airport air monitoring sites.

[0010] Furthermore, the method comprises the following steps:

[0011] S1. Based on the airport surface structure, airport oil depot area and the distribution of typical air pollution sources, identify multiple key points of the airport and their geographical coordinates, combine the Gauss-Kruger projection theory, construct the airport air monitoring site selection coordinate system, and convert the key point geographical coordinates into the air monitoring site selection coordinate system coordinates;

[0012] S2. Construct a site selection model for airport atmospheric monitoring stations: divide the airport area into a gridded area containing multiple non-overlapping grids, and regard the grids whose center points are located inside and on the edge of the figure surrounded by multiple key points, as well as the grids where the key points are located, as grids to be deployed; the optimization goal is to minimize the number of grids to be deployed and minimize the distance between the key points and the center points of the grids;

[0013] S3. Formulate coding rules for the site selection plan, and initialize different coding solutions of the optimization problem corresponding to the site selection plan in the elite genetic algorithm;

[0014] S4, decoding the generated different coding solutions, calculating the objective function value of each coding solution individual and using it as fitness;

[0015] S5, select individuals with different coding solutions in the population to form the parent population;

[0016] S6. Perform crossover and mutation operations on the coding solution chromosomes between the parent populations to obtain the offspring population, and similarly calculate the fitness of each coding solution individual in the offspring population;

[0017] S7, merge the offspring population with the parent population to form a new population; retain the elite population in the new population according to the fitness of each coding solution individual in the new population;

[0018] S8, return to step S5, reselect and form a parent population, and repeat the crossover inheritance and mutation operations until the maximum number of iterations is reached;

[0019] S9, output the individual with the best fitness in the current population;

[0020] S10. After decoding the best individual, the site selection location of the airport atmospheric monitoring station is obtained and output as the corresponding comprehensive layout plan.

[0021] In summary, due to the adoption of this technical solution, the beneficial effects of the present invention are as follows:

[0022] The method proposed in this invention aims to overcome the limitations of existing site selection methods, such as strong subjectivity and lack of scientific algorithms or theoretical support. By introducing theoretical calculation and grid coverage technology, this invention can more accurately and intuitively determine the optimal location of the atmospheric monitoring station, showing higher scientificity and effectiveness compared to the traditional subjective site selection method.

[0023] Specifically, the present invention first collects detailed data on the airport surface structural parameters, the distribution of the oil depot area, and the typical air pollution areas, including but not limited to the runway length, width, direction, airport reference point, and the specific location of the oil depot area, and clarifies the key points and their geographic coordinates. On this basis, the airport reference point is taken as the origin O, and the Gauss-Kruger projection theory is combined to construct a coordinate system for the site selection of the airport atmospheric monitoring station. Through this coordinate system, key monitoring points such as the airport runway head end point and the oil depot area center point can be accurately located and projected onto plane coordinates. Next, the present invention uses a gridding method to comprehensively cover the entire airport area. By comprehensively evaluating the environmental factors in different grid cells, the suitability of each grid cell as a monitoring site is calculated, and finally a point layout scheme that can achieve optimal coverage of all key points is determined.

[0024] The comprehensive layout method proposed in the present invention not only solves the "island" effect such as the limited coverage of a single monitoring point, but also significantly enhances the overall efficiency of the monitoring network, realizes blind spot filling of multiple monitoring points, and strengthens the linkage between monitoring points. Through scientific and reasonable site layout, the perception ability and response speed to changes in the airport's atmospheric environment can be effectively improved, providing strong data support for the airport's environmental protection management and flight safety. In addition, the application of the present invention is not limited to the planning stage of new facilities, but is also suitable for upgrading and renovating the atmospheric monitoring system of existing airports, showing broad application prospects and high practical value. Therefore, the method of the present invention is of great significance for promoting the green development of airports and protecting public health. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 It is a schematic diagram of the overall process of the method of the present invention;

[0026] Figure 2 This is a schematic diagram of geographical coordinates of key points of an airport according to an example of the present invention;

[0027] Figure 3 A schematic diagram of the coordinate system for selecting the site of an airport atmospheric monitoring station according to an example of the present invention;

[0028] Figure 4 It is a schematic diagram of iterative solution of the site selection optimization problem exemplified in the present invention;

[0029] Figure 5 This is a schematic diagram of the comprehensive layout of airport atmosphere monitoring stations according to an example of the present invention. DETAILED DESCRIPTION

[0030] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the parts of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0031] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. 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.

[0032] Example 1

[0033] A comprehensive layout method for airport air monitoring sites, the core content of the method is: based on the airport surface structure, the airport oil depot area and the distribution of typical air pollution sources, multiple key points of the airport and their geographical coordinates are clarified, and the airport air monitoring site selection coordinate system is constructed in combination with the Gauss-Kruger projection theory, and the key point geographical coordinates are converted into the coordinates of the air monitoring site selection coordinate system; the airport area is divided into a gridded area containing multiple grids, and the optimization target of the comprehensive layout of the airport air monitoring site is determined based on the site selection coordinate system and the gridded area, and an airport air monitoring site selection model is constructed; an elite genetic algorithm is used to solve the optimization problem corresponding to the airport air monitoring site selection model, and a comprehensive layout plan for the airport air monitoring site is obtained.

[0034] In this embodiment, you can refer to Figure 1 The process diagram is given, and the method can be divided into multiple steps, as shown below:

[0035] S1. Identify key points and construct the coordinate system for the site selection of airport air monitoring stations: Based on the airport surface structure, the airport oil depot area and the distribution of typical air pollution sources, the two ends of the airport runway head and the center point of the oil depot area are taken as key points; the airport reference point is taken as the origin O, and based on the Gauss-Kruger projection theory, the corresponding X-axis is established in the direction parallel to the y-axis in the Gauss-Kruger projection coordinate system, and the corresponding Y-axis is established in the direction parallel to the x-axis in the Gauss-Kruger projection coordinate system, so as to obtain the site selection coordinate system of the airport air monitoring station, and the coordinates of the key points are converted into the corresponding coordinates in the site selection coordinate system;

[0036] S2. Construct a site selection model for airport atmospheric monitoring stations: divide the airport area into a gridded area containing multiple non-overlapping grids, and regard the grids whose center points are located inside and on the edge of the figure surrounded by multiple key points, as well as the grids where the key points are located, as grids to be deployed; the optimization goal is to minimize the number of grids to be deployed and minimize the distance between the key points and the center points of the grids;

[0037] S3. Formulate coding rules for the site selection plan, and initialize different coding solutions of the optimization problem corresponding to the site selection plan in the elite genetic algorithm;

[0038] S4, decoding the generated different coding solutions, calculating the objective function value of each coding solution individual and using it as fitness;

[0039] S5, select individuals with different coding solutions in the population to form the parent population;

[0040] S6. Perform crossover and mutation operations on the coding solution chromosomes between the parent populations to obtain the offspring population, and similarly calculate the fitness of each coding solution individual in the offspring population;

[0041] S7, merge the offspring population with the parent population to form a new population; retain the elite population in the new population according to the fitness of each coding solution individual in the new population;

[0042] S8, return to step S5, reselect and form a parent population, and repeat the crossover inheritance and mutation operations until the maximum number of iterations is reached;

[0043] S9, output the individual with the best fitness in the current population;

[0044] S10. After decoding the best individual, the site selection location of the airport atmospheric monitoring station is obtained and output as the corresponding comprehensive layout plan.

[0045] Example 2

[0046] Based on Example 1, this example introduces in detail the details contained in each specific step of the method, and demonstrates the method process with specific data examples.

[0047] This embodiment uses theoretical calculation and analysis to scientifically calculate the location of the airport atmospheric monitoring station, thereby providing a decision-making reference for the comprehensive collection of airport atmospheric environment data. First, in the process of data collection and processing, relevant parameters such as the airport surface structure, the airport oil depot area and the distribution of typical atmospheric pollution sources are collected to derive the geographical coordinates of key points such as the airport reference point and the airport runway head end point and the oil depot center point.

[0048] Sample data and airport scene are as follows Figure 2As shown, point 0 is the airport reference point, points 1 and 2 are the two ends of the existing runway, points 5 and 6 are the two ends of the new runway, and points 3 and 4 are the center points of the oil depot area. The coordinates of each point are: point 0 (0, 0), point 1 (-848.2, -1067.7), point 2 (1459.2, 1107.3), point 3 (-718.6, 1284.4), point 4 (152.9, -3054.4), point 5 (2943, -523.9), point 6 (2753.3, -1777).

[0049] First, in step S1, based on the Gauss-Krüger projection coordinate system, the airport reference point A is taken as the origin O, and the corresponding X-axis is established in the direction parallel to the y-axis in the Gauss-Krüger projection coordinate system, and the corresponding Y-axis is established in the direction parallel to the x-axis in the Gauss-Krüger projection coordinate system, so as to obtain the site selection coordinate system of the airport atmospheric monitoring station, as shown in Figure 3 As shown; multiple key points of the airport include the end points of the airport runway (points 1, 2, 5, and 6) and the center points of the oil depot area (points 3 and 4). The coordinates of the key points are converted into corresponding coordinates in the site selection coordinate system.

[0050] In step S2, the grid of this embodiment is a square grid; a point is randomly selected in a circle with the airport reference point A as the center and a radius of r1. in:

[0051]

[0052] θ1 is the polar angle of point M1; square C1 is generated as follows: point M1 is used as the diagonal center of square C1, the side length of square C1 is r2, and any vertex of the square is selected and marked as Based on this vertex, record the other vertices in a clockwise or counterclockwise direction as Then the diagonal points are connected The angle between the positive direction of the X-axis of the atmospheric monitoring station’s site selection coordinate system and the positive direction of the X-axis is θ2;

[0053] Move point M1 along the edge In a certain direction parallel to the square, the square is translated in sequence according to the spacing of r2. After a total of n translations, n new square diagonal centers are obtained, and squares C are generated in sequence in the same way as square C1. k (k=2,3,...,n+1); then move point M1 along the edge Repeat the above operation on the other side of the square to obtain n new diagonal centers of the squares, generating square C. k (k=n+2,n+3,...,2n+1).

[0054] Next, for the existing squares C1 to C2n+1 , first move the diagonal center point along the edge In a certain direction parallel to the original image, the image is translated in sequence according to the spacing of r2. After a total of n translations, we get 2n 2 +n new square diagonal centers, and generate squares C in the same way as square C1 k (k=2n+2,...,2n 2 +3n+1); similarly for the square C1 to C 2n+1 , and then align the center point of its diagonal line along the edge Repeat the above operation on the other side parallel to the original direction, and you will get 2n 2 +n new square diagonal centers, generating square C k (k=2n 2 +3n+2,...,4n 2 +4n+1).

[0055] Each square is regarded as a grid, and the grids are numbered in sequence, denoted as W j (j=1,2,...,4n 2 +4n+1), the center point of the grid, that is, the center point of the diagonal of the corresponding square, is used as the monitoring station deployment point M j ; Multiple key points of the airport are recorded as K i After that, construct a set V, whose elements are key points K i The number of the grid where the site is located is j; and the total number of grids to be deployed is recorded as N2.

[0056] The above content is the data collection and processing process performed in this embodiment, and the location of the atmospheric monitoring station will be determined based on it next.

[0057] Similarly, in step S2, the key coordinates of the airport runway head end point, the center point of the oil depot area, and the grid parameters of the airport and its surrounding areas in the processed Gauss-Kruger projection coordinate system are input into the constructed airport atmospheric monitoring site selection model, and the optimization problem is as follows:

[0058]

[0059] st:

[0060]

[0061] N2=Q+k

[0062]

[0063] In the optimization problem, Q is the number of grids whose center points are located inside and on the edge of the graph surrounded by multiple key points, and k is the number of grids where the key points are located; Dij is the key point K i The distance from the center point of the grid, that is, the monitoring station deployment point M j The distance between i Is the artificial coefficient.

[0064] In step S3, the coding information in the coding rule includes the angle and distance of the monitoring site; the angle and distance parameters are encoded in the form of direct coding, as follows:

[0065] Chromosome p i (i=1,2,...,N P ) consists of gene fragments [x], [f], N P is the total number of initial chromosomes; gene fragment [x] includes parameters r1, r2, θ1, θ2, where θ1 = 2π*randi[0,1], θ2 = 2π*randi[0,1], r1 = randi(0,w1], r2 = randi(0,w2], randi represents a random number in a specified interval, w1 and w2 are artificial parameters (w2 is set comprehensively considering the coverage of a single monitoring site), which are 1000 and 1500 respectively; fragment [f] is parameter F, and F is the fitness value of the individual of the coding solution; from this N P After the chromosomes form the initial population P0, the fitness values ​​of all coding solution individuals in the initial population are set to 0.

[0066] In step S4, the fitness function of each coding solution individual is constructed as follows:

[0067]

[0068] In the formula, F is the fitness value of the individual encoding solution, λ1 is 1, λ2 is 100, and λ3 is 1; for chromosome p i , after calculating its fitness value, update the chromosome p i The corresponding gene fragment in [f].

[0069] In step S5, after determining the capacity of the pairing pool (such as N / 2), two different coding solution individuals are randomly selected from the initial population P0, and the coding solution individual with the smaller fitness value is added to the pairing pool; if the fitness values ​​of the two coding solution individuals are the same, one of them is randomly selected to be added to the pairing pool; this operation is repeated until the pairing pool capacity is full, forming the parent population P1.

[0070] In step S6, the process of crossover genetic operation is: select chromosomes p in pairs from the parent population P1 v and p v+1 , if the crossover probability p is satisfied c , then the two are cross-operated to enhance population diversity; the corresponding fragments [xv ] and [x v+1 ] are exchanged, where q is a random number in a preset interval; all coding solution individuals after the crossover operation are recorded as the offspring population P2, the fitness values ​​of the corresponding coding solution individuals are calculated, and the corresponding gene fragments [f] in their chromosomes are updated.

[0071] Similarly, in step S6, the mutation operation process is as follows: for each coding solution individual in the offspring population P2, if the mutation probability p is satisfied m , then perform a mutation operation on it and change its chromosome p d Corresponding gene fragment [x d The s-th gene mutation on ] is the s-th row element of the matrix g, and the matrix g is as follows:

[0072]

[0073] All coding solution individuals after the mutation operation are recorded as the offspring population P3, the fitness value of the corresponding coding solution individual is calculated, and the corresponding gene fragment [f] in its chromosome is updated.

[0074] In step S7, the parent population P1 and the child population P3 are merged, and after being sorted in descending order of fitness value, the top N P The chromosomes corresponding to the coded solution individuals constitute a new population P4.

[0075] In step S8, the crossover genetic and mutation operations are repeated until the maximum number of iterations G is reached. At this time, the newly obtained population P4 is the optimal solution set. Figure 4 The fitness decrease curve corresponding to the iteration situation of this embodiment.

[0076] In step S9, the individual with the best fitness is selected from the optimal solution set.

[0077] In step S10, the key parameters of the individual with the best fitness, i.e., r1, r2, θ1, θ2, are output. Combined with the generation rules of the gridded area, the recommended site selection of the airport air monitoring station is determined, and then the monitoring network is drawn to form a comprehensive layout plan of the airport air monitoring station for reference by the airport decision-making management and operation departments. In this embodiment, a total of 7 monitoring points are selected. The final site selection of the monitoring point is as follows: Figure 5 As shown, their coordinates in the atmospheric monitoring site selection coordinate system are: (-18.852, 974.328), (1459.18, 1107.31), (1421.55, 237.321), (2124.94, -1940.08), (684.538, -1203.08), (-52.469, -2643.47), (-755.859, -466.07).

Claims

1. A comprehensive layout method for airport air monitoring sites, characterized in that: The geographical coordinates of multiple key points of the airport are combined with the Gauss-Krüger projection theory to construct the site selection coordinate system of the airport atmospheric monitoring station, and the geographical coordinates of the key points are converted into the coordinates of the site selection coordinate system of the atmospheric monitoring station; the area where the airport is located is divided into a gridded area containing multiple grids, and the optimization target of the comprehensive layout of the airport atmospheric monitoring station is determined based on the site selection coordinate system and the gridded area, and a site selection model for the airport atmospheric monitoring station is constructed; the elite genetic algorithm is used to solve the optimization problem corresponding to the site selection model of the airport atmospheric monitoring station, and a comprehensive layout plan for the airport atmospheric monitoring station is obtained.

2. The comprehensive layout method of airport atmosphere monitoring sites according to claim 1 is characterized by: The method comprises the following steps: S1. Based on the airport surface structure, airport oil depot area and the distribution of typical air pollution sources, multiple key points of the airport and their geographical coordinates are identified, and the airport air monitoring station site selection coordinate system is constructed in combination with the Gauss-Kruger projection theory. The geographical coordinates of multiple key points of the airport are converted into the coordinates of the airport air monitoring station site selection coordinate system; S2. Constructing the site selection model for airport atmospheric monitoring stations: Divide the area where the airport is located into a gridded area containing multiple non-overlapping grids, and regard the grids whose center points are located inside and on the edge of the figure surrounded by multiple key points, as well as the grids where the key points are located, as the grids to be deployed; The optimization goal is to minimize the number of grids to be deployed and the distance between the key points and the center points of the grids. S3. Formulate coding rules for the site selection plan, and initialize different coding solutions of the optimization problem corresponding to the site selection plan in the elite genetic algorithm; S4, decoding the generated different coding solutions, calculating the objective function value of each coding solution individual and using it as fitness; S5, select individuals with different coding solutions in the population to form the parent population; S6. Perform crossover and mutation operations on the coding solution chromosomes between the parent populations to obtain the offspring population, and similarly calculate the fitness of each coding solution individual in the offspring population; S7, merge the offspring population with the parent population to form a new population; retain the elite population in the new population according to the fitness of each coding solution individual in the new population; S8, return to step S5, reselect and form a parent population, and repeat the crossover inheritance and mutation operations until the maximum number of iterations is reached; S9, output the individual with the best fitness in the current population; S10. After decoding the best individual, the site selection location of the airport atmospheric monitoring station is obtained and output as the corresponding comprehensive layout plan.

3. The comprehensive layout method of airport atmosphere monitoring sites according to claim 2 is characterized by: In step S1, based on the airport surface structure, the airport oil depot area and the distribution of typical air pollution sources, the two ends of the airport runway head and the center point of the oil depot area are taken as key points; the airport reference point is taken as the origin O, and based on the Gauss-Krüger projection theory, the corresponding X-axis is established in the direction parallel to the y-axis in the Gauss-Krüger projection coordinate system, and the corresponding Y-axis is established in the direction parallel to the x-axis in the Gauss-Krüger projection coordinate system, so as to obtain the site selection coordinate system of the airport air monitoring station, and the coordinates of the key points are converted into corresponding coordinates in the site selection coordinate system.

4. The comprehensive layout method of airport atmosphere monitoring sites according to claim 2 is characterized by: In step S2, the grid is a square grid; a point is randomly selected in a circle with the airport reference point A as the center and a radius of r1. in: θ1 is the polar angle of point M1; square C1 is generated as follows: point M1 is used as the diagonal center of square C1, the side length of square C1 is r2, and any vertex of square C1 is selected and marked as Based on this vertex, record the other vertices in a clockwise or counterclockwise direction as Then the diagonal points are connected The angle between the positive direction of the X-axis of the atmospheric monitoring station’s site selection coordinate system and the positive direction of the X-axis is θ2; Move point M1 along the edge In a certain direction parallel to the square, the square is translated in sequence according to the spacing of r2. After a total of n translations, n new square diagonal centers are obtained, and squares C are generated in sequence in the same way as square C1. k (k=2,3,...,n+1); then move point M1 along the edge Repeat the above operation on the other side of the square to obtain n new diagonal centers of the squares, generating square C. k (k=n+2,n+3,...,2n+1); Next, for the existing squares C1 to C 2n+1 , first move the diagonal center point along the edge In a certain direction parallel to the original image, the image is translated in sequence according to the spacing of r2. After a total of n translations, we get 2n 2 +n new square diagonal centers, and generate squares C in the same way as square C1 k (k=2n+2,...,2n 2 +3n+1); similarly for the square C1 to C 2n+1 , and then align the center point of its diagonal line along the edge Repeat the above operation on the other side parallel to the original direction, and you will get 2n 2 +n new square diagonal centers, generating square C k (k=2n 2 +3n+2,...,4n 2 +4n+1); Each square is regarded as a grid, and the grids are numbered in sequence, denoted as W j (j=1,2,...,4n 2 +4n+1), the center point of the grid, that is, the center point of the diagonal of the corresponding square, is used as the monitoring station deployment point M j ; Multiple key points of the airport are recorded as K i After that, construct a set V, whose elements are key points K i The number of the grid where the station is located is j; after the total number of grids to be deployed is recorded as N2, the optimization problem of the airport atmospheric monitoring station site selection model is constructed as follows: In the optimization problem, Q is the number of grids whose center points are located inside and on the edge of the graph surrounded by multiple key points, and k is the number of grids where the key points are located; D ij is the key point K i and the center point of the grid, i.e. the monitoring station deployment point M j The distance between i Is the artificial coefficient.

5. The comprehensive layout method of airport atmosphere monitoring sites according to claim 4 is characterized by: In step S3, the coding information in the coding rule includes the angle and distance of the monitoring site; the angle and distance parameters are encoded in the form of direct coding, as follows: Chromosome p i (i=1,2,...,N P ) consists of gene fragments [x], [f], N P is the total number of initial chromosomes; the gene segment [x] includes parameters r1, r2, θ1, θ2, where θ1 = 2π*randi[0,1], θ2 = 2π*randi[0,1], r1 = randi(0,w1], r2 = randi(0,w2], randi represents a random number in a specified interval, w1 and w2 are artificial parameters; the segment [f] is parameter F, and F is the fitness value of the individual of the coding solution; from this N P After the chromosomes form the initial population P0, the fitness values ​​of all coding solution individuals in the initial population are set to 0.

6. The comprehensive layout method of airport atmosphere monitoring sites according to claim 4 is characterized by: In step S4, the fitness function of each coding solution individual is constructed as follows: In the formula, F is the fitness value of the individual encoding solution; for chromosome p i , after calculating its fitness value, update the chromosome p i The corresponding gene fragment in [f].

7. The comprehensive layout method of airport atmosphere monitoring sites according to claim 2 is characterized by: In step S5, after determining the capacity of the pairing pool, two different coding solution individuals are randomly selected from the initial population P0, and the coding solution individual with the smaller fitness value is added to the pairing pool; if the fitness values ​​of the two coding solution individuals are the same, one of them is selected and added to the pairing pool; this operation is repeated until the pairing pool capacity is full, forming the parent population P1.

8. The comprehensive layout method of airport atmosphere monitoring sites according to claim 2 is characterized by: In step S6, the process of crossover genetic operation is: select chromosomes p in pairs from the parent population P1 v and p v+1 , if the crossover probability p is satisfied c , then perform a cross operation on the two and convert the corresponding fragments [x v ] and [x v+1 ] are exchanged, where q is a random number in a preset interval; all coding solution individuals after the crossover operation are recorded as the offspring population P2, the fitness values ​​of the corresponding coding solution individuals are calculated, and the corresponding gene fragments [f] in their chromosomes are updated; The process of mutation operation is: for each coding solution individual in the offspring population P2, if the mutation probability p is satisfied m , then perform a mutation operation on it and change its chromosome p d Corresponding gene fragment [x d The s-th gene mutation on ] is the s-th row element of the matrix g, and the matrix g is as follows: All coding solution individuals after the mutation operation are recorded as the offspring population P3, the fitness value of the corresponding coding solution individual is calculated, and the corresponding gene fragment [f] in its chromosome is updated.

9. The comprehensive layout method of airport atmosphere monitoring sites according to claim 8 is characterized by: In step S7, the parent population P1 and the child population P3 are merged, and after being sorted in descending order of fitness value, the top N P The chromosomes corresponding to the coded solution individuals constitute a new population P4.

10. The comprehensive layout method of airport atmosphere monitoring sites according to claim 9, characterized in that: In step S8, the crossover genetic and mutation operations are repeated until the maximum number of iterations G is reached. At this time, the newly obtained population P4 is the optimal solution set. In step S9, the individual with the best fitness is selected from the optimal solution set; In step S10, the best individual parameters are output, and the recommended site selection location of the airport air monitoring station is determined in combination with the generation rules of the gridded area, and then the monitoring network is drawn to form a comprehensive layout plan for the airport air monitoring station.

Images