A Genetic Algorithm-Based Optimization Method for Airport Noise Monitoring Point Layout

Abstract

This invention discloses a method for optimizing the layout of airport noise monitoring points based on a genetic algorithm. The method involves dividing the monitoring area into grids based on a noise prediction contour map; calculating the distance from any point within the monitoring area to the monitoring point; defining the probability of whether a point is covered by a monitoring point; calculating the sensing probability based on distance and monitoring point reliability parameters; establishing a joint sensing probability model and calculating the area coverage rate; setting a coverage rate optimization objective function; introducing multi-objective constraints; and using a genetic algorithm to optimize the comprehensive benefit function. A dynamic point quantity control mechanism is introduced to gradually reduce the number of monitoring points, outputting a simplified monitoring point layout scheme while maintaining the coverage rate above a set threshold. The optimization process of this invention fully incorporates the actual airport point layout constraints, reducing the number of monitoring points and prioritizing the elimination of redundant points, while maintaining a relatively stable overall coverage rate, significantly reducing equipment installation, maintenance, and data processing costs.

Description

Technical Field

[0001] This invention relates to the field of airport noise monitoring and optimization, and in particular to a method for optimizing the number of monitoring points by combining intelligent algorithms and grid-based modeling techniques, falling under the category of environmental noise monitoring and intelligent monitoring point optimization technology. Background Art

[0002] Currently, the deployment of noise monitoring points in most airports is primarily based on experience or preliminary configuration using contour maps generated by noise prediction models. This deployment method has significant practical value in the early stages of airport operation: firstly, it helps verify the spatial distribution of aircraft noise contour lines, checking the accuracy and applicability of the prediction model; secondly, some monitoring points are not simply set up to collect routine noise data, but rather to cross-validate data from other monitoring points and check system errors, thus providing a reliable foundation for subsequent noise data interpretation and management strategy development. As airport operations stabilize, aircraft takeoff and landing methods and runway usage patterns gradually solidify, and the spatial distribution patterns of airport noise become increasingly clear. While the existing monitoring point layout meets basic operational needs, there is still room for optimization in terms of refined management and cost control. For example, data collected from some monitoring points is not sensitive enough to typical noise events, making it difficult to provide effective support for noise complaint responses; furthermore, the redundant number of points not only increases the system's data processing pressure but also raises equipment operation and maintenance costs.

[0003] Therefore, given the airport's sound operation and the fact that the existing noise monitoring layout basically meets the requirements of regulations and standards, there is an urgent need to explore a scientific and quantifiable point optimization strategy to improve the monitoring efficiency of key areas, enhance the value of data utilization, effectively reduce the overall operating cost of the system, and further support the airport's refined management and public communication efforts. Summary of the Invention

[0004] This invention aims to propose a method for optimizing the layout of airport noise monitoring points. This method can be used for initial site selection of noise monitoring points and for site adjustment and optimization during the operational phase, helping to more accurately grasp the noise pollution situation and its changing trends around the airport. The rational layout of noise monitoring points is a key aspect of airport noise monitoring management, and this invention focuses on the research of the layout of airport noise monitoring points.

[0005] The technical solution adopted in this invention is an airport noise monitoring point optimization layout method based on genetic algorithm, which includes the following steps:

[0006] S1. Based on the noise prediction contour map, identify the affected area with a noise level greater than 70 dB, mark the noise-sensitive buildings or village centers in the area, merge sensitive buildings with a distance of less than 3 km into a group, and take the center of the group as the initial monitoring point location.

[0007] S2. Construct a general grid sensitive area with a radius of 5 km centered on each cluster, and divide the monitoring area into grids;

[0008] S3. Calculate the distance from any point Q(x,y) within the monitoring area to the monitoring point. distance ;

[0009] S4. Define whether point Q(x,y) is a monitored point. Coverage discrimination probability If it can cover the area, the value is 1; otherwise, it is 0.

[0010] S5. Establish monitoring points Perceptual probability model Q for point Q(x,y) per (x,y,s), calculate the sensing probability based on distance and measurement point reliability parameters;

[0011] S6. Establish a joint sensing probability model Q for the same target from multiple monitoring points. per (N);

[0012] S7. Calculate the area coverage R area (N) serves as an indicator of the overall perception capability of the monitoring network over the monitored area.

[0013] S8. Set the coverage optimization objective function, discretize the monitoring area into a grid, and use the overall coverage as the optimization objective;

[0014] S9. Use a genetic algorithm for initial optimization, with the goal of maximizing coverage, to generate a preliminary monitoring point layout;

[0015] S10. Based on the initial optimization, multi-objective constraints are introduced to construct a comprehensive benefit function, including a weighted combination of coverage, distance to the flight path, and distance to the background noise source;

[0016] S11. The comprehensive benefit function is further optimized using a genetic algorithm;

[0017] S12. Introduce a dynamic monitoring point quantity control mechanism to gradually reduce the number of monitoring points and output a simplified monitoring point layout scheme while maintaining the coverage rate at or above the set threshold.

[0018] Furthermore, in step S1, the noise prediction contour map is generated using INM software.

[0019] Furthermore, in step S5, the perceptual probability model is a piecewise function:

[0020] When d( ,q) ≤ r - re At that time, the probability of perception is 1;

[0021] When r - r e < d( ,q) < r + r e At that time, the probability of perception is:

[0022] ;

[0023] Where, r e This is a measure of the ability to monitor uncertainties at noise measurement points. Parameters , It is the attenuation coefficient, which controls the overall rate at which sensing ability decreases with increasing distance. It is the perception decay index. It is used to control the shape of the decay curve of the perception probability in the transition region.

[0024] Furthermore, in step S6, the joint sensing probability model is:

[0025] ;

[0026] Furthermore, in step S7, the formula for calculating the area coverage rate is:

[0027] ;

[0028] Where m×n represents the total number of grids in the monitoring area.

[0029] Furthermore, in step S10, the comprehensive benefit function is:

[0030] ;

[0031] in, The distance between the monitoring point and the aircraft's flight path. D represents the distance of the monitoring point from the background noise source. max ω1, ω2, and ω3 are normalization constants and weighting coefficients.

[0032] Furthermore, in step S12, the dynamic point quantity control mechanism includes:

[0033] S12.1 Phased convergence, with a larger number of monitoring points allowed in the initial stage;

[0034] S12.2 Gradually reduce the number of monitoring points, prioritizing the elimination of redundant points;

[0035] S12.3 Set a lower limit threshold for coverage to ensure that monitoring capabilities do not significantly decrease;

[0036] S12.4 adopts the optimal solution inheritance strategy, taking the optimal solution of the previous stage as the initial solution of the new stage.

[0037] An airport noise monitoring system, wherein the layout of monitoring points is optimized using any of the methods described above.

[0038] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the airport noise monitoring point optimization layout method.

[0039] An electronic device includes a processor and a memory, characterized in that the memory stores a computer program, and the processor executes the program to implement the airport noise monitoring point optimization layout method.

[0040] To address the issue of redundant monitoring point locations in existing airport noise monitoring point deployments, a monitoring point layout optimization method based on a genetic algorithm is proposed. By introducing a noise coverage model, gridded sensitive area division, a multi-constraint evolutionary mechanism, and a dynamic point compression strategy, the method achieves simultaneous optimization of the number and distribution of monitoring points, yielding the following technical benefits: 1. Effectively reduce the number of monitoring points;

[0041] This invention introduces a point number penalty factor into the optimization objective function and combines it with a dynamic point number control mechanism to gradually reduce the number of points during the optimization process. This significantly reduces the costs of equipment installation, operation and maintenance, and data processing.

[0042] 2. Adapt to complex constraints and enhance the robustness of the solution;

[0043] The optimization process of this invention fully incorporates the actual airport layout constraints, including (1) spatial correlation with typical aircraft flight paths, i.e., prioritizing layout near flight paths; (2) being far from background noise sources such as highways and high-speed railways; and (3) controlling the distance between monitoring points to more than 3km to avoid redundancy, while maintaining appropriate proximity to facilitate data mutual verification and improve monitoring accuracy.

[0044] 3. Ensure high coverage of monitoring points;

[0045] While reducing the number of monitoring points, redundant points were eliminated first, and core monitoring points were retained as much as possible. The overall coverage rate remained basically stable, and the decline in the monitoring capability of noise events was kept within an acceptable range. Attached Figure Description

[0046] Figure 1 This is a schematic diagram showing the distribution of noise monitoring points. Detailed Implementation

[0047] This invention provides a method for optimizing the layout of airport noise monitoring points based on genetic algorithms.

[0048] Example 1

[0049] A method for optimizing the layout of airport noise monitoring points based on genetic algorithms, specifically including the following steps:

[0050] S1. Using INM software, generate noise prediction contour maps to mark the affected areas with noise levels greater than 70 dB, and identify village centers or noise-sensitive buildings within these areas. Sensitive buildings within a 3 km radius are grouped together as a single cluster, with the center of each cluster representing the location of a noise monitoring point. Based on this, the preliminary locations for noise monitoring points are determined.

[0051] S2. Divide the area affected by aircraft noise into a general grid sensitive zone. Establish and divide the general grid sensitive zone with a radius of 5km, centered on the village center or noise-sensitive building.

[0052] S3. Any point within the detection area to monitoring point The distance is ;

[0053] S4. Assume a point within the monitoring area At the monitoring point The events covered are The probability of this event occurring is If the monitoring point can sense ,but ,otherwise .

[0054] S5. Monitoring Point For a certain point within the monitoring area The probability of perception at a location is ,like Less than or equal to The result is 1, if Greater than less than The result of the perception probability is The others are 0. Where 0 < < These are the reliability parameters for monitoring point measurements. These are the measurement parameters related to the measuring point. , , .

[0055] S6. To increase the probability of the target being measured, multiple monitoring points are used to measure the target simultaneously, and the joint measurement probability is: ,in The set of monitoring points for the measurement target.

[0056] S7. Area coverage rate refers to the monitoring point's ability to perceive the monitored area; the larger the coverage area, the stronger the perception ability. ,in It is the number of grids in the monitoring area. It is a set of monitoring points.

[0057] S8. After determining the function and related indicators to be optimized, a coverage optimization problem needs to be set up. Let the monitoring area A be a 100×100 square, divided into 100 grids of equal size and area 1, with a discretization precision of 1m. The joint coverage rate is obtained by calculating the coverage of each grid point relative to each monitoring point. After traversing all grid points, the coverage rate of the entire area is obtained and used as the optimization objective function. S9. Based on the above analysis, the steps of using a genetic algorithm are as follows:

[0058] Step 1: Initialization. Set up the evolution count calculator. Set the maximum number of generations. Randomly generated Individuals as the initial group .

[0059] Step 2: Individual evaluation. Calculate the group. The coverage rate of each individual in the process.

[0060] Step 3: Selection Operation. The selection operator is applied to the population, and based on the coverage of individuals, superior individuals are selected and passed on to the next population according to certain rules and methods.

[0061] Step 4: Crossover operation. The crossover operator is applied to the population, and for selected pairs of individuals, a portion of their chromosomes are exchanged with a certain probability to generate new individuals.

[0062] Step 5: Mutation Operation. The mutation operator is applied to the population, changing the value of one or more genes in selected individuals with a certain probability to other alleles. Population The next generation population is obtained after selection, crossover, and mutation operations. Calculate the coverage value and sort the data according to the coverage value to prepare for the next genetic operation.

[0063] Step 6: Termination Condition Check: If ,but Proceed to step 2, if If the individual with the highest coverage obtained in this evolutionary process is selected as the optimal solution, the calculation will terminate.

[0064] S10. The layout of monitoring points generated by the genetic algorithm is based on idealized conditions and only uses coverage as the optimization objective. It does not fully consider the relative position of the points to the aircraft track or the actual conditions of high background noise interference.

[0065] S11. Continue to optimize the objective function and add constraints to comprehensively optimize the following objectives: Define a comprehensive benefit function to evaluate the merits of a monitoring point layout, which includes a weighted sum of factors such as the distance of each monitoring point from the flight path, the distance from the noise source, and the coverage rate. The objective function can be expressed as:

[0066] ;

[0067] in: This indicates the distance of the monitoring point from the aircraft's flight path. This indicates the distance of the monitoring point from the background noise source. The distance constant is set to normalize the index. This indicates that the corresponding weighting coefficients are used to balance the impact of various objectives.

[0068] S12. To solve the optimization problem, the genetic algorithm is used again.

[0069] S13. To achieve acceptable coverage with as few monitoring points as possible, a dynamic point number control mechanism is introduced: the maximum allowed number of monitoring points is gradually reduced, guiding the algorithm to tend to use fewer points during later convergence, thus outputting a concise but effective point placement scheme. Specifically, dynamic control is implemented through the following strategies.

[0070] S13.1: Phased convergence: In the initial stage of the algorithm, more monitoring points are allowed so that the genetic algorithm mainly optimizes the coverage index, and the coverage is optimized with more points to obtain a high-quality initial solution.

[0071] S13.2: Gradually reduce the number of monitoring points. During the algorithm's operation, the number of points is gradually reduced, guiding the algorithm towards a more streamlined solution. If deleting a monitoring point has little impact on coverage (perhaps because the area covered by that point is already redundantly covered by other points), then the decrease in fitness caused by reducing the number of points is small, and the algorithm can still accept it and retain these more streamlined solutions through selection operations. Conversely, if the removal of a point leads to a significant decrease in fitness (i.e., a substantial reduction in coverage), then the solution with that point will have an advantage in selection, indicating that the number of points cannot be reduced further. Thus, the algorithm gradually approaches a balance between minimizing the number of points and improving coverage.

[0072] S13.3: To ensure that the coverage effect of the final solution remains acceptable, a lower limit threshold for coverage is pre-set. During the dynamic point reduction process, the coverage rate of the current optimal solution is monitored in real time. When it is found that further reducing the number of monitoring points would cause the coverage rate to fall below the threshold, the point reduction is stopped. The dynamic mechanism will reduce the number of points as much as possible until it approaches the critical point of coverage performance.

[0073] S13.4: Inheritance and Re-optimization: After each reduction in the number of monitoring points, an inheritance strategy is used to utilize the optimal solution from the previous stage as one of the initial solutions for the new stage. The fitness is then re-evaluated before continuing the evolution. In the final stage, the number of monitoring points is compressed to a small value, and the solution obtained at this point is the final output scheme.

[0074] Example 2

[0075] A method for optimizing the layout of airport noise monitoring points based on genetic algorithms, specifically including the following steps:

[0076] S1. Use INM software to generate noise prediction contour maps, marking the impact areas with noise levels greater than 70dB, and identifying village centers or noise-sensitive buildings (such as hospitals, schools, and residential areas) within these areas. Sensitive buildings within a 3km radius are grouped together as a single cluster, with the center of each cluster representing the location of the noise monitoring point. Based on this, the preliminary locations for noise monitoring points are determined (e.g., ...). Figure 1 (As shown).

[0077] S2. Divide the area affected by aircraft noise into a general grid sensitive zone. Establish and divide the general grid sensitive zone with a radius of 5km, centered on the village center or noise-sensitive building.

[0078] S3. Any point within the detection area to monitoring point The distance is ;

[0079] S4. Assume a point within the monitoring area At the monitoring point The events covered are The probability of this event occurring is If the monitoring point can sense ,but ,otherwise .

[0080] S5. Monitoring Point For a certain point within the monitoring area The probability of perception at a location is ,like Less than or equal to The result is 1, if Greater than less than The result of the perception probability is The others are 0. Where 0 < < These are the reliability parameters for monitoring point measurements. These are the measurement parameters related to the measuring point. , , .

[0081] S6. To increase the probability of the target being measured, multiple monitoring points need to be used to measure the target simultaneously. The joint measurement probability is: ,in The set of monitoring points for the measurement target.

[0082] S7. Area coverage rate refers to the monitoring point's ability to perceive the monitored area; the larger the coverage area, the stronger the perception ability. ,in It is the number of grids in the monitoring area. It is a set of monitoring points.

[0083] S8. After determining the function and related indicators to be optimized, a coverage optimization problem needs to be set up. Assume the monitoring area A is a 100×100 square, divided into 100 grids of equal size and area 1, with a discretization precision of 1m. The joint coverage rate is obtained by calculating the coverage of each grid point relative to each monitoring point. After traversing all grid points, the coverage rate of the entire area is obtained and used as the optimization objective function. S9. Based on the above analysis, the steps of using a genetic algorithm are as follows:

[0084] Step 1: Initialization. Set up the evolution count calculator. Set the maximum number of generations. Randomly generated Individuals as the initial group .

[0085] Step 2: Individual evaluation. Calculate the group. The coverage rate of each individual in the process.

[0086] Step 3: Selection Operation. The selection operator is applied to the population, and based on the coverage of individuals, some superior individuals are selected to be passed on to the next population according to certain rules and methods.

[0087] Step 4: Crossover operation. The crossover operator is applied to the population, and for selected pairs of individuals, a portion of their chromosomes are exchanged with a certain probability to generate new individuals.

[0088] Step 5: Mutation Operation. The mutation operator is applied to the population, changing the value of one or more genes in selected individuals with a certain probability to other alleles. Population The next generation population is obtained after selection, crossover, and mutation operations. Calculate the coverage value and sort the data according to the coverage value to prepare for the next genetic operation.

[0089] Step 6: Termination Condition Check: If ,but Proceed to step 2, if If the individual with the highest coverage obtained in this evolutionary process is selected as the optimal solution, the calculation will terminate.

[0090] S10. The monitoring point layout generated by the genetic algorithm is based on idealized conditions, with coverage as the optimization objective alone. It does not fully consider other key factors, such as the relative position of the monitoring points to the aircraft's flight path and actual conditions like high background noise interference. Therefore, it is necessary to further optimize the monitoring point locations to improve the practicality and accuracy of the solution.

[0091] S11. Continue to optimize the objective function and add constraints to comprehensively optimize the following objectives: Define a comprehensive benefit function to evaluate the merits of a monitoring point layout, which includes a weighted sum of factors such as the distance of each monitoring point from the flight path, the distance from the noise source, and the coverage rate. The objective function can be expressed as:

[0092] ;

[0093] in: This indicates the distance of the monitoring point from the aircraft's flight path. This indicates the distance of the monitoring point from background noise sources (traffic noise, industrial noise). The distance constant is set to normalize the index. This indicates that the corresponding weighting coefficients are used to balance the impact of various objectives.

[0094] S12. To solve the above optimization problem, the genetic algorithm is used again.

[0095] S13. In the above optimization process, to achieve acceptable coverage with the fewest possible monitoring points, a dynamic point number control mechanism is introduced. The core idea of ​​this mechanism is to gradually reduce the maximum allowed number of monitoring points, guiding the algorithm to tend to use fewer points during later convergence, thereby outputting a concise but effective point placement scheme. Specifically, dynamic control can be implemented through the following strategies.

[0096] S13.1: Phased Convergence: In the initial stage of the algorithm, a larger number of monitoring points are allowed so that the genetic algorithm mainly optimizes indicators such as coverage and quickly finds a solution with a wide coverage. First, the coverage is optimized with a larger number of points to obtain a high-quality initial solution.

[0097] S13.2: Gradually reduce the number of monitoring points. During algorithm execution, the number of points is gradually reduced, guiding the algorithm towards a more streamlined solution. If deleting a monitoring point has little impact on coverage (possibly because the area covered by that point is already redundantly covered by other points), then the decrease in fitness caused by reducing the number of points is small, and the algorithm can still accept it and retain these more streamlined solutions through selection operations. Conversely, if the removal of a point leads to a significant decrease in fitness (a substantial reduction in coverage), then the solution possessing that point will have an advantage in selection, indicating that the number of points cannot be further reduced. In this way, the algorithm gradually approaches a balance between minimizing the number of points and achieving optimal coverage.

[0098] S13.3: To ensure that the coverage effect of the final solution is "still acceptable," a lower limit threshold for coverage can be preset (e.g., 90% or the detection rate of a certain noise event). During the dynamic point reduction process, the coverage of the current optimal solution is monitored in real time. When it is found that further reducing the number of monitoring points will cause the coverage to fall below the threshold, the point reduction is stopped. The dynamic mechanism will reduce the number of points as much as possible until it approaches the critical point of coverage performance.

[0099] S13.4: Inheritance and Re-optimization: After each reduction in the number of monitoring points, an inheritance strategy can be used to utilize the optimal solution from the previous stage as one of the initial solutions for the new stage, and the fitness is re-evaluated before continuing the evolution. This ensures that the point reduction process does not deviate from the previously found good solution. In the final stage, the number of monitoring points is compressed to a small value, and the solution obtained by the algorithm at this point is the final output scheme.

[0100] Example

[0101] A genetic algorithm-based method for optimizing the layout of airport noise monitoring points includes the following steps and mechanisms:

[0102] Initial monitoring point deployment

[0103] First, based on the INM isopleth map, areas with noise levels greater than 70 dB were identified. Then, considering the locations of noise-sensitive buildings such as hospitals, schools, and residences near the airport, sensitive targets were screened and spatially aggregated. Multiple adjacent buildings were grouped into a cluster through spatial merging, with the cluster center serving as the initial monitoring point location. This method established a relatively comprehensive monitoring network in the initial stage, providing a foundation for subsequent optimization.

[0104] Based on this, a 5km radius permeable grid sensitive area is constructed with each cluster as the center. The entire area is divided into equally sized grid cells to simulate the sensing range of monitoring points and support the calculation of coverage.

[0105] Monitoring coverage probability model

[0106] To quantify the effectiveness of monitoring point deployment, this invention establishes a probability model for monitoring point coverage of any location within the area. This model treats the phenomenon of any location being covered (i.e., detectable) by a monitoring point as a probabilistic event and characterizes the monitoring probability using factors such as distance. To measure the overall monitoring network's coverage capability for airport noise, the metric of "area coverage rate" is introduced. The method involves dividing the monitoring area into many small grid cells (as described in the aforementioned generalized grid division), and then traversing each grid cell to determine whether it is effectively covered by at least one monitoring point.

[0107] Monitoring point sensing model and coverage calculation

[0108] A probability model for the perception of any grid cell by a monitoring point is established. This model considers factors such as distance attenuation and the reliability of the monitoring point to determine whether a point is perceived by a certain monitoring point. The perception capabilities of multiple monitoring points for the same grid point are combined to obtain a joint perception probability.

[0109] By traversing all grid points and comparing whether each point is detected, the overall coverage rate of the monitoring area, i.e., the proportion of grid points that are effectively detected, is calculated. This metric will serve as a core component of the optimization fitness function.

[0110] Noise monitoring point layout process based on genetic algorithm

[0111] This method uses a genetic algorithm to optimize the location of monitoring points. The core process includes: initialization: setting the population size and chromosome encoding (corresponding to different combinations of locations), and randomly generating several monitoring point layout schemes;

[0112] Fitness assessment: Scoring is performed based on the coverage of each scheme; Selection operation: High-fitness placement combinations are retained; Crossover and mutation: Simulating gene recombination and mutation, new site combinations are generated; Evolutionary iteration: Continuous evolution through multiple generations gradually approaches the optimal layout scheme; Termination judgment: The optimal solution is output based on convergence or the maximum number of generations. The initial optimization goal is to maximize coverage, striving to achieve the optimal sensing range through position adjustment.

[0113] Multi-objective function optimization

[0114] Building upon basic optimization, several practical constraints are introduced to construct a more comprehensive benefit function, including: proximity of monitoring points to aircraft flight paths; minimizing distance from high background noise sources (such as highways and railways); controlling the distance between monitoring points to avoid overly dense or sparse distribution; and maintaining stable coverage. By setting weight parameters for each of these objectives, a unified evaluation framework is constructed within the fitness function, enabling the algorithm to seek the optimal balance among multiple objectives.

[0115] Point number control and convergence strategy

[0116] To avoid an excessive number of monitoring points, a dynamic point quantity control mechanism was designed and implemented throughout the genetic algorithm's operation. This mechanism includes: Phased point reduction: Initially, a larger number of points are allowed to prioritize coverage. The number of monitoring points is gradually reduced in the mid-to-late stages. Redundant point removal mechanism: When coverage changes are minimal, redundant points in overlapping coverage areas are prioritized for deletion. Optimal solution inheritance mechanism: Each time the number of points is reduced, the optimal solution from the previous stage is retained as the new initial population, improving the continuity and stability of the solutions. This mechanism guides the algorithm to achieve a dynamic trade-off between coverage and the number of monitoring points, ultimately resulting in a fewer but more effective point deployment scheme.

Claims

1. A method for optimizing the layout of airport noise monitoring points based on genetic algorithms, characterized in that, Includes the following steps: S1. Based on the noise prediction contour map, identify the affected area with a noise level greater than 70 dB, mark the noise-sensitive buildings or village centers in the area, merge sensitive buildings with a distance of less than 3 km into a group, and take the center of the group as the initial monitoring point location. S2. Construct a general grid sensitive area with a radius of 5 km centered on each cluster, and divide the monitoring area into grids; S3. Calculate the distance from any point Q(x,y) within the monitoring area to the monitoring point. distance ; S4. Define whether point Q(x,y) is a monitored point. Coverage discrimination probability If it can cover the area, the value is 1; otherwise, it is 0. S5. Establish monitoring points Perceptual probability model Q for point Q(x,y) per (x,y,s), calculate the sensing probability based on distance and measurement point reliability parameters; S6. Establish a joint sensing probability model Q for the same target from multiple monitoring points. per (N); S7. Calculate the area coverage R area (N) serves as an indicator of the overall perception capability of the monitoring network over the monitored area. S8. Set the coverage optimization objective function, discretize the monitoring area into a grid, and use the overall coverage as the optimization objective; S9. Use a genetic algorithm for initial optimization, with the goal of maximizing coverage, to generate a preliminary monitoring point layout; S10. Based on the initial optimization, multi-objective constraints are introduced to construct a comprehensive benefit function, including a weighted combination of coverage, distance to the flight path, and distance to the background noise source; S11. The comprehensive benefit function is further optimized using a genetic algorithm; S12. Introduce a dynamic monitoring point quantity control mechanism to gradually reduce the number of monitoring points and output a simplified monitoring point layout scheme while maintaining the coverage rate at or above the set threshold.

2. The airport noise monitoring point optimization layout method based on genetic algorithm according to claim 1, characterized in that, In step S1, the noise prediction contour map is generated using INM software.

3. The airport noise monitoring point optimization layout method based on genetic algorithm according to claim 1, characterized in that, In step S5, the perceptual probability model is a piecewise function: When d( ,q) ≤ r - r e At that time, the probability of perception is 1; When r - r e < d( ,q) < r + r e At that time, the probability of perception is: ； Where, r e This is a measure of the ability to monitor uncertainties at noise measurement points. Parameters , It is the attenuation coefficient, which controls the overall rate at which sensing ability decreases with increasing distance. It is the perception decay index. It is used to control the shape of the decay curve of the perception probability in the transition region.

4. The airport noise monitoring point optimization layout method based on genetic algorithm according to claim 1, characterized in that, In step S6, the joint sensing probability model is: 。 5. The airport noise monitoring point optimization layout method based on genetic algorithm according to claim 1, characterized in that, In step S7, the formula for calculating the area coverage rate is: ； Where m×n represents the total number of grids in the monitoring area.

6. The airport noise monitoring point optimization layout method based on genetic algorithm according to claim 1, characterized in that, In step S10, the comprehensive benefit function is: ； in, The distance between the monitoring point and the aircraft's flight path. D represents the distance of the monitoring point from the background noise source. max ω1, ω2, and ω3 are normalization constants and weighting coefficients.

7. The method for optimizing the layout of airport noise monitoring points based on genetic algorithm according to claim 1, characterized in that, In step S12, the dynamic point quantity control mechanism includes: S12.1 Phased convergence, with a larger number of monitoring points allowed in the initial stage; S12.2 Gradually reduce the number of monitoring points, prioritizing the elimination of redundant points; S12.3 Set a lower limit threshold for coverage to ensure that monitoring capabilities do not significantly decrease; S12.4 adopts the optimal solution inheritance strategy, taking the optimal solution of the previous stage as the initial solution of the new stage.

8. An airport noise monitoring system, characterized in that, The layout of its monitoring points is optimized using the method described in any one of claims 1-7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the airport noise monitoring point optimization layout method as described in any one of claims 1-7.

10. An electronic device comprising a processor and a memory, characterized in that, The memory stores a computer program, and when the processor executes the program, it implements the airport noise monitoring point optimization layout method as described in any one of claims 1-7.

Images