Sonar buoy deployment simulation optimization method and electronic equipment

Abstract

This invention discloses a sonar buoy deployment simulation optimization method and electronic equipment. The sonar buoy deployment simulation optimization method includes: dividing the coverage area of ​​the sonar buoy deployment scheme into multiple grids; initializing a population, the population comprising multiple chromosomes, each chromosome randomly initialized, each chromosome including multiple sets of genomes, each set of genomes corresponding to a grid, each set of genomes including multiple genes, each gene representing the boundary adjustment value of the corresponding grid; setting a fitness function for the chromosomes, the fitness function calculating the fitness value based on the coverage, overlap, and balance of the number of sonar buoys in the grid; performing multiple iterations until the iteration termination condition is met, then ending the iteration and outputting the optimal chromosome within the final population. This invention effectively solves the problems of regional overlap and omission, ensuring the effectiveness of the solution and the global convergence capability of the algorithm. It significantly improves the efficiency and system response capability of multi-platform collaborative regional detection in complex marine environments.

Description

Technical Field

[0001] This invention relates to the field of maritime search and rescue technology, and in particular to a sonar buoy deployment simulation optimization method, electronic equipment, storage medium and computer program product. Background Technology

[0002] In maritime emergency search and rescue operations, data collection from sonar buoys in target sea areas is a critical task. This scenario typically involves deploying a limited number of sonar buoys across a vast ocean area, with multiple unmanned patrol vessels collaborating to collect and transmit sonar buoy data. Existing research has explored several techniques based on optimization algorithms and clustering methods for sonar buoy deployment and data collection task allocation. These primarily fall into three categories: First, static deployment strategies based on regular grids or empirical models. These methods are simple in structure, computationally efficient, and suitable for sea areas with relatively regular structures or clear prior information. Second, using clustering algorithms to initially group sonar buoys. This allows for rapid sonar buoy allocation when the distribution is relatively uniform, improving the operability of task allocation. Third, applying evolutionary computation methods such as genetic algorithms for regional adjustment. These methods possess strong global search capabilities and can improve the balance and coverage of regional allocation within a certain number of iterations. These methods, to some extent, improve the coverage integrity of sonar buoy deployment and the spatial balance of data collection task allocation.

[0003] However, existing technologies still have significant drawbacks: First, most methods do not fully consider the geometric boundary constraints of actual sea areas and the constraints of navigation safety and communication interference during the collaborative operation of multiple unmanned vessels, resulting in coverage blind spots or overlapping areas in sonar buoy deployment; second, the clustering process lacks effective handling of empty clusters and boundary conflicts, which can easily lead to uneven distribution of sonar buoys; third, existing optimization strategies often ignore the trade-offs between multiple objectives such as coverage, overlap rate, and balance, resulting in poor overall performance in practical applications; finally, existing technologies have poor adaptability in dynamic environments and multi-platform collaborative scenarios, making it difficult to quickly respond to changes in tasks. Summary of the Invention

[0004] Therefore, it is necessary to address the technical problems of regional overlap and omission in the deployment of sonar buoys and the low efficiency of regional detection in existing technologies, and to provide a sonar buoy deployment simulation optimization method, electronic equipment, storage medium and computer program products.

[0005] This invention provides a simulation optimization method for sonar buoy deployment, comprising:

[0006] The coverage area of ​​the sonar buoy deployment scheme is divided into multiple grids, and the coverage area includes multiple sonar buoys;

[0007] Initialize the population, which includes multiple chromosomes, each chromosome is randomly initialized, each chromosome includes multiple sets of genomes, each set of genomes corresponds to a grid, each set of genomes includes multiple genes, and each gene is used to represent the boundary adjustment value of the corresponding grid.

[0008] Set a fitness function for the chromosome, which calculates the chromosome's fitness value based on the coverage, overlap, and balance of the number of sonar buoys in the grid.

[0009] The iteration is performed multiple times until the iteration termination condition is met, at which point the iteration ends. In each iteration, the fitness value of chromosomes in the population is calculated based on the fitness function, and crossover, mutation and / or elitist retention operations are performed on one or more chromosomes.

[0010] After the iteration ends, the optimal chromosome in the final population is output, and the boundary of each grid is adjusted based on the optimal chromosome to determine the sonar buoys covered by each adjusted grid.

[0011] Furthermore, the method also includes: obtaining a specified coverage density value given by the user, and determining a sonar buoy deployment scheme that satisfies the specified coverage density value.

[0012] Furthermore, determining the sonar buoy deployment scheme that satisfies the specified coverage density value includes:

[0013] The minimum number of sonar buoys required to satisfy the specified coverage density value is calculated as follows: ,in, The minimum number of sonar buoys is given, where A is the length of the coverage area, B is the width of the coverage area, and p is the specified coverage density value. The coverage radius of a single sonar buoy;

[0014] Establish an iterative search mechanism, and execute the following method in each iteration:

[0015] Will The sonar buoys are deployed in a preset area according to multiple distribution schemes, and the coverage area of ​​the sonar buoys for each distribution scheme is calculated.

[0016] Calculate the maximum coverage density by selecting the largest coverage area;

[0017] If the maximum coverage density is greater than or equal to p, stop the iteration and return the distribution scheme corresponding to the maximum coverage density as the sonar buoy deployment scheme; otherwise, let p be the maximum coverage density. = +1, execute the next iteration.

[0018] Furthermore, the setting of the chromosome fitness function includes:

[0019] The fitness function of the chromosome is set based on the number of sonar buoys not covered by any grid, the number of sonar buoys covered by multiple grids, and the variance of the number of sonar buoys contained in each grid.

[0020] Furthermore, the calculation of the fitness value of chromosomes within the population based on the fitness function includes:

[0021] For each chromosome in the population, perform the following operation:

[0022] The boundary of the grid corresponding to each genome of the chromosome is adjusted based on the adjustment value of the gene in the genome to obtain the adjusted boundary of each grid.

[0023] Based on the adjusted boundaries of each grid, determine the sonar buoys covered by each grid;

[0024] Calculate the number of sonar buoys not covered by any grid, the number of sonar buoys covered by multiple grids, and the variance of the number of sonar buoys contained in each grid;

[0025] The fitness value of the chromosome is calculated based on the fitness function, taking into account the number of sonar buoys not covered by any grid, the number of sonar buoys covered by multiple grids, and the variance of the number of sonar buoys contained in each grid.

[0026] Furthermore, the crossing over, mutation, and / or elite preservation operations on one or more chromosomes include:

[0027] Multiple chromosomes were selected from the population in this iteration as parent individuals;

[0028] Two parent individuals are randomly selected, and each gene locus of the two selected parent individuals is exchanged with a preset exchange probability to obtain offspring individuals;

[0029] For each gene locus in the offspring, the gene value is randomly changed using a preset mutation probability;

[0030] The offspring individuals are added to the population in the next iteration;

[0031] From the population of this iteration, sort the chromosomes in descending order of fitness, and select a predetermined number of elite chromosomes with high fitness to add to the population of the next iteration.

[0032] Furthermore, after determining the sonar buoys covered by each adjusted grid, the method further includes:

[0033] Each grid is assigned a cruise device, and sonar buoys covered by the same grid are assigned to the same cruise device for that grid.

[0034] This invention provides an electronic device, comprising:

[0035] At least one processor; and,

[0036] A memory communicatively connected to at least one of the processors; wherein,

[0037] The memory stores instructions that can be executed by at least one of the processors, which enable the at least one processor to perform the sonar buoy deployment simulation optimization method as described above.

[0038] The present invention provides a storage medium that stores computer instructions, which, when executed by a computer, are used to perform all the steps of the sonar buoy deployment simulation optimization method described above.

[0039] This invention provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the sonar buoy deployment simulation optimization method as described above.

[0040] This invention divides the coverage area of ​​a sonar buoy deployment scheme into multiple grids, and then uses a genetic algorithm to perform multi-objective optimization on the grid boundaries. Through integer encoding, multi-index fitness function design, and crossover and mutation operations, it effectively solves the problems of regional overlap and omission, ensuring the effectiveness of the solution and the global convergence capability of the algorithm. This invention constructs a complete sonar buoy deployment and data collection task allocation process through the coordinated operation of three modules: sonar buoy deployment, sonar buoy allocation, and genetic algorithm optimization. This significantly improves the efficiency and system response capability of multi-platform collaborative area detection in complex marine environments. Attached Figure Description

[0041] Figure 1 This is a flowchart illustrating the workflow of a sonar buoy deployment simulation optimization method according to an embodiment of the present invention.

[0042] Figure 2 This is a flowchart illustrating the simulation optimization method for sonar buoy deployment according to another embodiment of the present invention.

[0043] Figure 3 This is a schematic diagram of a sonar buoy deployment scheme according to an example of the present invention;

[0044] Figure 4 This is an example of a sonar buoy allocation scheme according to the present invention;

[0045] Figure 5 A flowchart illustrating the workflow of a sonar buoy deployment simulation optimization method, which is the preferred embodiment of the present invention.

[0046] Figure 6This is a schematic diagram of the grid region boundary as an example of the present invention;

[0047] Figure 7 This is a schematic diagram of the hardware structure of an electronic device according to the present invention. Detailed Implementation

[0048] The specific embodiments of the present invention will be further described below with reference to the accompanying drawings. Identical components are indicated by the same reference numerals. It should be noted that the terms "front," "rear," "left," "right," "up," and "down" used in the following description refer to directions in the accompanying drawings, while the terms "inner" and "outer" refer to directions toward or away from the geometric center of a specific component, respectively.

[0049] like Figure 1 The diagram shown is a flowchart of a sonar buoy deployment simulation optimization method according to an embodiment of the present invention, including:

[0050] Step S101: Divide the coverage area of ​​the sonar buoy deployment scheme into multiple grids, wherein the coverage area includes multiple sonar buoys;

[0051] Step S102: Initialize the population, which includes multiple chromosomes, each chromosome is randomly initialized, each chromosome includes multiple sets of genomes, each set of genomes corresponds to a grid, each set of genomes includes multiple genes, and each gene is used to represent the boundary adjustment value of the corresponding grid.

[0052] Step S103: Set the fitness function of the chromosome. The fitness function calculates the fitness value of the chromosome based on the coverage, overlap and balance of the number of sonar buoys in the grid.

[0053] Step S104: Perform multiple iterations until the iteration termination condition is met, then end the iteration. In each iteration, calculate the fitness value of chromosomes in the population based on the fitness function, and perform crossover, mutation and / or elite retention operations on one or more chromosomes.

[0054] Step S105: After the iteration ends, output the optimal chromosome in the final population, adjust the boundary of each grid based on the optimal chromosome, and determine the sonar buoys covered by each adjusted grid.

[0055] Specifically, the present invention can be applied to electronic devices with processing capabilities, such as computers.

[0056] First, step S101 is executed to divide the coverage area of ​​the sonar buoy deployment scheme into multiple grids, and the coverage area includes multiple sonar buoys.

[0057] like Figure 3The diagram shows a sonar buoy deployment scheme according to an example of the present invention, including multiple sonar buoys 1. The coverage area of ​​the sonar buoy deployment scheme can be a rectangular area. Then, the coverage area of ​​all the sonar buoys 1 is divided into multiple grids.

[0058] The sonar buoys are deployed in an array, and the sonar buoy deployment scheme includes: the number of sonar buoy columns, the number of sonar buoy rows, and the sonar buoy array pattern.

[0059] Among them, the array patterns include, but are not limited to, symmetrical uniform distribution, row-oriented staggered uniform distribution, and column-oriented staggered uniform distribution.

[0060] This embodiment employs a grid-based strategy to initially group sonar buoys in the sea area. Assuming that K patrol devices need to be dispatched to perform the mission, preferably unmanned patrol vessels, the monitored sea area is uniformly divided into K grids along the row and column directions (K being the number of patrol devices). All sonar buoys within each grid are initially assigned to the same unmanned patrol vessel, forming an initial mission partitioning scheme.

[0061] Then, steps S102 to S104 are performed for genetic algorithm optimization. The genetic algorithm optimization employs an evolutionary computation strategy to optimize the initial sonar buoy allocation results, effectively resolving complex issues such as unreasonable region boundaries and sonar buoy point allocation conflicts. By simulating the mechanisms of natural selection, genetic crossover, and gene mutation in biological evolution, the population evolution gradually improves the quality of the solution.

[0062] Specifically, step S102 is executed to initialize the population, which includes multiple chromosomes, each chromosome is randomly initialized, each chromosome includes multiple sets of genomes, each set of genomes corresponds to a grid, each set of genomes includes multiple genes, and each gene is used to represent the boundary adjustment value of the corresponding grid.

[0063] Specifically, chromosome encoding and population initialization are performed first. Based on the sonar buoy allocation results after grid division, the boundary of each grid is calculated. Preferably, the boundary of each grid is a rectangular boundary. The entire coverage area can be represented using a two-dimensional coordinate system. Therefore, the boundary of each grid is... ,in, This represents the minimum coordinate of the grid boundary in the x-direction. This represents the minimum coordinate of the grid boundary in the y-direction. This represents the maximum coordinate of the grid boundary in the x-direction. This represents the maximum coordinate of the grid boundary in the y-direction.

[0064] The algorithm uses integer encoding. A chromosome includes multiple genomes, each genome corresponds to a grid, and each gene represents the adjustment value of the region boundary of the corresponding grid. Therefore, the current state can be represented as an all-zero encoding.

[0065] Then, the gene value represents the number of movable steps of the boundary in the corresponding direction, and the chromosome length is L, which is the number of boundaries in each grid. Preferably, the boundary of each grid is a rectangular boundary, then the chromosome length is... K represents the number of grids. Then, population initialization is performed, which is a random initialization, that is, a random value is set for each gene of each chromosome.

[0066] Then, step S103 is executed to set the fitness function of the chromosome, which calculates the fitness value of the chromosome based on the coverage, overlap and balance of the number of sonar buoys in the grid.

[0067] The fitness function comprehensively considers three key metrics related to the number of sonar buoys: coverage, overlap, and balance. The fitness function is set based on these three metrics. This multi-objective optimization design ensures that the solution is optimal across all three dimensions: coverage, overlap, and balance.

[0068] Then, step S104 is executed, and multiple iterations are performed until the iteration termination condition is met, at which point the iteration ends. In each iteration, the fitness value of chromosomes in the population is calculated based on the fitness function, and crossover, mutation, and / or elite retention operations are performed on one or more chromosomes.

[0069] Finally, step S105 is executed. After the iteration ends, the optimal chromosome in the final population is output. Based on the optimal chromosome, the boundary of each grid is adjusted, and the sonar buoys covered by each grid after adjustment are determined.

[0070] Specifically, the sonar buoys covered by each adjusted grid are output as the sonar buoy deployment scheme.

[0071] This optimization process enables the system to find a high-quality sonar buoy allocation scheme that meets both the requirements of full coverage and maintains regional balance, overcoming the limitations of traditional clustering algorithms in boundary processing and providing technical support for the efficient execution of unmanned patrol vessels' collection missions.

[0072] This invention divides the coverage area of ​​a sonar buoy deployment scheme into multiple grids, and then uses a genetic algorithm to perform multi-objective optimization on the grid boundaries. Through integer encoding, multi-index fitness function design, and crossover and mutation operations, it effectively solves the problems of regional overlap and omission, ensuring the effectiveness of the solution and the global convergence capability of the algorithm. This invention constructs a complete sonar buoy deployment and data collection task allocation process through the coordinated operation of three modules: sonar buoy deployment, sonar buoy allocation, and genetic algorithm optimization. This significantly improves the efficiency and system response capability of multi-platform collaborative area detection in complex marine environments.

[0073] like Figure 2 The diagram shown is a flowchart of a sonar buoy deployment simulation optimization method according to another embodiment of the present invention, including:

[0074] Step S201: Obtain the specified coverage density value given by the user, and determine the sonar buoy deployment scheme that meets the specified coverage density value.

[0075] Step S202: Divide the coverage area of ​​the sonar buoy deployment scheme into multiple grids, wherein the coverage area includes multiple sonar buoys.

[0076] Step S203: Initialize the population, which includes multiple chromosomes, each chromosome is randomly initialized, each chromosome includes multiple sets of genomes, each set of genomes corresponds to a grid, each set of genomes includes multiple genes, and each gene is used to represent the boundary adjustment value of the corresponding grid.

[0077] Step S204: Based on the number of sonar buoys not covered by any grid, the number of sonar buoys covered by multiple grids, and the variance of the number of sonar buoys contained in each grid, a fitness function for the chromosome is set. The fitness function calculates the fitness value of the chromosome based on the coverage rate, overlap rate, and balance of the number of sonar buoys in the grid.

[0078] Step S205: Perform multiple iterations until the iteration termination condition is met, then end the iteration. In each iteration:

[0079] Multiple chromosomes were selected from the population in this iteration as parent individuals;

[0080] Two parent individuals are randomly selected, and each gene locus of the two selected parent individuals is exchanged with a preset exchange probability to obtain offspring individuals;

[0081] For each gene locus in the offspring, the gene value is randomly changed using a preset mutation probability;

[0082] The offspring individuals are added to the population in the next iteration;

[0083] From the population of this iteration, sort the chromosomes in descending order of fitness, and select a predetermined number of elite chromosomes with high fitness to add to the population of the next iteration.

[0084] Step S206: After the iteration ends, output the optimal chromosome in the final population, adjust the boundary of each grid based on the optimal chromosome, determine the sonar buoys covered by each grid after adjustment, assign a cruise device to each grid, and assign the sonar buoys covered by the same grid to the same cruise device of the grid.

[0085] Specifically, step S201 is executed first to obtain the specified coverage density value given by the user and determine the sonar buoy deployment scheme that meets the specified coverage density value.

[0086] Specifically, the user inputs a specified coverage density value p, and the coverage area range A×B (km). Based on the specified coverage density value, a sonar buoy deployment scheme that satisfies the specified coverage density value is determined.

[0087] In one embodiment, determining the sonar buoy deployment scheme that satisfies the specified coverage density value includes:

[0088] The minimum number of sonar buoys required to satisfy the specified coverage density value is calculated as follows: ,in, The minimum number of sonar buoys is given, where A is the length of the coverage area, B is the width of the coverage area, and p is the specified coverage density value. The coverage radius of a single sonar buoy;

[0089] Establish an iterative search mechanism, and execute the following method in each iteration:

[0090] Will The sonar buoys are deployed in a preset area according to multiple distribution schemes, and the coverage area of ​​the sonar buoys for each distribution scheme is calculated.

[0091] Calculate the maximum coverage density by selecting the largest coverage area;

[0092] If the maximum coverage density is greater than or equal to p, stop the iteration and return the distribution scheme corresponding to the maximum coverage density as the sonar buoy deployment scheme; otherwise, let p be the maximum coverage density. = +1, execute the next iteration.

[0093] Specifically, the sonar buoy deployment scheme includes the number of rows, columns, and arrangement patterns of the sonar buoy array. Different sonar buoy deployment schemes have different numbers of rows, columns, and / or arrangement patterns of sonar buoy arrays.

[0094] The deployment modes include:

[0095] 1.1) Symmetrical and uniform distribution

[0096] For a sea area of ​​A×B, specify the number of sonar buoys N (N≥1), let the number of sonar buoy columns be n and the number of sonar buoy rows be m, and deploy all sonar buoys in an m×n array, that is:

[0097]

[0098] Obviously, at least there will be. and Two deployment methods.

[0099] According to common sense, when the ratio The closer At the same number of sonar buoys, the larger the coverage area; for the same ratio, the more sonar buoys, the larger the coverage area. Therefore, a near-optimal sonar buoy deployment standard can be obtained:

[0100] Condition (1)

[0101] Where m is the number of rows in the distributed sonar buoy array, and n is the number of columns in the distributed sonar buoy array. For the preset threshold, Take the smaller value; in this embodiment, it is preferred to take the smaller value. When the coverage density meets the specified requirements, the upper limit of the number of sonar buoys to end the exploration can be obtained through the above formula.

[0102] Record all ordered pairs of real numbers that satisfy condition (1). .

[0103] In a symmetrically and uniformly distributed sonar buoy array In the middle, the spacing between sonar buoy arrays Spacing between sonar buoys Calculated separately as follows:

[0104]

[0105] This embodiment describes the placement point of the sonar buoy. Since they are placed within the coverage area, the coordinates of each sonar buoy placement point are calculated using the following formula:

[0106]

[0107] in, .

[0108] 1.2) Interlaced and uniformly distributed

[0109] For a search area of ​​A×B, the number of sonar buoys N (N≥1) can be categorized into two types: staggered row uniform distribution and staggered column uniform distribution. A staggered column uniform distribution of the sonar buoy array refers to a deployment where sonar buoys are divided into rows and columns, with the number of buoys in odd-numbered columns remaining the same, and the number of buoys in even-numbered columns being one less than that in odd-numbered columns. The buoys are uniformly distributed throughout the sea area without any significant blind spots. A staggered row uniform distribution of the sonar buoy array refers to a deployment where sonar buoys are divided into rows and columns, with the number of buoys in odd-numbered rows remaining the same, and the number of buoys in even-numbered rows being one less than that in odd-numbered columns. The buoys are uniformly distributed throughout the sea area without any significant blind spots.

[0110] Let the number of sonar buoys be n, and the number of odd-numbered sonar buoys be m. Then the number of even-numbered sonar buoys is m-1. Due to the symmetrical and uniform distribution, there are obviously two ordered pairs of real numbers. and It also satisfies the following two alternating uniform distributions, therefore, the discussion here should satisfy... and .

[0111] When the columns are uniformly distributed in an alternating pattern, the following conditions are met:

[0112]

[0113] Similarly, a uniformly distributed row orientation satisfies:

[0114]

[0115] Sonar buoy spacing Spacing between sonar buoys The calculation method is the same as above.

[0116] When the columns are uniformly distributed in an alternating pattern, the coordinates of the placement points of each sonar buoy in the odd-numbered columns are calculated using the following formula:

[0117]

[0118] in, .

[0119] The formula for calculating the coordinates of each sonar buoy placement point in the even-numbered sequence is as follows:

[0120]

[0121] in, .

[0122] When the rows are evenly distributed with staggered orientations, the coordinates of the placement points of each sonar buoy in the odd-numbered rows are calculated using the following formula:

[0123]

[0124] in, .

[0125] The formula for calculating the coordinates of each sonar buoy placement point in the even-numbered sequence is as follows:

[0126]

[0127] in, .

[0128] The coverage area of ​​the sonar buoy detection range within the coverage area is calculated as follows:

[0129] Assuming there are several sonar buoys deployed in the area, and the coordinates of their deployment points are obtained from the previous step, the detection range of one sonar buoy is approximately a circle with a radius of d. c Also known as the detection radius. The Monte Carlo algorithm is used for approximate area calculation.

[0130] First, a large number of random point projections are performed within the detection area. The number of projections is set to N, and a random number generator is used to generate random coordinates within the bounding rectangle each time. ,in exist The internal order follows a uniform distribution. exist The internal order follows a uniform distribution.

[0131] Next, it is determined whether each random point falls within the coverage circle of any sonar buoy. For each random point... Iterate through all sonar buoys and calculate the distance from the point to the center of each sonar buoy. The distance d is calculated using the following formula:

[0132]

[0133] If there exists a sonar buoy such that d ≤ dc, then the random point falls within the coverage area of ​​the sonar buoy, and the number M of points falling within the coverage area of ​​the sonar buoy is incremented by 1.

[0134] Finally, based on the principles of the Monte Carlo algorithm, the approximate value of the total coverage area S of the sonar buoy search range within the region is:

[0135]

[0136] The more points N are used, the closer the calculated coverage area S is to the true value. Experiments have shown that N is better when it is more than 10,000 times.

[0137] Deployment method for sonar buoys under specified coverage density conditions

[0138] 3.1) The user inputs a specified coverage density value p, and the area range A×B (km).

[0139] 3.2) Determine the termination condition for the iterative search.

[0140] The coverage density of the sonar buoy deployment field is:

[0141] p=

[0142] in, This indicates the area actually covered by the detected sonar buoy.

[0143] Clearly, coverage density is positively correlated with coverage area. Based on the above formula, the minimum number of sonar buoys required to achieve a given coverage density p can be calculated. This means placing a certain number of sonar buoys without overlap to achieve a certain coverage area, thus obtaining the corresponding coverage density. The formula for calculating this number of sonar buoys is as follows:

[0144]

[0145] Therefore, this value is used as the lower limit for the number of sonar buoys.

[0146] 3.3) Establish an iterative search mechanism, executing the following method in each iteration:

[0147] (1) Sonar buoys are deployed in a symmetrical and staggered uniform distribution within the coverage area. A combination of the number of sonar buoy rows, the number of sonar buoy rows, and the deployment pattern constitutes a distribution scheme. The coverage area of ​​each distribution scheme is calculated using the Monte Carlo method, and the results are stored in a structure of (number of sonar buoy rows, number of sonar buoy rows, deployment pattern, coverage area).

[0148] (2) Sort the results collected in the current iteration according to the coverage area, select the largest coverage area, and then calculate the largest coverage density.

[0149] (3) If the coverage requirement is met Stop iteration and return the number of sonar buoy columns, the number of sonar buoys per column, and the deployment pattern corresponding to the distribution scheme; otherwise, clear the stored results. = +1, repeat (1) and (2).

[0150] The returned distribution scheme will be used as the sonar buoy deployment scheme. Sonar buoys will be redeployed in the area and presented to the user, with the boundaries of the sonar buoy array being... ,in, Let x be the minimum coordinate of the array boundary in the x-direction. Let be the minimum coordinate of the array boundary in the y-direction. This represents the maximum coordinate of the array boundary in the x-direction. This represents the maximum coordinate of the array boundary in the y-direction.

[0151] Then, step S202 is executed to divide the coverage area of ​​the sonar buoy deployment scheme into multiple grids, wherein the coverage area includes multiple sonar buoys.

[0152] Specifically, to provide a high-quality initial solution for the genetic algorithm optimization, this embodiment employs a grid partitioning strategy to initially group the sonar buoys in the sea area. Assuming that K patrol devices need to be dispatched to perform the mission, the monitored sea area is uniformly divided into K grids along the row and column directions (K is the number of patrol devices). All sonar buoys within each grid are initially assigned to the same patrol device, forming an initial mission partitioning scheme. The resulting set of grid scheme pairs is as follows:

[0153]

[0154] It can be seen that the area of ​​responsibility for any one of the patrol devices is:

[0155]

[0156]

[0157] in, , This represents the coordinates of the area of ​​responsibility of the cruise equipment on the x-axis. The coordinates of the area of ​​responsibility of the cruise equipment on the y-axis.

[0158] Iterate through all sonar buoy points, based on the coordinates of the sonar buoys ( , Determine the grid to which it belongs and assign it to the corresponding k-th patrol device. The patrol device is preferably an unmanned patrol vessel.

[0159] In most cases, Where pop_size is the population size of the genetic algorithm. The remaining population is then randomly assigned from the sonar buoys being detected.

[0160] This method ensures the uniformity and rationality of the initial solution in space, laying a good foundation for subsequent optimization.

[0161] Then, steps S203 to S205 are performed for genetic algorithm optimization. The genetic algorithm optimization module employs an evolutionary computation strategy to optimize the initial sonar buoy allocation results, effectively resolving complex issues such as unreasonable region boundaries and sonar buoy point allocation conflicts. This module simulates the mechanisms of natural selection, genetic crossover, and gene mutation in biological evolution, gradually improving the quality of the solution through population evolution.

[0162] First, step S203 is executed to initialize the population, which includes multiple chromosomes. Each chromosome is randomly initialized, and each chromosome includes multiple sets of genomes. Each set of genomes corresponds to a grid, and each set of genomes includes multiple genes. Each gene is used to represent the boundary adjustment value of the corresponding grid.

[0163] First, chromosome encoding and population initialization are performed. Based on the sonar buoy allocation results after grid division, the boundary of each grid is calculated. Preferably, the boundary of each grid is a rectangle. The entire coverage area can be represented using a two-dimensional coordinate system. Then, the boundary of the k-th grid is... ,in, This represents the minimum coordinate of the grid boundary in the x-direction. This represents the minimum coordinate of the grid boundary in the y-direction. This represents the maximum coordinate of the grid boundary in the x-direction. This represents the maximum coordinate of the grid boundary in the y-direction.

[0164] The algorithm uses integer encoding. A chromosome consists of multiple genome groups, each corresponding to a grid. Each gene represents an adjustment value for the boundary of the corresponding grid region. Therefore, the current state can be represented as an all-zero encoding. For example... Figure 3 As shown, to adapt to the three array configurations mentioned above, with or as the basic unit The gene value represents the number of movable steps of the boundary in the corresponding direction, and the chromosome length is L, which is the number of boundaries in each grid. Preferably, the boundary of each grid is a rectangular boundary, then the chromosome length is... K is the number of grids. Therefore, the value range for each code is:

[0165]

[0166]

[0167]

[0168]

[0169] For convenience, the following text will be referred to as ,in, Let be the value of the i-th gene in the chromosome. Let be the lower limit value of the i-th gene. This represents the upper limit value of the i-th gene.

[0170] Then, population initialization is performed. Population initialization is randomized, that is, random values ​​are set for each gene on each chromosome.

[0171] Then, step S204 is executed, which sets the fitness function of the chromosome based on the number of sonar buoys not covered by any grid, the number of sonar buoys covered by multiple grids, and the variance of the number of sonar buoys contained in each grid. The fitness function calculates the fitness value of the chromosome based on the coverage, overlap and balance of the number of sonar buoys in the grid.

[0172] Specifically, the fitness function comprehensively considers three key indicators: the number of sonar buoys not covered by any area. Number of sonar buoys covered by multiple areas and the variance of the number of sonar buoy points in each region. This multi-objective optimization design ensures that the solution is optimal in terms of coverage, overlap, and balance.

[0173] In one embodiment, setting the chromosome fitness function includes:

[0174] Set the chromosome fitness function as follows:

[0175] ,in, For fitness, The first weighting coefficient, This is the second weighting coefficient. This is the third weighting coefficient. .

[0176] Then, step S205 is executed, and multiple iterations are performed until the iteration termination condition is met, at which point the iteration ends. In each iteration:

[0177] Multiple chromosomes were selected from the population in this iteration as parent individuals;

[0178] Two parent individuals are randomly selected, and each gene locus of the two selected parent individuals is exchanged with a preset exchange probability to obtain offspring individuals;

[0179] For each gene locus in the offspring, the gene value is randomly changed using a preset mutation probability;

[0180] The offspring individuals are added to the population in the next iteration;

[0181] From the population of this iteration, sort the chromosomes in descending order of fitness, and select a predetermined number of elite chromosomes with high fitness to add to the population of the next iteration.

[0182] Specifically, the selection and crossover mechanisms are executed first. The evolutionary process employs a roulette wheel selection mechanism, prioritizing chromosomes with higher fitness as parent individuals. The crossover operation uses a single-point crossover strategy, with the crossover rate expressed as... During the crossover process, each gene locus is processed with a certain probability. Exchange:

[0183]

[0184] in, This indicates the selected parent individuals. ,in, For the i-th gene of the first parent individual used for exchange, For the i-th gene of the second parent individual used for exchange, Let i be the i-th gene of the offspring after the first parent individual is swapped. Let i be the i-th gene of the offspring after the second parent individual is swapped. It is a random number.

[0185] Then, the mutation operation is performed while maintaining feasibility. The mutation operation is performed probabilistically. Randomly change gene values:

[0186]

[0187] in, For the i-th gene of the offspring individual to perform the mutation operation, p rand It is a random value, and .

[0188] Crucially, a feasibility check must be performed after the mutation to ensure that the new chromosome does not cause regional overlap; only mutations that pass the check will be accepted. The steps for the feasibility check are as follows:

[0189] 1. Traverse all regions and check. Does it meet the requirements? .

[0190] if , exchange; if , and exchange.

[0191] 2. Traverse all sonar buoy coordinates and determine if there are any that have not been... Covered buoys, if they exist, are not feasible;

[0192] Finally, elite retention and convergence guarantees are implemented. The elite retention strategy selects the best batch of chromosomes from each generation to directly enter the next generation, and the number of elite individuals is denoted as "elite". This mechanism ensures the convergence and solution quality of the algorithm, preventing excellent solutions from being lost during the evolution process.

[0193] The fitness is calculated based on the number of sonar buoys not covered by any grid, the number of sonar buoys covered by multiple grids, and the variance of the number of sonar buoys contained in each grid.

[0194] In one embodiment, calculating the fitness value of chromosomes within the population based on the fitness function includes:

[0195] For each chromosome in the population, perform the following operation:

[0196] The boundary of the grid corresponding to each genome of the chromosome is adjusted based on the adjustment value of the gene in the genome to obtain the adjusted boundary of each grid.

[0197] Based on the adjusted boundaries of each grid, determine the sonar buoys covered by each grid;

[0198] Calculate the number of sonar buoys not covered by any grid, the number of sonar buoys covered by multiple grids, and the variance of the number of sonar buoys contained in each grid;

[0199] The fitness value of the chromosome is calculated based on the fitness function, taking into account the number of sonar buoys not covered by any grid, the number of sonar buoys covered by multiple grids, and the variance of the number of sonar buoys contained in each grid.

[0200] Specifically, each genome of each chromosome corresponds to a grid boundary. In each iteration, chromosomes are removed from the population, and the grid boundary corresponding to each genome of the chromosome is defined using... or Using the basic unit as the gene value, the boundary value represents the number of movable steps in the corresponding direction. Multiplying the gene value by the basic unit and then adding it to the corresponding grid boundary yields the adjusted boundary. The boundary of each grid is... Each genome consists of four gene values. Therefore, the gene values ​​are multiplied by the basic unit, and then divided by the corresponding values. After adding them together, we get the adjusted result. Among them, gene values ​​can be positive, negative, or 0, therefore the adjusted... It may increase, decrease, or remain unchanged.

[0201] Then, based on the coordinates of each sonar buoy, the sonar buoys covered by each grid are determined, and the number of sonar buoys not covered by any grid, the number of sonar buoys covered by multiple grids, and the variance of the number of sonar buoys contained in each grid are calculated. Then, these values ​​are substituted into the fitness function to obtain the fitness value of the chromosome.

[0202] Finally, when the genetic algorithm termination condition is met, step S206 is executed. After the iteration ends, the optimal chromosome in the final population is output. Based on the optimal chromosome, the boundary of each grid is adjusted, the sonar buoys covered by each grid after adjustment are determined, and a cruise device is assigned to each grid. The sonar buoys covered by the same grid are assigned to the same cruise device of the grid.

[0203] Among these, the preferred patrol equipment is an unmanned patrol vessel.

[0204] The optimization process in this embodiment enables the system to find a high-quality sonar buoy allocation scheme that satisfies both full coverage requirements and maintains regional balance. This solves the limitations of traditional clustering algorithms in boundary processing and provides technical support for the efficient execution of unmanned patrol vessel collection tasks.

[0205] This embodiment employs three sonar buoy deployment modes (symmetric staggered, row-direction offset staggered, and column-direction offset staggered), combined with geometric constraints, to significantly improve the coverage integrity of the target sea area by sonar buoys, overcoming the problems of overlapping blind spots and low resource utilization in traditional deployment methods. This embodiment utilizes a genetic algorithm for multi-objective optimization of the region boundary. Through integer encoding, multi-index fitness function design, and feasibility constraints of crossover and mutation operations, it effectively solves the problems of region overlap and omission, ensuring the effectiveness of the solution and the global convergence capability of the algorithm. This embodiment, through the coordinated operation of three modules—sonic buoy deployment, sonar buoy allocation, and genetic algorithm optimization—constructs a complete sonar buoy deployment and data collection task allocation process, significantly improving the efficiency and system response capability of multi-platform collaborative area detection in complex sea environments.

[0206] like Figure 5 The diagram shown is a flowchart of a sonar buoy deployment simulation optimization method according to the preferred embodiment of the present invention, including:

[0207] Step S501, input task parameters: sea area size A, B, specified coverage p, other simulation system parameters;

[0208] Step S502: Calculate the minimum number of buoys;

[0209] Step S503: Determine the number of rows and columns of the buoy array, calculate the buoy spacing, evaluate three array patterns, including symmetrical uniform distribution and staggered uniform distribution, and generate a set of buoy positions.

[0210] Step S504: Calculate the working area of ​​the unmanned patrol vessel using grid partitioning;

[0211] Step S505, chromosome coding and population initialization;

[0212] Step S506: Calculate individual fitness;

[0213] Step S507: Determine whether to terminate the iteration. If not, perform the selection operation, crossover operation, mutation operation, and elite retention. Otherwise, proceed to step S508.

[0214] Step S508: Output the sonar buoy deployment plan.

[0215] As an example, the specific steps are as follows:

[0216] Step S501, define input variables. Assume the search area is a rectangular region with a horizontal side length of 50 (km) and a vertical side length of 60 (km). To achieve a comprehensive search of this area, the detection radius of a single sonar buoy is... =2 (km), the detection reliability and the contact probability are respectively 2 (km), Number of unmanned patrol boats available .

[0217] Step S502: Calculate the required lower limit of sonar buoys. Assuming the desired monitoring coverage (i.e., the specified coverage density value) is p = 0.75, then the minimum number of sonar buoys required is... It is given by the following formula:

[0218]

[0219] Substituting the values, we can see that the lower limit for the number of sonar buoys is... 180.

[0220] Step S503: Calculate the sonar buoy array layout parameters. Assume the number of sonar buoy arrays is n, and the number of rows is m. Establish an iterative search mechanism, executing the following method in each iteration:

[0221] (1) Each sonar buoy generates all schemes in an orderly manner.<m,n> That is, all conditions are met. The ordered pairs of schemes are distributed symmetrically and uniformly within the current region:

[0222]

[0223]

[0224] in, .

[0225] (2) Calculate the coverage area and number of samples using the Monte Carlo method. .

[0226]

[0227] (3) Sort the results collected in the current iteration according to the coverage area, select the largest coverage area, and then calculate the largest coverage density.

[0228] (4) If the current iteration reaches the coverage requirement, stop the iteration and return the number of sonar buoy columns m, the number of sonar buoy columns n, the array mode and the number of sonar buoys used for the scheme. ,like Figure 3 As shown; otherwise, clear the stored results. = +1, repeat (1)-(3).

[0229] Step S504: Initialize sonar buoy allocation based on grid partitioning. Assuming the number of deployable unmanned patrol vessels is limited, and the number of sonar buoys carried by each vessel is also limited, K unmanned patrol vessels need to be dispatched to perform the mission, where:

[0230]

[0231] First, obtain all possible combinations of grid rows and columns, forming a set:

[0232]

[0233] It can be determined that the area of ​​responsibility for any randomly selected unmanned patrol vessel is:

[0234]

[0235]

[0236] in, .

[0237] Iterate through all sonar buoy points, determine the grid to which they belong based on their coordinates (x, y), and assign them to the corresponding k-th unmanned patrol vessel.

[0238] In most cases, The remaining population comes from the random allocation of the sonar buoys.

[0239] Step S505, the boundaries of each grid region are encoded using integers, such as... Figure 6 As shown, each chromosome represents the number of adjustment steps for each region boundary, and the gene values ​​range from [value missing]. The step size is uniformly set as , This represents the ratio of the distance between the boundary corresponding to the current gene encoding and the boundary of the lower or left region to the step size. This represents the ratio of the distance between the boundary corresponding to the current gene encoding and the boundary of the upper or right region to the step size.

[0240] Step S506, the fitness function comprehensively considers the uncover rate, overlap rate, and regional balance, and is designed as follows:

[0241] in, These are weighting coefficients. The number of sonar buoy points contained in the 1st, 2nd, ..., kth grid.

[0242] Step S507: Optimize the region boundary using a genetic algorithm.

[0243] 1) The evolutionary process employs a roulette wheel selection mechanism, which uses repeatable sampling to select parents based on the selection probability distribution, prioritizing chromosomes with higher fitness as parent individuals. .

[0244] Specifically, the selection probability of each chromosome is calculated:

[0245]

[0246] in, Indicates the first Fitness values ​​of each chromosome This represents the total number of chromosomes in the population.

[0247] Then calculate the cumulative probability for each chromosome. This yields the cumulative probability array.

[0248] Perform iterations, in each iteration:

[0249] Generate a uniformly random number r in the range [0, 1), iterate through the cumulative probability array, and find the first one that satisfies this condition. Select the individuals, and then perform the next iteration until the required number of parent individuals are selected.

[0250] 2) The crossover operation adopts a single-point crossover strategy, and the crossover rate is expressed as... During the crossover process, two parent individuals are randomly selected, and each gene locus is crossovered at a certain rate. Exchange:

[0251]

[0252] in, This indicates the selected parent individuals. ,in, For the i-th gene of the first parent individual used for exchange, For the i-th gene of the second parent individual used for exchange, Let i be the i-th gene of the offspring after the first parent individual is swapped. Let i be the i-th gene of the offspring after the second parent individual is swapped. It is a random number.

[0253] 3) Mutation operations and feasibility maintenance. Mutation operations are based on... Gene values ​​are changed randomly with probability:

[0254]

[0255] in, For the i-th gene of the offspring individual to which the mutation operation is performed. It is a randomly generated decimal between 0 and 1.

[0256] 4) Select a number of individuals with high fitness functions from the original parent generation, the number of which is called elite, and keep them directly in the next generation.

[0257] 5) Repeat the above process until the number of iterations is reached.

[0258] Step S508: Output the final sonar buoy allocation scheme. Based on the optimized area boundaries, assign a monitoring area to each unmanned patrol vessel, output the sonar buoy point set for each area and the coordinates of the area boundaries, and complete the maritime search mission planning, such as... Figure 4 As shown.

[0259] The effects of this invention can be further illustrated by the following simulation experiments:

[0260] 1. Experimental conditions and methods

[0261] Hardware platform: Intel Core i3-4150 processor, CPU frequency 2.4GHz, 64GB memory;

[0262] Software platform: The computer uses 64-bit Windows 11 Professional and Python 3.12.

[0263] 2. Simulation Content

[0264] Following the technical solution of this invention, sonar buoys were deployed and multiple unmanned patrol vessels were assigned tasks in a simulated sea area of ​​50km×60km (see initial sea area and sonar buoy deployment details). Figure 3 ), Figure 4The final allocation result, optimized by a genetic algorithm, is divided into multiple grids 2. From a subjective perspective, existing technologies using basic clustering methods exhibit significant overlap and omissions in region coverage, with some marginal sonar buoys not effectively included in any collection area. In contrast, the sonar buoy allocation result output by this invention not only achieves full coverage and no overlap, but also features regularly shaped and evenly distributed regions, significantly improving the rationality and operational feasibility of task allocation.

[0265] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0266] like Figure 7 The diagram shown is a hardware structure schematic of an electronic device according to the present invention, comprising:

[0267] At least one processor 701; and,

[0268] A memory 702 is communicatively connected to at least one of the processors 701; wherein,

[0269] The memory 702 stores instructions that can be executed by at least one of the processors, which enable the at least one of the processors to perform the sonar buoy deployment simulation optimization method as described above.

[0270] Figure 7 Take the 701 processor as an example.

[0271] The electronic device may also include an input device 703 and a display device 704.

[0272] The processor 701, memory 702, input device 703 and display device 704 can be connected by a bus or other means. The figure shows an example of connection by a bus.

[0273] The memory 702, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as the program instructions / modules corresponding to the sonar buoy deployment simulation optimization method in the embodiments of this application, for example, Figure 1 , Figure 2 The method flow is shown. The processor 701 executes various functional applications and data processing by running non-volatile software programs, instructions, and modules stored in the memory 702, thereby realizing the sonar buoy deployment simulation optimization method in the above embodiments.

[0274] The memory 702 may include a program storage area and a data storage area. The program storage area may store an operating system and an application program required for at least one function. The data storage area may store data created based on the use of the sonar buoy deployment simulation optimization method. Furthermore, the memory 702 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 702 may optionally include memory remotely located relative to the processor 701, and these remote memories may be connected via a network to the apparatus performing the sonar buoy deployment simulation optimization method. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0275] The input device 703 can receive user clicks and generate signal inputs related to user settings and function control of the sonar buoy deployment simulation optimization method. The display device 704 may include a display screen or other display equipment.

[0276] When one or more modules are stored in the memory 702, and are run by one or more processors 701, the sonar buoy deployment simulation optimization method in any of the above method embodiments is executed.

[0277] This invention divides the coverage area of ​​a sonar buoy deployment scheme into multiple grids, and then uses a genetic algorithm to perform multi-objective optimization on the grid boundaries. Through integer encoding, multi-index fitness function design, and crossover and mutation operations, it effectively solves the problems of regional overlap and omission, ensuring the effectiveness of the solution and the global convergence capability of the algorithm. This invention constructs a complete sonar buoy deployment and data collection task allocation process through the coordinated operation of three modules: sonar buoy deployment, sonar buoy allocation, and genetic algorithm optimization. This significantly improves the efficiency and system response capability of multi-platform collaborative area detection in complex marine environments.

[0278] One embodiment of the present invention provides a storage medium that stores computer instructions, which, when executed by a computer, are used to perform all the steps of the sonar buoy deployment simulation optimization method described above.

[0279] In the context of this disclosure, a storage medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. The storage medium can be a machine-readable signal medium or a machine-readable storage medium. Optionally, the storage medium can be a non-transitory computer-readable storage medium, such as a ROM, random access memory (RAM), compact disc ROM (CD-ROM), magnetic tape, floppy disk, and optical data storage device.

[0280] One embodiment of the present invention provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the sonar buoy deployment simulation optimization method as described above.

[0281] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

Claims

1. A simulation optimization method for sonar buoy deployment, characterized in that, include: The coverage area of ​​the sonar buoy deployment scheme is divided into multiple grids, and the coverage area includes multiple sonar buoys; Initialize the population, which includes multiple chromosomes, each chromosome is randomly initialized, each chromosome includes multiple sets of genomes, each set of genomes corresponds to a grid, each set of genomes includes multiple genes, and each gene is used to represent the boundary adjustment value of the corresponding grid. Set a fitness function for the chromosome, which calculates the chromosome's fitness value based on the coverage, overlap, and balance of the number of sonar buoys in the grid. The iteration is performed multiple times until the iteration termination condition is met, at which point the iteration ends. In each iteration, the fitness value of chromosomes in the population is calculated based on the fitness function, and crossover, mutation and / or elitist retention operations are performed on one or more chromosomes. After the iteration ends, the optimal chromosome in the final population is output, and the boundary of each grid is adjusted based on the optimal chromosome to determine the sonar buoys covered by each grid after adjustment. The method further includes: obtaining a specified coverage density value given by the user, and determining a sonar buoy deployment scheme that satisfies the specified coverage density value; The determination of the sonar buoy deployment scheme that satisfies the specified coverage density value includes: The minimum number of sonar buoys required to satisfy the specified coverage density value is calculated as follows: ,in, The minimum number of sonar buoys is given, where A is the length of the coverage area, B is the width of the coverage area, and p is the specified coverage density value. The coverage radius of a single sonar buoy; Establish an iterative search mechanism, and execute the following method in each iteration: Will The sonar buoys are deployed in a preset area according to multiple distribution schemes, and the coverage area of ​​the sonar buoys for each distribution scheme is calculated. Calculate the maximum coverage density by selecting the largest coverage area; If the maximum coverage density is greater than or equal to p, stop the iteration and return the distribution scheme corresponding to the maximum coverage density as the sonar buoy deployment scheme; otherwise, let p be the maximum coverage density. = +1, execute the next iteration.

2. The sonar buoy deployment simulation optimization method according to claim 1, characterized in that, The setting of the chromosome fitness function includes: The fitness function of the chromosome is set based on the number of sonar buoys not covered by any grid, the number of sonar buoys covered by multiple grids, and the variance of the number of sonar buoys contained in each grid.

3. The sonar buoy deployment simulation optimization method according to claim 2, characterized in that, The calculation of the fitness value of chromosomes within the population based on the fitness function includes: For each chromosome in the population, perform the following operation: The boundary of the grid corresponding to each genome of the chromosome is adjusted based on the adjustment value of the gene in the genome to obtain the adjusted boundary of each grid. Based on the adjusted boundaries of each grid, determine the sonar buoys covered by each grid; Calculate the number of sonar buoys not covered by any grid, the number of sonar buoys covered by multiple grids, and the variance of the number of sonar buoys contained in each grid; The fitness value of the chromosome is calculated based on the fitness function, taking into account the number of sonar buoys not covered by any grid, the number of sonar buoys covered by multiple grids, and the variance of the number of sonar buoys contained in each grid.

4. The sonar buoy deployment simulation optimization method according to claim 1, characterized in that, The crossover, mutation, and / or elitist preservation operations performed on one or more chromosomes include: Multiple chromosomes were selected from the population in this iteration as parent individuals; Two parent individuals are randomly selected, and each gene locus of the two selected parent individuals is exchanged with a preset exchange probability to obtain offspring individuals; For each gene locus in the offspring, the gene value is randomly changed using a preset mutation probability; The offspring individuals are added to the population in the next iteration; From the population of this iteration, sort the chromosomes in descending order of fitness, and select a predetermined number of elite chromosomes with high fitness to add to the population of the next iteration.

5. The sonar buoy deployment simulation optimization method according to claim 1, characterized in that, After determining the sonar buoys covered by each adjusted grid, the method further includes: Each grid is assigned a cruise device, and sonar buoys covered by the same grid are assigned to the same cruise device for that grid.

6. An electronic device, characterized in that, include: At least one processor; as well as, A memory communicatively connected to at least one of the processors; wherein, The memory stores instructions that can be executed by at least one of the processors, which are executed to enable at least one of the processors to perform the sonar buoy deployment simulation optimization method as described in any one of claims 1 to 5.

7. A storage medium, characterized in that, The storage medium stores computer instructions, which, when executed by the computer, are used to perform all the steps of the sonar buoy deployment simulation optimization method as described in any one of claims 1 to 5.

8. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instruction is executed by the processor, it implements the sonar buoy deployment simulation optimization method as described in any one of claims 1 to 5.

Images