Adaptive optimization method for sonar deployment points in flight equipment and electronic equipment

Abstract

This invention discloses an adaptive optimization method and electronic equipment for sonar dipping points of flight equipment. The adaptive optimization method includes: constructing the dynamic activity range of a maritime search target, determining the target's maximum activity radius during each sonar dipping detection by the flight equipment (maritime search involves multiple flight equipment continuously dipping sonar points for detection); based on the dynamic activity range, constructing dynamic spatial constraints for dipping points, where each dipping point is the detection point for the flight equipment's sonar dipping; and based on these dynamic spatial constraints, optimizing the positions of multiple dipping points on one or more flight equipment using an improved differential evolution algorithm. The method proposed in this invention can achieve adaptive optimization of the layout of multiple search dipping points in complex sea conditions where the target's movement direction is unknown. It possesses good engineering practicality and promotional value, and can be widely applied in target search, underwater detection, and other fields.

Description

Technical Field

[0001] This invention relates to the field of maritime target search technology, and in particular to an adaptive optimization method for sonar deployment points of flight equipment, electronic equipment, storage media, and computer program products. Background Technology

[0002] In maritime target search missions, the effective detection window for targets is typically only a few hours to tens of hours, during which rapid positioning and detection must be completed. Due to errors in the initial positioning information, and the fact that underwater targets are affected by various factors such as ocean currents, waves, buoyancy from leaking gas, and structural damage, they may drift nonlinearly, resulting in a high degree of uncertainty in their direction and path of motion, posing a severe challenge to accurate searching.

[0003] Search aircraft equipped with dipping sonar systems can detect weak underwater sound sources with high sensitivity by receiving signals related to underwater targets (such as structural vibrations, residual sounds from equipment operation, or signals emitted by signal sources). This makes it one of the most effective early target detection methods in distant waters. Therefore, scientifically and rationally planning the sonar dipping positions of each aircraft in different rounds directly affects detection efficiency, search coverage, and the final probability of target discovery.

[0004] However, existing target search path planning methods still have significant shortcomings when dealing with complex scenarios where the target's motion direction is unknown and the trajectory is highly random:

[0005] Inaccurate target activity range modeling: Traditional methods assume that the target is stationary or drifts at a constant speed in a fixed direction, failing to fully consider the diffusion effect caused by ocean current disturbances and buoyancy changes; often a fixed radius circular search area is set with the initial reporting point as the center, without dynamically expanding the boundary over time, resulting in large blind areas in early detection, and waste of resources due to excessive expansion in the later stage.

[0006] The sonar deployment points lack an adaptive mechanism: In multi-robot collaborative operations, the spatial distribution of each deployment point is mostly based on preset sector divisions or uniform polar coordinates, without real-time adjustments considering the potential diffusion trend of the target. Fixed angle intervals fail to optimize the angle between adjacent detection circles according to changes in detection distance, easily forming wedge-shaped gap blind zones; furthermore, the lack of a mechanism to prevent backtracking leads to detection redundancy. Summary of the Invention

[0007] Therefore, it is necessary to address the technical problem that existing target search path planning methods are unable to cope with complex scenarios where the target's motion direction is unknown and the trajectory is highly random. This requires providing an adaptive optimization method for the sonar deployment point of flight equipment, as well as electronic devices, storage media, and computer program products.

[0008] This invention provides an adaptive optimization method for sonar deployment points of flight equipment, comprising:

[0009] The dynamic activity range of the maritime search target is constructed, and the maximum activity radius of the target is determined during each dipping sonar detection by the flight equipment. The maritime search includes multiple dipping sonar detections by multiple flight equipment in succession.

[0010] Based on the aforementioned dynamic activity range, dynamic spatial constraints are constructed for the deployment point, which is the detection point for the sonar deployed by the flight equipment.

[0011] Based on the aforementioned dynamic spatial constraints, the positions of multiple launch points for one or more flight devices are optimized using an improved differential evolution algorithm.

[0012] Furthermore, the construction of the dynamic activity range of the maritime search target includes:

[0013] The maximum radius of motion of the target during the i-th dipping sonar detection by the flight equipment is determined as: ,in, This indicates the i-th sonar deployment. Let be the maximum radius of motion of the target during the i-th dipping sonar detection by the flight equipment. The target's maximum movement speed, The time delay from when the target loses contact to when the search begins. This refers to the cycle of a single sonar deployment operation. The initial report shows the mean square error of the target's location.

[0014] Furthermore, the step of constructing dynamic spatial constraints for the hoisting point based on the dynamic activity range includes:

[0015] Establish a polar coordinate system with the location where the target lost contact as the origin;

[0016] The radial distance constraint for the i-th launch point of the k-th flight equipment is as follows: ,in, Let be the polar radius of the i-th hoisting point of the k-th flight equipment in the polar coordinate system. Let the polar radius of the (i-1)th hoisting point of the k-th flight equipment be in the polar coordinate system. The radial random growth coefficient, Let be the maximum radius of motion of the target during the i-th dipping sonar detection by the flight equipment. The maximum radius of activity of the target during the (i-1)th dipping sonar detection by the flight equipment;

[0017] The angle increment constraint for the i-th launching point of the k-th flight equipment is as follows: ,in, For the angle increment constraint of the i-th hoisting point of the k-th flight equipment, Let the polar angle of the i-th hoisting point of the k-th flight equipment be in the polar coordinate system. Let the polar angle of the (i-1)th hoisting point of the k-th flight equipment be in the polar coordinate system. Let be the angle threshold of the i-th launching point of the k-th flight equipment, and , where λ is the distance factor of the deployment point and Rs is the effective detection radius of the sonar.

[0018] Furthermore, the optimization of the positions of multiple launch points for one or more flight devices using an improved differential evolution algorithm includes:

[0019] The polar coordinates of the initial hoisting point for each flight equipment are fixed.

[0020] An initial population is established, comprising multiple samples. A polar coordinate system is established with the location where the target loses contact as the origin. Each sample includes multiple elements, each element representing the polar coordinates of a single deployment point of a flight device in the polar coordinate system. Each sample includes the polar coordinates of all deployment points of each flight device except the initial deployment point. Furthermore, based on satisfying the dynamic spatial constraints of the flight device's sonar deployment points, the polar coordinates of multiple deployment points in the sample are randomly set.

[0021] Set a fitness function, which calculates the fitness value of a sample based on the coverage of each sample;

[0022] Perform multiple iterations until the iteration termination condition is met, then terminate the iteration. In each iteration, calculate the test sample for each sample in the current iteration population, and add the test sample and the sample with the higher fitness value in the corresponding sample to the population of the next iteration as the sample of the next iteration population.

[0023] After the iteration ends, the sample with the highest fitness value in the population at the end of the iteration is taken as the optimal solution.

[0024] Furthermore, the polar coordinates of the initial hoisting point for each flight device are fixed, including:

[0025] The polar coordinates of the initial launch point of the k-th flight equipment for each sample are fixed as follows:

[0026] ,in, Let the polar radius of the initial deployment point of the k-th flight equipment be the polar radius of the deployment point in the polar coordinate system. Let the polar angle of the initial deployment point of the k-th flight equipment in the polar coordinate system be denoted as . This refers to the maximum operating radius of the target during the initial dipping sonar detection by the flight equipment. C represents the effective detection radius of the sonar, and C represents the number of flying devices.

[0027] Furthermore, the setting of the fitness function includes:

[0028] Set the fitness function as follows: ,in, Let be the fitness value of the q-th sample. This represents the actual coverage area of ​​the q-th sample calculated using the Monte Carlo algorithm. The target's maximum movement speed, The time delay from when the target loses contact to when the search begins. This refers to the cycle of a single sonar deployment operation. The initial reported positional error is given by N, where N is the number of launches allowed for each flight device.

[0029] Furthermore, the calculation of the test samples for each sample in the current iteration population includes:

[0030] For each sample in the population in this iteration, the corresponding experimental sample is calculated as follows:

[0031] ;

[0032] ,in, Let be the first random sample randomly drawn from the population Q in the t-th iteration. Let be the second random sample randomly drawn from the population Q in the t-th iteration. Let be the third random sample randomly drawn from the population Q in the t-th iteration, and the first, second, and third random samples are different. Scaling factor Let be the difference sample corresponding to the q-th sample in the population during the t-th iteration. This represents the d-th element of the experimental sample corresponding to the q-th sample in the t-th iteration. Cross factor Let d be the d-th element of the difference sample corresponding to the q-th sample in the population during the t-th iteration. Let be the d-th element of the q-th sample in the population during the t-th iteration, and rand be a random number. Indicates from A random element is selected from the data, where C is the number of flying devices and N is the number of times each flying device is allowed to perform a hoisting operation.

[0033] This invention provides an electronic device, comprising:

[0034] At least one processor; and,

[0035] A memory communicatively connected to at least one of the processors; wherein,

[0036] The memory stores instructions that can be executed by at least one of the processors to enable at least one of the processors to perform the adaptive optimization method for the sonar deployment point of the flight equipment as described above.

[0037] This invention provides a storage medium that stores computer instructions, which, when executed by a computer, are used to perform all steps of the adaptive optimization method for sonar deployment points of flight equipment as described above.

[0038] This invention provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the adaptive optimization method for sonar deployment points of flight equipment as described above.

[0039] This invention constructs a dynamic range of movement for a maritime search target, establishes dynamic spatial constraints on deployment points, and optimizes the positions of multiple deployment points for one or more flight devices under these dynamic spatial constraints using an improved differential evolution algorithm. The proposed method enables adaptive optimization of the deployment point layout for multiple searches in complex sea conditions where the target's direction of motion is unknown. It possesses good engineering practicality and widespread applicability, and can be broadly applied in target search, underwater detection, and other fields. Attached Figure Description

[0040] Figure 1 This is a flowchart illustrating an adaptive optimization method for sonar deployment points of flight equipment according to an embodiment of the present invention.

[0041] Figure 2 This is a flowchart illustrating an adaptive optimization method for sonar deployment points of flight equipment, according to another embodiment of the present invention.

[0042] Figure 3 A flowchart illustrating the workflow of an adaptive optimization method for sonar deployment points of flight equipment, representing the preferred embodiment of the present invention.

[0043] Figure 4a This is a schematic diagram of a dual-frame sonar deployment scheme according to an example of the present invention;

[0044] Figure 4b This is a schematic diagram of a three-aircraft sonar deployment scheme according to an example of the present invention;

[0045] Figure 4c This is an example of the coverage variation of a dual-rack machine at different iteration numbers according to the present invention;

[0046] Figure 4dThis invention provides an example of the coverage variation of three machines at different iteration numbers;

[0047] Figure 5 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] To address the issue of highly uncertain underwater target motion characteristics during target search, there is an urgent need to propose a method for optimizing the launching point that can dynamically model the target's activity range, construct a variable spatial constraint mechanism, and possess high convergence efficiency and strong global search capability. This method aims to achieve blind-spot-free, highly continuous, and fast-response acoustic detection coverage under multi-machine collaboration, thereby improving the success rate and timeliness of target search.

[0050] This invention aims to solve the following core problems in the planning of sonar deployment points in current target search:

[0051] (1) How to scientifically model the dynamic activity area of ​​the target over time to avoid detection blind spots or invalid searches caused by unreasonable search boundary settings;

[0052] (2) How to establish a spatial constraint mechanism that is adaptively updated with each detection round to prevent gaps between backtracking search and detection, and improve the continuity and integrity of detection.

[0053] This invention proposes an adaptive optimization method for sonar deployment points of search flight equipment, which combines time-evolution maximum active circle modeling with an improved differential evolution algorithm.

[0054] like Figure 1 The diagram shows a flowchart of an adaptive optimization method for sonar deployment points of flight equipment according to an embodiment of the present invention, including:

[0055] Step S101: Construct the dynamic activity range of the maritime search target and determine the maximum activity radius of the target during each dipping sonar detection by the flight equipment. The maritime search includes multiple flight equipment continuously dipping sonar for detection.

[0056] Step S102: Based on the dynamic activity range, construct the dynamic spatial constraints of the hoisting point, where the hoisting point is the detection point of the flight equipment hoisting sonar.

[0057] Step S103: Based on the dynamic spatial constraints, optimize the positions of multiple launching points of one or more flight devices by using an improved differential evolution algorithm.

[0058] Specifically, the present invention can be applied to electronic devices with processing capabilities, such as computers.

[0059] This invention is primarily applied to maritime target search. It addresses situations where a target has lost contact and is detected multiple times using one or more aerial devices to deploy sonar. The invention optimizes the coordinates of one or more deployment points, allowing the aerial device to deploy sonar according to these optimized coordinates. Each time, the aerial device deploys a sonar unit at a deployment point to detect the target, and after a certain period, retracts the sonar unit and moves to the next deployment point to deploy another sonar unit to detect the target.

[0060] First, step S101 is executed to construct the dynamic activity range of the maritime search target and determine the maximum activity radius of the target during each sonar deployment by the flight equipment. The maritime search includes multiple flight equipment deploying sonar multiple times in succession for detection.

[0061] Specifically, when searching for targets at sea, the target will move after losing contact due to the influence of water currents and wind. Therefore, it is necessary to construct the dynamic activity range of the target in the maritime search. The flying target performs multiple dipping sonar detection operations, and the maximum activity radius of the target is calculated during each dipping sonar detection operation by the flying equipment.

[0062] Preferably, the flight equipment is a helicopter.

[0063] Then, step S102 is executed to construct dynamic spatial constraints for the hoisting point based on the dynamic activity range.

[0064] Specifically, to ensure continuous detection and avoid blind spots and backtracking searches, this invention proposes dynamic spatial constraints on the placement points.

[0065] This invention sets two types of constraints that are adaptively updated with each lifting cycle: radial constraints and angular increment constraints.

[0066] In some embodiments, dynamic spatial constraints include radial constraints and angular increment constraints.

[0067] Specifically, a polar coordinate system is established with the target's location when it lost contact as the origin. The location of the deployment point can be identified using polar coordinates in the polar coordinate system, where polar coordinates include polar radius and polar angle. The polar radius is the radial distance from the location to the origin, and the polar angle is the angle between the location and the origin. The radial constraint is the constraint on the polar radius of the deployment point. The angular increment constraint is the constraint on the increment of the polar angle between two consecutive deployment points.

[0068] Finally, step S103 is executed, whereby, based on the dynamic spatial constraints, the positions of multiple launching points of one or more flight devices are optimized using an improved differential evolution algorithm.

[0069] Specifically, this invention optimizes the positions of multiple launch points for one or more flight devices based on an improved differential evolution algorithm. Specifically, the improved differential evolution algorithm is used to optimize the launch point positions.

[0070] This invention constructs a dynamic range of movement for a maritime search target, establishes dynamic spatial constraints on deployment points, and optimizes the positions of multiple deployment points for one or more flight devices under these dynamic spatial constraints using an improved differential evolution algorithm. The proposed method enables adaptive optimization of the deployment point layout for multiple searches in complex sea conditions where the target's direction of motion is unknown. It possesses good engineering practicality and widespread applicability, and can be broadly applied in target search, underwater detection, and other fields.

[0071] like Figure 2 The diagram shown is a flowchart of an adaptive optimization method for sonar deployment points of flight equipment according to another embodiment of the present invention, including:

[0072] Step S201: Construct the dynamic activity range of the maritime search target, and determine the maximum activity radius of the target during each dipping sonar detection by the flight equipment. The maritime search includes multiple consecutive dipping sonar detections by multiple flight equipment. Constructing the dynamic activity range of the maritime search target includes: determining the maximum activity radius of the target during the i-th dipping sonar detection by the flight equipment as: ,in, This indicates the i-th sonar deployment. The maximum radius of motion of the target during the i-th dipping sonar detection by the flight equipment. The target's maximum movement speed, The time delay from when the target loses contact to when the search begins. This refers to the cycle of a single sonar deployment operation. The initial report shows the mean square error of the target's location.

[0073] Step S202: Based on the dynamic activity range, construct dynamic spatial constraints for the deployment point, where the deployment point is the detection point for the flight equipment to deploy sonar, specifically including:

[0074] Establish a polar coordinate system with the location where the target lost contact as the origin;

[0075] The radial distance constraint for the i-th launch point of the k-th flight equipment is as follows: ,in, Let be the polar radius of the i-th hoisting point of the k-th flight equipment in the polar coordinate system. Let the polar radius of the (i-1)th hoisting point of the k-th flight equipment be in the polar coordinate system. The radial random growth coefficient, Let be the maximum radius of motion of the target during the i-th dipping sonar detection by the flight equipment. The maximum radius of activity of the target during the (i-1)th dipping sonar detection by the flight equipment;

[0076] The angle increment constraint for the i-th launching point of the k-th flight equipment is as follows: ,in, For the angle increment constraint of the i-th hoisting point of the k-th flight equipment, Let the polar angle of the i-th hoisting point of the k-th flight equipment be in the polar coordinate system. Let the polar angle of the (i-1)th hoisting point of the k-th flight equipment be in the polar coordinate system. Let be the angle threshold of the i-th launching point of the k-th flight equipment, and , where λ is the distance factor of the deployment point and Rs is the effective detection radius of the sonar.

[0077] Step S203: Set the polar coordinates of the initial hoisting point for each flight equipment.

[0078] An initial population is established, comprising multiple samples. A polar coordinate system is established with the location where the target lost contact as the origin. Each sample includes multiple elements, each element representing the polar coordinates of a single deployment point of a flight device in the polar coordinate system. Each sample includes the polar coordinates of all deployment points of each flight device except the initial deployment point. Furthermore, based on satisfying the dynamic spatial constraints of the flight device's sonar deployment points, the polar coordinates of multiple deployment points in the sample are randomly set between adjacent deployment points of the same flight device.

[0079] Step S204: Set the fitness function, which calculates the fitness value of each sample based on the coverage of each sample.

[0080] Step S205: Perform multiple iterations until the iteration termination condition is met, then end the iteration. In each iteration, calculate the test sample for each sample in the current iteration population, and put the test sample and the sample with the higher fitness value in the corresponding sample into the population of the next iteration as the sample of the next iteration population.

[0081] Step S206: After the iteration ends, the sample with the highest fitness value in the population at the end of the iteration is taken as the optimal solution.

[0082] This embodiment discloses a method for optimizing the layout of dipping sonar detection points for search flight equipment based on dynamic constraint modeling and an improved differential evolution algorithm. It is particularly suitable for conducting multi-aircraft coordinated and efficient acoustic detection missions for underwater targets such as wrecked ships or sunken submarines when the direction of movement of underwater targets is unknown and the trajectory is uncertain.

[0083] The key parameters involved in this invention are shown in Table 1:

[0084] Table 1

[0085]

[0086] Specifically, first, step S201 is executed to construct the dynamic activity range of the maritime search target and determine the maximum activity radius of the target during each dipping sonar detection by the flight equipment. The maritime search includes multiple consecutive dipping sonar detections by multiple flight equipment. Constructing the dynamic activity range of the maritime search target includes: determining the maximum activity radius of the target during the i-th dipping sonar detection by the flight equipment as follows: ,in, This indicates the i-th sonar deployment. The maximum radius of motion of the target during the i-th dipping sonar detection by the flight equipment. The target's maximum movement speed, The time delay from when the target loses contact to when the search begins. This refers to the cycle of a single sonar deployment operation. The initial report shows the mean square error of the target's location.

[0087] Specifically, the first step is to model the dynamic activity range of the crashed target.

[0088] Assuming that when the search aircraft performs the i-th dipping detection, the target's possible activity range is centered on its initial reported position, Let be the radius of the largest movable circle. This radius is calculated by the following formula:

[0089] (1)

[0090] in, Let represent the i-th sonar deployment. This model comprehensively considers the initial positioning error and the maximum drift distance accumulated over time, providing a reasonable spatial boundary for target search. It assumes that the target follows a uniform or Gaussian diffusion distribution within this circular domain, serving as the probabilistic basis for optimizing the deployment point.

[0091] The target velocity is an estimate, obtained when the ocean current direction and wind speed are aligned.

[0092] In some embodiments, It is the wind speed multiplied by the attenuation factor and the ocean current speed.

[0093] This is an input parameter set by the user, typically 1km or 2km. Alternatively, it can be assumed that the mean square error of the search device determining the final contact point location is... The root mean square error of the initial hoisting point for the flight equipment is Then the overall positioning mean square error for:

[0094] .in, and This is then used as an input parameter and set by the user.

[0095] Then, step S202 is executed, constructing dynamic spatial constraints for the deployment point based on the dynamic activity range. The deployment point is the detection point for the flight equipment's deployed sonar, specifically including:

[0096] Establish a polar coordinate system with the location where the target lost contact as the origin;

[0097] The radial distance constraint for the i-th launch point of the k-th flight equipment is as follows: ,in, Let be the polar radius of the i-th hoisting point of the k-th flight equipment in the polar coordinate system. Let the polar radius of the (i-1)th hoisting point of the k-th flight equipment be in the polar coordinate system. The radial random growth coefficient can be considered as a disturbance of the polar diameter at the lifting point. Let be the maximum radius of motion of the target during the i-th dipping sonar detection by the flight equipment. The maximum radius of activity of the target during the (i-1)th dipping sonar detection by the flight equipment;

[0098] The angle increment constraint for the i-th launching point of the k-th flight equipment is as follows: ,in, For the angle increment constraint of the i-th hoisting point of the k-th flight equipment, Let the polar angle of the i-th hoisting point of the k-th flight equipment be in the polar coordinate system. Let the polar angle of the (i-1)th hoisting point of the k-th flight equipment be in the polar coordinate system. Let be the angle threshold of the i-th launching point of the k-th flight equipment, and , where λ is the distance factor of the deployment point and Rs is the effective detection radius of the sonar.

[0099] Specifically, in step S202, dynamic spatial constraints for the suspension points are constructed.

[0100] A polar coordinate system is established with the target's location at the time of loss of contact as the origin. To ensure continuous detection and avoid blind spots and backtracking searches, this embodiment proposes two types of constraints that are adaptively updated with each deployment cycle. The dynamic spatial constraints include radial constraints and angular increment constraints.

[0101] Radial constraint:

[0102] Let the radial distance of the i-th launch point of the k-th flight equipment be... The radius of the target's maximum active circle at the corresponding time is Then the radial distance of the (i+1)th lifting point It should satisfy:

[0103] (2)

[0104] in This is the radial growth coefficient, reflecting the overall outward diffusion trend of the target, preventing backtracking caused by the inward contraction of the detection point. Let be the polar radius of the i-th hoisting point of the k-th flight equipment in the polar coordinate system. Let the polar radius of the (i-1)th hoisting point of the k-th flight equipment be in the polar coordinate system. Let be the maximum radius of motion of the target during the i-th dipping sonar detection by the flight equipment. The maximum operating radius of the target during the (i-1)th dipping sonar detection by the flight equipment.

[0105] Angle increment constraint:

[0106] To avoid detection blind spots between adjacent launch points, the angular increment between adjacent detection points of the same flight equipment over time is defined. It must not exceed the angle threshold. The calculation formula is:

[0107] (3)

[0108] (4)

[0109] In formula (3), λ is the distance factor between the lifting points. For the effective detection radius of the sonar, in formula (4), For the angle increment constraint of the i-th hoisting point of the k-th flight equipment, Let the polar angle of the i-th hoisting point of the k-th flight equipment be in the polar coordinate system. Let the polar angle of the (i-1)th hoisting point of the k-th flight equipment be in the polar coordinate system. Let be the angle threshold for the i-th deployment point of the k-th flying device. Angle increment constraints ensure that the detection range of the current deployment point overlaps with the previous point, achieving continuous coverage. When As the angle increases, the allowable angle interval automatically decreases to maintain detection continuity. Furthermore, a sector division strategy is employed among multiple aircraft, with each flight device responsible for a preset angle interval to avoid excessive overlap of detection areas.

[0110] Then, steps S203 to S206 are performed to optimize the improved differential evolution algorithm.

[0111] To find the optimal combination of hoisting points that satisfies the above constraints, this embodiment uses an improved differential evolution algorithm to optimize the location of the hoisting points with the goal of maximizing the search coverage.

[0112] Specifically, step S203 is executed to fix the polar coordinates of the initial hoisting point of each flight equipment;

[0113] An initial population is established, comprising multiple samples. A polar coordinate system is established with the location where the target lost contact as the origin. Each sample includes multiple elements, each element representing the polar coordinates of a single deployment point of a flight device in the polar coordinate system. Each sample includes the polar coordinates of all deployment points of each flight device except the initial deployment point. Furthermore, based on satisfying the dynamic spatial constraints of the flight device's sonar deployment points, the polar coordinates of multiple deployment points in the sample are randomly set between adjacent deployment points of the same flight device.

[0114] Specifically, in order to find the optimal combination of hanging points that satisfies the above constraints, this invention employs an improved differential evolution algorithm with the goal of maximizing the search coverage.

[0115] First, the polar coordinates of the initial launch point for each flight equipment are fixed.

[0116] In one embodiment, the fixed setting of the polar coordinates of the initial launch point for each flight device includes:

[0117] The polar coordinates of the initial launch point of the k-th flight equipment for each sample are fixed as follows:

[0118] ,in, Let the polar radius of the initial deployment point of the k-th flight equipment be the polar radius of the deployment point in the polar coordinate system. Let the polar angle of the initial deployment point of the k-th flight equipment in the polar coordinate system be denoted as . This refers to the maximum operating radius of the target during the initial dipping sonar detection by the flight equipment. C represents the effective detection radius of the sonar, and C represents the number of flying devices.

[0119] Specifically, to ensure that the initial lifting points are evenly distributed along the circumference of the initial search response point, the initial lifting point of the k-th flight equipment is fixed as follows:

[0120] (5)

[0121] in, Let the polar radius of the initial deployment point of the k-th flight equipment be the polar radius of the deployment point in the polar coordinate system. Let the polar angle of the initial deployment point of the k-th flight equipment in the polar coordinate system be denoted as . This refers to the maximum operating radius of the target during the initial dipping sonar detection by the flight equipment. C represents the effective detection radius of the sonar, and C represents the number of flying devices.

[0122] Then, population initialization is performed. The population includes multiple samples, each of which is a sample in the improved differential evolution algorithm. The samples are encoded with real numbers, and each sample represents a complete hoisting scheme. Each sample includes multiple elements, each element representing the polar coordinates of a hoisting point of a flight device in the polar coordinate system. The first hoisting point of each flight device is set using formula (5). The improved differential evolution algorithm optimizes the second to third hoisting points of different flight devices. The parameters for the second launch point are specifically for optimizing the flight equipment. The polar coordinates of the i-th deployment point of the k-th flight equipment are represented as follows: ,in Let be the polar radius of the i-th launching point of the k-th flight equipment. Let be the polar angle of the i-th launching point of the k-th flight equipment. To ensure that all initial populations satisfy the constraints and reduce the generation of invalid solutions, the q-th solution in population Q is... The initialization introduces radial constraints and angular increment constraints. That is, in the same flight equipment, except for the first launch point, the polar coordinates of each launch point and the polar coordinates of the previous launch point need to satisfy the radial constraint of formula (2) and the angular increment constraint of formula (4). The expression for the qth sample is:

[0123] (6)

[0124] in Let Q be the q-th sample containing Each element corresponds to a polar coordinate of the second and subsequent launch points of all flight equipment.

[0125] Then, step S204 is executed to set the fitness function, which calculates the fitness value of a sample based on the coverage of each sample.

[0126] In one embodiment, setting the fitness function includes:

[0127] Set the fitness function as follows: ,in, Let be the fitness value of the q-th sample. This represents the actual coverage area of ​​the q-th sample calculated using the Monte Carlo algorithm. The target's maximum movement speed, The time delay from when the target loses contact to when the search begins. This refers to the cycle of a single sonar deployment operation. The initial reported positional error is given by N, where N is the number of launches allowed for each flight device.

[0128] Specifically, the Monte Carlo algorithm was used to calculate the actual coverage area of ​​the N hoisting points of the C-frame flight equipment, and the sample... The coverage rate is:

[0129] (7)

[0130] In formula (7), Let be the fitness value of the q-th sample. This represents the actual coverage area calculated using the Monte Carlo algorithm for all drop points, with the denominator representing the maximum area of ​​activity of the crashed target during the Nth drop by the search flight equipment.

[0131] In some embodiments, the Monte Carlo method is used to calculate the actual coverage area, including:

[0132] A large number of sampling points (e.g., 10,000 points) are generated uniformly and randomly within the active circle area defined by the maximum active radius of the target.

[0133] For each sampling point, determine whether it is within the detection range (radius Rs = 3km) of any drop point;

[0134] Calculate coverage rate = number of covered points / total number of sampling points;

[0135] Calculate the actual coverage area = coverage rate × total area of ​​the maximum active circle.

[0136] 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, the test sample of each sample in the current iteration population is calculated, and the test sample and the sample with the higher fitness value in the corresponding sample are put into the population of the next iteration as samples of the next iteration population.

[0137] In one embodiment, calculating the test sample for each sample in the current iteration population includes:

[0138] For each sample in the population in this iteration, the corresponding experimental sample is calculated as follows:

[0139] ;

[0140] ,in, Let be the first random sample randomly drawn from the population Q in the t-th iteration. Let be the second random sample randomly drawn from the population Q in the t-th iteration. Let be the third random sample randomly drawn from the population Q in the t-th iteration, and the first, second, and third random samples are different. Scaling factor Let be the difference sample corresponding to the q-th sample in the population during the t-th iteration. This represents the d-th element of the experimental sample corresponding to the q-th sample in the t-th iteration. Cross factor Let d be the d-th element of the difference sample corresponding to the q-th sample in the population during the t-th iteration. Let be the d-th element of the q-th sample in the population during the t-th iteration, and rand be a random number. Indicates from A random element is selected from the data, where C is the number of flying devices and N is the number of times each flying device is allowed to perform a hoisting operation.

[0141] Specifically, perform the differential mutation operation. In the t-th iteration, perform a differential mutation operation on the population sample. Differential mutation is performed to obtain mutated samples. and test samples :

[0142] (8)

[0143] (9)

[0144] In formula (8), , and This indicates that three distinct samples are randomly selected from the population Q in the t-th iteration. Indicates the scaling factor. This represents the sample after the difference operation. In formula (9) This refers to the mutated sample, i.e., the test sample. Represents the crossover factor, and rand is a random number in the range (0,1). Indicates from Randomly select an element from the list. Ensure the test samples after mutation At least inheritance One of the elements.

[0145] Then, a selection operation is performed to compare the original samples. coverage With test samples coverage Select the better samples for the next iteration:

[0146] (10)

[0147] in, This is the q-th sample entering the (t+1)-th iteration. In the t-th iteration, if the original sample... coverage ≥Test Sample coverage Then select the original sample. As the q-th sample in the (t+1)th iteration, otherwise select the experimental sample. As the qth sample in the t+1th iteration.

[0148] In some embodiments, for each sample in the current iteration population, after calculating the corresponding test sample, the method further includes:

[0149] For each element of the test sample, check whether it meets the radial constraint and the angle increment constraint. That is, for each test sample, except for the first launch point in the same flight equipment, compare the polar coordinates of each launch point with the polar coordinates of the previous launch point to determine whether it meets the radial constraint of formula (2) and the angle increment constraint of formula (4).

[0150] If there are elements in the test sample that do not satisfy the radial constraint and / or the angle increment constraint, then the element is subject to boundary constraints, pulling the polar radius of the element that does not satisfy the radial constraint back to the boundary of the radial constraint, and / or pulling the polar angle of the element that does not satisfy the angle increment constraint back to the boundary of the angle increment constraint.

[0151] For example, Let be the polar radius of the i-th launching point of the k-th flight equipment. The polar angle of the i-th launch point of the k-th flight equipment needs to satisfy the following boundary constraints:

[0152] ;

[0153] .

[0154] In some embodiments, optimizing the locations of multiple launch points for one or more flight devices using an improved differential evolution algorithm also includes maintaining population diversity.

[0155] In some embodiments, in each iteration, after calculating the trial samples for each sample in the current iteration population and placing the trial samples and the samples with higher fitness values ​​in the corresponding samples into the population for the next iteration, the method further includes:

[0156] If a preset number of iterations is set, a new sample is generated and replaced with the sample with the lowest fitness value in the current iteration population in the next iteration population.

[0157] Specifically, every 10 generations, a new sample is generated and re-initialized to replace the 10% of samples with the lowest fitness values ​​in the population, and new samples that meet the dynamic constraints are added to avoid the population getting trapped in local optima.

[0158] Finally, step S206 is executed. After the iteration ends, the sample with the highest fitness value in the population at the end of the iteration is taken as the optimal solution.

[0159] Specifically, the differential mutation operation, selection operation, and population diversity maintenance operation are repeated, that is, step S205 is repeatedly executed until the number of iterations reaches the preset threshold or the coverage increase of multiple consecutive iterations is lower than the convergence threshold. Then, it is determined that the iteration termination condition is met, the iteration ends, and the sample with the highest fitness value in the population at the end of the iteration is output as the optimal placement point planning scheme.

[0160] This embodiment exhibits strong target adaptability. By establishing a time-evolution-based maximum activity circle model, it accurately reflects the diffusion trend of underwater trapped targets, avoiding blind spots or resource waste caused by rigid search boundaries and improving the scientific rigor of the search. Simultaneously, it demonstrates high detection continuity. By introducing dynamic constraints of radial increment and angular increment, it effectively prevents detection backtracking and wedge-shaped blind spots, ensuring the spatial continuity and integrity of multi-round detection. Furthermore, this embodiment boasts high optimization efficiency. By incorporating physical constraints into the initialization phase of the improved differential evolution algorithm, it significantly reduces invalid solutions. Combined with a diversity maintenance mechanism, it accelerates convergence. Finally, this embodiment exhibits excellent collaborative coverage performance, supporting multi-machine collaborative operations. Through sector allocation and global optimization, it achieves omnidirectional balanced detection, increasing the probability of detecting targets drifting in unknown directions.

[0161] like Figure 3 The diagram shown is a flowchart of an adaptive optimization method for sonar deployment points of a flight-mounted device, according to a preferred embodiment of the present invention. The flight-mounted device is preferably a helicopter, and includes:

[0162] Step S301: Combine the maximum moving speed (drift speed), positioning error, delay time, and hoisting cycle to construct the dynamic activity area of ​​the target over time;

[0163] Step S302: Construct the helicopter sonar deployment model and the dynamic spatial constraints of the sonar deployment point;

[0164] Step S303: Initialize the population based on the dynamic constraints of the hoisting point, and iteratively optimize the position of the hoisting point using an improved differential evolution method.

[0165] The method proposed in this embodiment can achieve adaptive optimization of the layout of multiple search helicopter launch points in complex sea conditions where the target's motion direction is unknown. It has good engineering practicality and promotion value, and can be widely used in target search, underwater detection and other fields.

[0166] The following is an experimental example of the present invention.

[0167] 1. Experimental Environment

[0168] The experimental hardware environment in this embodiment is an Intel Core i9-13900K processor and 32GB of memory.

[0169] The specific experimental steps will be described in detail below.

[0170] Step 1: Parameter Initialization

[0171] km / h, km, min, min, km, Distance factor of the hoisting point .

[0172] Step 2: Calculate the maximum radius of the movable circle for each hoisting operation.

[0173] According to formula (1), the maximum radius of the movable circle corresponding to each hoisting operation was calculated, and the results are shown in Table 2:

[0174] Table 2

[0175]

[0176] Step 3: Dynamic Constraint Construction

[0177] Each lifting point needs to consider radial constraints and angular increment constraints.

[0178] Taking the second deployment of the first flight equipment as an example:

[0179] Radial constraint: Polar diameter of the first launch point of the first flight equipment =3, assuming radial random growth coefficient Then the extreme diameter of the second lifting point satisfies

[0180] Angle increment constraint: If =4, then the angle threshold of the first placement point =1.79, the angle increment range is .

[0181] Step 4: Generation of Multi-Machine Collaboration Scheme

[0182] The population size for differential evolution is set to 100, the maximum number of iterations is 100, and the scaling factor is [not specified]. = 0.5, cross factor = 0.5. Running the improved differential evolution algorithm, the resulting deployment schemes and coverage curves for different numbers of search helicopters are shown below. Figure 4a , Figure 4b , Figure 4c and Figure 4d As shown. Among them, Figure 4a It includes curve 411 for the hoisting scheme of the first helicopter and curve 412 for the hoisting scheme of the second helicopter. Figure 4b It includes the launching scheme curve 421 for the first helicopter, the launching scheme curve 422 for the second helicopter, and the launching scheme curve 423 for the third helicopter. Figure 4c This includes coverage variation curves for different iterations of the dual-rack machine 43. Figure 4d This includes coverage variation curves for three machines at different iteration numbers.44

[0183] like Figure 4a and Figure 4b As shown, the method proposed in this embodiment can adaptively adjust the layout of the hoisting points according to the trend of target diffusion over time. The coverage of the dual-machine and triple-machine schemes tends to stabilize after about 30 iterations. Figure 4c and Figure 4d The coverage curves show that the improved algorithm converges quickly and does not exhibit significant oscillations or stagnation, verifying its stability and efficiency.

[0184] 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.

[0185] like Figure 5 The diagram shown is a hardware structure schematic of an electronic device according to the present invention, comprising:

[0186] At least one processor 501; and,

[0187] A memory 502 is communicatively connected to at least one of the processors 501; wherein,

[0188] The memory 502 stores instructions that can be executed by at least one of the processors to enable the at least one of the processors to perform the adaptive optimization method for the sonar deployment point of the flight equipment as described above.

[0189] Figure 5 Take a processor 501 as an example.

[0190] The electronic device may also include an input device 503 and a display device 504.

[0191] The processor 501, memory 502, input device 503 and display device 504 can be connected by a bus or other means. The figure shows an example of connection by bus.

[0192] The memory 502, 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 adaptive optimization method for sonar deployment points of flight equipment in the embodiments of this application, for example, Figure 1 , Figure 2 The method flow is shown. The processor 501 executes various functional applications and data processing by running non-volatile software programs, instructions, and modules stored in the memory 502, thereby realizing the adaptive optimization method for the sonar deployment point of the flight equipment in the above embodiment.

[0193] Memory 502 may include a program storage area and a data storage area. The program storage area may store an operating system and application programs required for at least one function. The data storage area may store data created based on the use of the adaptive optimization method for sonar dipping points of the flight equipment. Furthermore, memory 502 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, memory 502 may optionally include memory remotely located relative to processor 501, and this remote memory may be connected via a network to means of performing the adaptive optimization method for sonar dipping points of the flight equipment. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0194] The input device 503 can receive user clicks and generate signal inputs related to user settings and function control of the adaptive optimization method for the sonar dipping point of the flight equipment. The display device 504 may include a display screen or other display device.

[0195] When one or more modules are stored in the memory 502 and are run by one or more processors 501, the adaptive optimization method for the sonar deployment point of the flight equipment in any of the above method embodiments is executed.

[0196] This invention constructs a dynamic range of movement for a maritime search target, establishes dynamic spatial constraints on deployment points, and optimizes the positions of multiple deployment points for one or more flight devices under these dynamic spatial constraints using an improved differential evolution algorithm. The proposed method enables adaptive optimization of the deployment point layout for multiple searches in complex sea conditions where the target's direction of motion is unknown. It possesses good engineering practicality and widespread applicability, and can be broadly applied in target search, underwater detection, and other fields.

[0197] 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 steps of the adaptive optimization method for sonar deployment points of flight equipment as described above.

[0198] 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.

[0199] One embodiment of the present invention provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the adaptive optimization method for sonar deployment points of flight equipment as described above.

[0200] 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. An adaptive optimization method for sonar deployment points of flight equipment, characterized in that, include: The dynamic activity range of the maritime search target is constructed, and the maximum activity radius of the target is determined during each dipping sonar detection by the flight equipment. The maritime search includes multiple dipping sonar detections by multiple flight equipment in succession. Based on the aforementioned dynamic activity range, dynamic spatial constraints are constructed for the deployment point, which is the detection point for the sonar deployed by the flight equipment. Based on the aforementioned dynamic spatial constraints, the positions of multiple launch points for one or more flight devices are optimized using an improved differential evolution algorithm. The construction of dynamic spatial constraints for the hoisting point based on the dynamic activity range includes: Establish a polar coordinate system with the location where the target lost contact as the origin; The radial distance constraint for the i-th launch point of the k-th flight equipment is: ,in, Let be the polar radius of the i-th hoisting point of the k-th flight equipment in the polar coordinate system. Let the polar radius of the (i-1)th hoisting point of the k-th flight equipment be in the polar coordinate system. The radial random growth coefficient, Let be the maximum radius of motion of the target during the i-th dipping sonar detection by the flight equipment. The maximum radius of activity of the target during the (i-1)th dipping sonar detection by the flight equipment; The angle increment constraint for the i-th launching point of the k-th flight equipment is as follows: ,in, For the angle increment constraint of the i-th hoisting point of the k-th flight equipment, Let the polar angle of the i-th hoisting point of the k-th flight equipment be in the polar coordinate system. Let the polar angle of the (i-1)th hoisting point of the k-th flight equipment be in the polar coordinate system. Let be the angle threshold of the i-th launching point of the k-th flight equipment, and Where λ is the distance factor of the deployment point and Rs is the effective detection radius of the sonar; The optimization of the positions of multiple launch points for one or more flight devices using an improved differential evolution algorithm includes: The polar coordinates of the initial hoisting point for each flight equipment are fixed. An initial population is established, comprising multiple samples. A polar coordinate system is established with the location where the target loses contact as the origin. Each sample includes multiple elements, each element representing the polar coordinates of a single deployment point of a flight device in the polar coordinate system. Each sample includes the polar coordinates of all deployment points of each flight device except the initial deployment point. Furthermore, based on satisfying the dynamic spatial constraints of the flight device's sonar deployment points, the polar coordinates of multiple deployment points in the sample are randomly set. Set a fitness function, which calculates the fitness value of a sample based on the coverage of each sample; Perform multiple iterations until the iteration termination condition is met, then terminate the iteration. In each iteration, calculate the test sample for each sample in the current iteration population, and add the test sample and the sample with the higher fitness value in the corresponding sample to the population of the next iteration as the sample of the next iteration population. After the iteration ends, the sample with the highest fitness value in the population at the end of the iteration is taken as the optimal solution; The fixed polar coordinates of the initial hoisting point for each flight equipment include: The polar coordinates of the initial launch point of the k-th flight equipment for each sample are fixed as follows: ,in, Let the polar radius of the initial deployment point of the k-th flight equipment be the polar radius of the deployment point in the polar coordinate system. Let the polar angle of the initial deployment point of the k-th flight equipment in the polar coordinate system be denoted as . This refers to the maximum operating radius of the target during the initial dipping sonar detection by the flight equipment. C represents the effective detection radius of the sonar, and C represents the number of flying devices. The setting of the fitness function includes: Set the fitness function as follows: ,in, Let be the fitness value of the q-th sample. This represents the actual coverage area of ​​the q-th sample calculated using the Monte Carlo algorithm. The target's maximum movement speed, The time delay from when the target loses contact to when the search begins. This refers to the cycle of a single sonar deployment operation. The initial reported positional error is given by N, where N is the number of launches allowed for each flight device.

2. The adaptive optimization method for sonar deployment points of flight equipment according to claim 1, characterized in that, The dynamic activity range for constructing maritime search targets includes: The maximum radius of motion of the target during the i-th dipping sonar detection by the flight equipment is determined as: ,in, This indicates the number of times the sonar has been deployed. The maximum radius of motion of the target during the i-th dipping sonar detection by the flight equipment. The target's maximum movement speed, The time delay from when the target loses contact to when the search begins. This refers to the cycle of a single sonar deployment operation. The initial report shows the mean square error of the target's location.

3. The adaptive optimization method for sonar deployment points of flight equipment according to claim 1, characterized in that, The calculation of the test samples for each sample in the population in this iteration includes: For each sample in the population in this iteration, the corresponding experimental sample is calculated as follows: ； ,in, Let be the first random sample randomly drawn from the population Q in the t-th iteration. Let be the second random sample randomly drawn from the population Q in the t-th iteration. Let be the third random sample randomly drawn from the population Q in the t-th iteration, and the first, second, and third random samples are different. Scaling factor Let be the difference sample corresponding to the q-th sample in the population during the t-th iteration. This represents the d-th element of the experimental sample corresponding to the q-th sample in the t-th iteration. Cross factor Let d be the d-th element of the difference sample corresponding to the q-th sample in the population during the t-th iteration. Let d be the d-th element of the q-th sample in the population during the t-th iteration. Indicates from A random element is selected from the data, where C is the number of flying devices and N is the number of times each flying device is allowed to perform a hoisting operation.

4. 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 executable by at least one of the processors, which are executed to enable the at least one of the processors to perform the adaptive optimization method for sonar deployment points of flight equipment as described in any one of claims 1 to 3.

5. A storage medium, characterized in that, The storage medium stores computer instructions, which, when executed by the computer, are used to perform all steps of the adaptive optimization method for sonar deployment points of flight equipment as described in any one of claims 1 to 3.

6. 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 adaptive optimization method for sonar deployment points of flight equipment as described in any one of claims 1 to 3.

Images