An unmanned surface vehicle communication relay method

Abstract

The application discloses an unmanned ship communication relay method and device, equipment, a storage medium and a system, relates to the technical field of unmanned surface vehicle cluster communication networking and underwater task planning. The method introduces an underwater acoustic propagation model on the basis of a traditional K-means algorithm, comprehensively considers distance propagation loss, ocean environmental noise and obstacle propagation loss, converts a communication quality index into a weight coefficient through a Sigmoid function, constructs an improved K-means loss function, and realizes reasonable clustering of underwater task points and optimization of USV positions. The application fully combines the characteristics of underwater acoustic communication, improves the scientificity and practicability of multi-unmanned ship communication relay planning, can effectively solve the problem of unreasonable task point distribution in a complex underwater environment, and improves the reliability and stability of underwater communication.

Description

Technical Field

[0001] This application relates to the field of unmanned surface vessel swarm communication networking and underwater mission planning technology, specifically to an unmanned surface vessel communication relay method, device, equipment, storage medium and system. Background Technology

[0002] As marine exploration, resource surveying, and underwater rescue missions continue to expand into deep-sea and complex waters, the demand for information exchange between underwater operational equipment is increasing. Due to factors such as the characteristics of seawater, underwater topography, and operational distance, underwater communication links typically suffer from high propagation attenuation, limited communication distance, and insufficient stability. Unmanned surface vehicles (USVs) offer advantages such as maneuverability, convenient deployment, and strong communication payload capacity. They can serve as surface communication relay nodes, providing communication support to multiple underwater mission sites or underwater operational equipment, thereby constructing a multi-USV collaborative communication relay network.

[0003] In existing technologies, task points are typically allocated based on the spatial distance between the task point and the USV. Clustering is achieved by minimizing intra-class distance, and relay node locations are determined based on a preset communication radius to realize the grouping of underwater task points and the planning of USV relay locations. The above methods can complete the division of task points and the configuration of relay nodes under relatively ideal communication environments and conditions where the distribution of task points is relatively regular or there are few obstacles. However, they still have shortcomings under conditions of complex marine environments, significant differences in communication link quality, and underwater acoustic propagation being affected by various factors.

[0004] Existing methods suffer from at least the following problems: the task point partitioning process relies primarily on spatial distance, making it difficult to reflect the actual propagation state of underwater acoustic signals; the impact of marine environmental noise and underwater obstacles on communication links is not fully considered; and the location planning of relay USVs does not match the actual communication quality. These problems can easily lead to unreasonable task point grouping, insufficient local communication coverage, and decreased link reliability, resulting in increased communication error rates, reduced task execution efficiency, and slower collaborative response. Summary of the Invention

[0005] The main objective of this application is to provide an unmanned surface vessel (USV) communication relay method, apparatus, device, storage medium, and system. The aim is to introduce an underwater acoustic communication model based on the traditional K-means algorithm to solve the problem of unreasonable underwater task point allocation caused by various interference factors in actual underwater environments.

[0006] To achieve the above objectives, the first aspect of this application provides an unmanned surface vessel (USV) communication relay method, comprising: acquiring the three-dimensional coordinates of underwater mission points, the number of USVs, and the mission area; initializing the position coordinates of each USV; calculating the distance between each USV and each underwater mission point; calculating the attenuated signal strength from each USV to each underwater mission point based on an underwater acoustic propagation model, wherein the underwater acoustic propagation model includes propagation loss due to distance, marine environmental noise, and obstacle propagation loss; normalizing the attenuated signal strength to obtain a communication quality index; converting the communication quality index into weight coefficients using a Sigmoid function, and constructing an improved K-means loss function containing the weight coefficients; iteratively clustering the underwater mission points based on the improved K-means loss function until the clustering results converge to obtain the USV group to which each underwater mission point belongs; recalculating the position coordinates of the corresponding USVs based on the coordinates of the underwater mission points within each USV group, and performing unmanned surface vessel relay communication based on the recalculated USV position coordinates.

[0007] Optionally, the propagation loss caused by the distance is calculated using the following formula:

[0008] In the formula, TL D For sound propagation loss, n For coefficients under different propagation conditions, L ij for USV i With mission points j The distance between them α Seawater sound absorption coefficient; Seawater sound absorption coefficient α The relationship between the frequency of the sound signal and the frequency is:

[0009] In the formula, f The frequency of the sound signal.

[0010] Optionally, the marine environmental noise includes wind noise, rain noise and distant ship noise, and the wind noise includes high-frequency wind noise and low-frequency wind noise; Among them, for high-frequency wind noise The following model is used for calculation:

[0011]

[0012] In the formula, v is the wind speed, with the unit being m / s. f w The frequency of wind noise is given by the unit . kHz , ΔT For temperature difference, δ ( Δt () represents the temperature difference function; The temperature difference is defined as follows:

[0013] In the formula, T air For air temperature, T sea Seawater temperature; For low-frequency wind noise The following model is used for calculation:

[0014] Rain noise Calculated using the following formula:

[0015] In the formula, R For rainfall, λ (v) and μ (v) refers to wind speed v Piecewise functions; Dipole noise level of a distant ship Calculated using the following formula:

[0016] In the formula, k For wave number, d The depth of the original monopole sound source. N This represents the number of ships per unit area. SL ship This indicates the monopole sound source spectral level of the ship. Represented as:

[0017] In the formula, f s This refers to the frequency of ship noise.

[0018] Optionally, the obstacle propagation loss is calculated using the following logarithmic function:

[0019] In the formula, TL Ob This indicates the loss of propagation due to obstacles. D x1 and D x2This represents the perpendicular distance from the two edge points of the obstacle to the line connecting the signal source and the underwater mission point. D L It represents the distance from the signal source to the nearest intersection point of the obstacle along the line connecting the signal source and the underwater mission point.

[0020] Optionally, the function for normalizing the attenuated signal strength is:

[0021] In the formula, ρ ij This is the result after normalization. SL ij For the first i USV in the first j The attenuated signal strength emitted from each underwater mission point p and q These are all coefficients of the normalized function, where, p Used to control the rate of change of the normalization function q Used to change the position of the normalization function in the horizontal direction.

[0022] Optionally, the communication quality metrics can be converted into weighting coefficients using a Sigmoid function. The formula is:

[0023] In the formula, ρ ij This is the value of the signal strength after normalization. m and n These are the parameters that control the change of the function; The improved K-means loss function takes the form of:

[0024] in, Y The value of the loss function. I For the number of USVs, J It refers to the number of underwater mission sites. Y k The loss function value after introducing the communication model.

[0025] In addition, to achieve the above objectives, this application also provides an unmanned surface vessel communication relay device, including: The initialization module is used to obtain the three-dimensional coordinates of the underwater mission point, the number of USVs, and the mission area; and to initialize the position coordinates of each USV. The distance calculation module is used to calculate the distance between each USV and each underwater mission point; The signal strength calculation module is used to calculate the attenuated signal strength from each USV to each underwater mission point based on an underwater acoustic propagation model, which includes propagation loss caused by distance, marine environmental noise, and obstacle propagation loss; the attenuated signal strength is normalized to obtain communication quality indicators; The weight coefficient construction module is used to convert the communication quality index into weight coefficients through the Sigmoid function and construct an improved K-means loss function containing the weight coefficients. The clustering module is used to iteratively cluster underwater mission points based on the improved K-means loss function until the clustering results converge, thereby obtaining the USV group to which each underwater mission point belongs. The position update module is used to recalculate the position coordinates of the corresponding USV based on the coordinates of the underwater mission points within each USV group, and to perform unmanned surface vessel relay communication based on the recalculated position coordinates of the USV.

[0026] To achieve the above objectives, a third aspect of this application provides an electronic device including a processor and a memory, wherein the memory stores instructions that, when executed by the processor, implement the unmanned surface vessel communication relay method as described in any one aspect of the first application.

[0027] To achieve the above objectives, a fourth aspect of this application provides a computer-readable storage medium having program instructions stored thereon that, when executed by a processor, implement the unmanned surface vessel communication relay method as described in any one aspect of the first application.

[0028] To achieve the above objectives, a fifth aspect of this application provides a multi-unmanned surface vessel (USV) communication relay planning system, including multiple USVs and a controller, the controller being used to execute an unmanned surface vessel communication relay method as described in any of the first aspects.

[0029] This application proposes an unmanned surface vessel (USV) communication relay method, apparatus, device, storage medium, and system. The method includes acquiring the three-dimensional coordinates of underwater mission points, the number of USVs, and the mission area; initializing the position coordinates of each USV; calculating the distance between each USV and each underwater mission point; calculating the attenuated signal strength from each USV to each underwater mission point based on an underwater acoustic propagation model, which includes propagation loss due to distance, marine environmental noise, and obstacle propagation loss; normalizing the attenuated signal strength to obtain a communication quality index; converting the communication quality index into weight coefficients using a sigmoid function and constructing an improved K-means loss function containing the weight coefficients; iteratively clustering the underwater mission points based on the improved K-means loss function until the clustering results converge to obtain the USV group to which each underwater mission point belongs; recalculating the position coordinates of the corresponding USVs based on the coordinates of the underwater mission points within each USV group; and performing unmanned surface vessel relay communication based on the recalculated USV position coordinates. This application improves upon the K-means algorithm, leveraging its speed and simplicity to achieve high efficiency even with a large number of underwater task points. An underwater acoustic communication model is introduced, quantifying and incorporating the effects of environmental noise, communication distance loss, and obstacles during signal propagation into the K-means algorithm. This ensures that the clustering algorithm fully considers underwater acoustic communication factors when allocating task points, resulting in allocation effects that better reflect reality. Attached Figure Description

[0030] Figure 1 This is a flowchart of the invention's technical solution; Figure 2 This is a task scenario diagram; Figure 3 Diagram showing the method for selecting obstacle distance; Figure 4 Normalization function parameters Control effect diagram; Figure 5 Normalization function parameters Control effect diagram; Figure 6 A trend chart for constructing a function that introduces weight coefficients in the K-means algorithm.

[0031] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0032] It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0033] Traditional underwater communication relay planning methods typically rely solely on Euclidean distance for clustering, such as directly using the standard K-means algorithm to assign underwater mission points to the nearest USVs based on geometric distance. However, this purely geometric approach ignores crucial factors such as the physical attenuation characteristics of underwater acoustic propagation, marine environmental noise interference, and terrain obstruction. In real-world complex waters, even if two mission points are spatially close, the presence of strong absorption layers or large obstacles in between can result in extremely poor communication quality; conversely, links with slightly greater distances but better channel conditions are more reliable. Therefore, clustering methods relying solely on geometric distance can lead to unreasonable deployment of USV relay nodes, large coverage blind spots in some areas, and high communication failure rates, severely impacting the efficiency and success rate of underwater detection, monitoring, and rescue missions.

[0034] To address the aforementioned problems, the first embodiment of this application provides an unmanned surface vessel (USV) communication relay method. This method solves the technical problems mentioned in the background art, such as poor underwater communication links and unreasonable deployment of USV relay nodes due to relying solely on geometric distance for task point grouping. The method can be executed by a processor, which can be located within the USV. (Refer to...) Figure 1 The execution process of this method can be described as follows: Step S101: Obtain the three-dimensional coordinates of the underwater mission point, the number of USVs, and the mission area range.

[0035] Determine the number of underwater mission sites 3D coordinates Scope of the mission area M and N are both in km, and N is the number of USVs that can serve as communication relay nodes on the water surface. Randomly initialize the USV's position coordinates within the task area. .

[0036] The entire mission scenario is as follows Figure 2 As shown below. (Combined with...) Figure 2 The scenario involves multiple underwater vehicles (USVs) distributed on the surface of the mission area, with several mission points underwater possessing three-dimensional coordinates, and obstacles affecting the propagation of underwater acoustic signals. Each USV acts as a surface communication relay node, establishing a communication link with the underwater mission points. Based on this scenario, the spatial distance between the USVs and the mission points can be determined, and the impact of propagation loss, environmental noise, and obstacles on communication quality can be further analyzed.

[0037] Step S102: Calculate the distance between each USV and each underwater mission point.

[0038] Among them, the distance between the USV and the mission point It can be defined as:

[0039] In the formula, For the first The location coordinates of each task point For the first The location coordinates of the USV.

[0040] Step S103: Calculate the attenuated signal strength from each USV to each underwater mission point based on the underwater acoustic propagation model. The underwater acoustic propagation model includes propagation loss caused by distance, marine environmental noise, and obstacle propagation loss. Normalize the attenuated signal strength to obtain the communication quality index.

[0041] In one embodiment of this application, step S103 includes the following sub-steps: Step S1031: Establish a mathematical model of the propagation distance and propagation loss between the USV and the underwater mission point.

[0042]

[0043] In the formula, For sound propagation loss, For coefficients under different propagation conditions, for With mission points The distance between them Seawater sound absorption coefficient α The relationship between the frequency of the sound signal and the frequency is:

[0044] In the formula, The frequency of the sound signal is expressed in units of 1000 ppm. .

[0045] It should be noted that the propagation coefficient varies under different propagation conditions. The values ​​of are different. When the sound wave propagates as a plane wave, Set to 0; when sound waves propagate as cylindrical waves in ideal waveguides formed by total internal reflection on the seabed and sea surface, Take 1; when considering interface sound absorption while the sound wave propagates as a cylindrical wave, Take 1.5; when the sound wave propagates as a spherical wave, Take 2; when the sound wave propagates after passing through the shallow sea negative transition layer, Take 3; when the sound wave propagates as a spherical wave or uses a dipole sound source, Take 4.

[0046] Step S1032: For the marine environmental noise model, this application mainly considers three cases: wind noise, rain noise, and distant ship noise.

[0047] Among them, considering wind noise, for the high-frequency band of 10-1000kHz wind noise This application adopts the following model:

[0048]

[0049] In the formula, Wind speed, unit: , The frequency of wind noise is given by the unit . , δ ( Δt ) represents the temperature difference function. Temperature difference, defined as:

[0050] In the formula, For air temperature, Seawater temperature, all units are... .

[0051] For low-frequency wind noise This application adopts the following model:

[0052] Taking rain noise into account, wind speed v Rain noise The impact can be expressed as:

[0053] In the formula, Rainfall amount, in units of , and All are about wind speed Piecewise functions In different ranges, and They can be defined as follows:

[0054]

[0055] In the frequency range of 1-100kHz, the final rain noise can be expressed as:

[0056] In the formula, The frequency of rain noise, in units of .

[0057] The sound frequencies generated by distant ships are mainly concentrated in the frequency band of tens to hundreds of Hz, for example, in the 50-500 Hz frequency range. The noise received by hydrophones deployed in the deep sea mainly originates from horizontal propagation, and the intensity of this noise is highly correlated with the intensity of shipping activity in the adjacent sea area.

[0058] According to the principle of sound wave reflection, under low-frequency sound wave conditions, the sound field radiated by each monopole sound source will interfere with the sound wave reflected back from the sea surface, thus forming a sound field pattern with dipole characteristics. Based on this principle, this application simplifies the sound source model of a long-range ship as a dipole array. Based on this, the formula for calculating the dipole noise level of a distant ship can be expressed as follows:

[0059] In the formula, For wave number, The depth of the original monopole sound source. This represents the number of ships per unit area. The spectral level of a monopole sound source can be expressed as:

[0060] In the formula, This refers to the frequency of ship noise.

[0061] Therefore, the total marine environmental noise is:

[0062] In the formula, The sum of marine environmental noise, , , These represent the wind-generated noise, the final rain noise, and the dipole noise level of a distant ship, respectively. The wind-generated noise includes high-frequency wind-generated noise. and low-frequency wind noise .

[0063] Step S1033: When underwater acoustic propagation encounters obstacles, the communication effect is greatly reduced. This application considers the distance of the obstacle from the signal source and the size of the obstacle to measure the magnitude of underwater acoustic signal loss. Assuming there is an obstacle on the line connecting the signal source and the underwater mission point, the closer the obstacle is to the signal source, the greater the propagation loss, and the relationship is non-linear; the closer the obstacle is to the sound source, the greater its impact on propagation loss. This application uses a logarithmic function to evaluate the propagation loss when underwater acoustic propagation encounters obstacles. The expression of the logarithmic function is as follows:

[0064] In the formula, This indicates the loss of propagation due to obstacles. and This represents the perpendicular distance from the two edge points of the obstacle to the line connecting the signal source and the underwater mission point. It represents the distance from the signal source to the nearest intersection point of the obstacle along the line connecting the signal source and the underwater mission point.

[0065] For example, the value retrieval rules are as follows: Figure 3 As shown. Figure 3 The relevant parameters in the obstacle propagation loss model are shown. When the underwater acoustic propagation path between the USV and the underwater mission point is blocked by an obstacle, the additional propagation loss can be described using the position and scale of the obstacle relative to the signal propagation line.

[0066] Step S1034: The After the USV emits an acoustic signal, it attenuates to the following value after propagation loss in the ocean environment:

[0067] In the formula, For the first The signal strength emitted by the USV For the first USV in the first The attenuated signal strength emitted from each underwater mission point The total noise intensity of the marine environment, and These represent the loss intensity caused by propagation distance and obstacles, respectively.

[0068] Since the attenuated signal strength obtained may be within any range, this application normalizes it for ease of subsequent calculations. Specifically, the selection rule for the normalization function is as follows: [The following text appears to be incomplete and requires further context:] The values ​​of and the normalized values ​​show a positive correlation when . near When the normalized value is close to 1, the function value increases with... The value gradually decreases to 0 as it decreases. Based on the above rules, the normalization function is designed as follows:

[0069] In the formula, This is the result after normalization. For the first USV in the first The attenuated signal strength emitted from each underwater mission point and These are all function coefficients. Among them, Used to control the rate of change of a function, the control effect is as follows: Figure 4 As shown, Used to change the position of a function in the direction of its movement on the water's surface, but not to change the rate of change of the function; the control effect is as follows: Figure 5 As shown. Figure 4 This shows the position control parameters. At the same time, different rate of change parameters The impact on the normalization result of the attenuated signal strength, as As the value increases from 0.02 to 0.1, the rate of change of the normalization function within the transition interval gradually increases, and the curve changes from gentle to steep, while its center position remains unchanged. Therefore, the normalization function can be improved by adjusting the parameter. Control the sensitivity of the normalization result to changes in the attenuation signal strength. Figure 5 It shows the change rate parameter At the same time, control parameters at different positions The impact on the normalization function. With... As the value changes, the normalized curve shifts along the horizontal axis, but its overall trend and steepness remain basically unchanged. Therefore, increasing... This can shift the curve toward a higher signal strength, thereby adjusting the signal strength range corresponding to a significant change in the normalization result.

[0070] Step S104: Convert the communication quality index into weight coefficients using the Sigmoid function, and construct an improved K-means loss function that includes the weight coefficients.

[0071] It should be noted that the K-means algorithm is essentially a clustering algorithm, the goal of which is to... The underwater mission points are divided into: There are three non-overlapping sets, and the centers of each set correspond to... The location of an underwater mission point determines which set it is closest to the center point of.

[0072] In this application, Euclidean distance is used to measure the distance between two points. The optimal partitioning strategy is selected by minimizing the loss function. The goal of the loss function is to minimize the distance from all underwater task points to the center point of their respective sets. Accordingly, the loss function is set as follows:

[0073] In the formula, The value of the loss function. For the number of USVs, It refers to the number of underwater mission sites. For the first USV and the The distance between the underwater mission points.

[0074] This application sets an improved K-means loss function, the expression of which is shown below:

[0075] In the formula, The value of the loss function. The loss function value after introducing the communication model, For the number of USVs, It refers to the number of underwater mission sites. The weighting coefficient has a range of values. . A larger value indicates better communication performance. To highlight the impact of communication performance on the allocation result, this application uses the Sigmoid function to construct... The construction result is shown below:

[0076] In the formula, This is the value of the signal strength after normalization. and These are the parameters that control the change of the control function.

[0077] Preferably, Take 20, Take 0.7. For example... Figure 6 As shown, Figure 6 Communication quality indicators are shown. With weighting coefficients The mapping relationship between them. After adopting this Sigmoid function, when the communication quality index is low, the weight coefficient is close to 0; when the communication quality index exceeds the preset change range, the weight coefficient increases rapidly and gradually approaches 1. Thus, the quality differences of different communication links can be transformed into clustering weights, so that USVs with better communication quality and underwater mission points are combined with higher priority in the clustering process.

[0078] Step S105: Iteratively cluster the underwater mission points based on the improved K-means loss function until the clustering results converge, and obtain the USV group to which each underwater mission point belongs.

[0079] Repeat the above process until the clustering results of the task points no longer change.

[0080] Step S106: Recalculate the position coordinates of the corresponding USV based on the coordinates of the underwater mission points within each USV group, and perform unmanned surface vessel relay communication based on the recalculated position coordinates of the USV.

[0081] Specifically, based on the above steps, this application recalculates the center point position of each task point in each category using the following formula:

[0082]

[0083] In the formula, , Assigned to respectively The x and y coordinates of the task point To be assigned Number of task points For the re-determined The coordinates of the point on the water surface, this point is... As a communication relay node.

[0084] The second embodiment of this application provides an unmanned surface vessel (USV) communication relay device to solve the same technical problem as the method embodiment. The device may include the following modules: The initialization module is used to obtain the three-dimensional coordinates of the underwater mission point, the number of USVs, and the mission area; and to initialize the position coordinates of each USV. The distance calculation module is used to calculate the distance between each USV and each underwater mission point; The signal strength calculation module is used to calculate the attenuated signal strength from each USV to each underwater mission point based on the underwater acoustic propagation model, which includes propagation loss caused by distance, marine environmental noise, and obstacle propagation loss; the attenuated signal strength is normalized to obtain communication quality indicators; The weight coefficient construction module is used to convert communication quality metrics into weight coefficients using the Sigmoid function and to construct an improved K-means loss function that includes the weight coefficients. The clustering module is used to iteratively cluster underwater mission points based on the improved K-means loss function until the clustering results converge, and obtain the USV group to which each underwater mission point belongs; The position update module is used to recalculate the position coordinates of the corresponding USV based on the coordinates of the underwater mission points within each USV group, and to perform unmanned surface vessel relay communication based on the recalculated position coordinates of the USV.

[0085] It is understood that the above-described device embodiments correspond to the method embodiments. Therefore, the device embodiments have all the beneficial effects of the method embodiments, and will not be repeated here.

[0086] The third embodiment of this application provides an electronic device, including a processor and a memory. The memory stores instructions that, when executed by the processor, implement the method provided in the preceding embodiments. This electronic device can be a hardware platform with data processing capabilities, such as a shore-based control center server, an edge computing gateway for a USV cluster, or a portable planning terminal.

[0087] The fourth embodiment of this application provides a computer-readable storage medium storing program instructions that, when executed by a processor, implement the method provided in the preceding embodiments. The storage medium may be a physical carrier such as a solid-state drive (SSD), flash memory card, read-only memory (ROM), or erasable programmable read-only memory (EEPROM).

[0088] The fifth embodiment of this application provides a multi-unmanned surface vessel (USV) communication relay planning system, including multiple USVs and a controller. The controller is used to execute the method provided in the previous embodiments. The system centrally processes underwater mission point coordinates and environmental parameters through the controller, runs the multi-USV communication relay planning method to generate an optimal relay deployment scheme, and issues position commands to each USV to perform maneuver adjustments, thereby constructing a highly reliable underwater communication coverage network.

[0089] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A communication relay method for unmanned surface vessels, characterized in that, include: Obtain the three-dimensional coordinates of the underwater mission location, the number of USVs, and the mission area. Calculate the distance between each USV and each underwater mission point; The attenuated signal strength from each USV to each underwater mission point is calculated based on an underwater acoustic propagation model, which includes propagation loss due to distance, marine environmental noise, and obstacle propagation loss. The attenuated signal strength is then normalized to obtain a communication quality index. The communication quality metrics are converted into weight coefficients using the Sigmoid function, and an improved K-means loss function containing the weight coefficients is constructed. Based on the improved K-means loss function, the underwater mission points are iteratively clustered until the clustering results converge, and the USV group to which each underwater mission point belongs is obtained. The position coordinates of the corresponding USV are recalculated based on the coordinates of the underwater mission points within each USV group, and relay communication is performed based on the recalculated position coordinates of the USV.

2. The unmanned surface vessel communication relay method as described in claim 1, characterized in that, The propagation loss caused by the distance is calculated using the following formula: In the formula, TL D For sound propagation loss, n For coefficients under different propagation conditions, L ij for USV i With mission points j The distance between them α Seawater sound absorption coefficient; Seawater sound absorption coefficient α The relationship between the frequency of the sound signal and the frequency is: In the formula, f The frequency of the sound signal.

3. The unmanned surface vessel communication relay method as described in claim 1, characterized in that, The marine environmental noise includes wind noise, rain noise and distant ship noise, and wind noise includes high-frequency wind noise and low-frequency wind noise. Among them, for high-frequency wind noise The following model is used for calculation: In the formula, v is the wind speed, with the unit being m / s. f w The frequency of wind noise is given by the unit . kHz , ΔT For temperature difference, δ ( Δt () represents the temperature difference function; The temperature difference is defined as follows: In the formula, T air For air temperature, T sea Seawater temperature; For low-frequency wind noise The following model is used for calculation: Rain noise Calculated using the following formula: In the formula, R For rainfall, λ (v) and μ (v) refers to wind speed v Piecewise functions; Dipole noise level of a distant ship Calculated using the following formula: In the formula, k For wave number, d The depth of the original monopole sound source. N This represents the number of ships per unit area. SL ship This indicates the monopole sound source spectral level of the ship. Represented as: In the formula, f s This refers to the frequency of ship noise.

4. The unmanned surface vessel communication relay method as described in claim 1, characterized in that, The obstacle propagation loss is calculated using the following logarithmic function: In the formula, TL Ob This indicates the loss of propagation due to obstacles. D x1 and D x2 This represents the perpendicular distance from the two edge points of the obstacle to the line connecting the signal source and the underwater mission point. D L It represents the distance from the signal source to the nearest intersection point of the obstacle along the line connecting the signal source and the underwater mission point.

5. The unmanned surface vessel communication relay method as described in claim 1, characterized in that, The function for normalizing the attenuated signal strength is: In the formula, ρ ij This is the result after normalization. SL ij For the first i USV in the first j The attenuated signal strength emitted from each underwater mission point p and q These are all coefficients of the normalization function; in, p Used to control the rate of change of the normalization function q Used to change the position of the normalization function in the horizontal direction.

6. The unmanned surface vessel communication relay method as described in claim 1, characterized in that, The communication quality metrics are converted into weighting coefficients using the Sigmoid function. The formula is: In the formula, ρ ij This is the value of the signal strength after normalization. m and n These are the parameters that control the change of the function; The improved K-means loss function takes the form of: in, Y The value of the loss function. I For the number of USVs, J It refers to the number of underwater mission sites. Y k The loss function value after introducing the communication model.

7. An unmanned surface vessel (USV) communication relay device, used to implement the USV communication relay method as described in any one of claims 1-6, characterized in that, include: The initialization module is used to obtain the three-dimensional coordinates of the underwater mission point, the number of USVs, and the mission area; and to initialize the position coordinates of each USV. The distance calculation module is used to calculate the distance between each USV and each underwater mission point; The signal strength calculation module is used to calculate the attenuated signal strength from each USV to each underwater mission point based on an underwater acoustic propagation model, which includes propagation loss caused by distance, marine environmental noise, and obstacle propagation loss; the attenuated signal strength is normalized to obtain communication quality indicators; The weight coefficient construction module is used to convert the communication quality index into weight coefficients through the Sigmoid function and construct an improved K-means loss function containing the weight coefficients. The clustering module is used to iteratively cluster underwater mission points based on the improved K-means loss function until the clustering results converge, thereby obtaining the USV group to which each underwater mission point belongs. The position update module is used to recalculate the position coordinates of the corresponding USV based on the coordinates of the underwater mission points within each USV group, and to perform unmanned surface vessel relay communication based on the recalculated position coordinates of the USV.

8. An electronic device comprising a processor and a memory, the memory storing instructions that, when executed by the processor, implement the unmanned surface vessel communication relay method as described in any one of claims 1-6.

9. A computer-readable storage medium having stored thereon program instructions that, when executed by a processor, implement the unmanned surface vessel communication relay method as described in any one of claims 1-6.

10. A multi-unmanned surface vessel (USV) communication relay planning system, characterized in that, It includes multiple USVs and a controller, the controller being used to perform the unmanned surface vessel communication relay method as described in any one of claims 1-6.

Images