A relay type unmanned ship air-sea integrated monitoring method, system, device and storage medium

Abstract

The application discloses a relay type unmanned ship air-sea integrated monitoring method, system, equipment and storage medium, relates to the technical field of unmanned ship cooperative communication and monitoring, and comprises the following steps: constructing a task priority calculation model, and generating grid data priority of each grid; based on the grid data priority, a dynamic buffer and transmission sequence generation mechanism is generated in combination with a dual-machine communication link state to output dual-machine state parameters; the dual-machine communication link state is combined, the relay path and bandwidth allocation are scheduled through link state sensing and spatial constraint, and when the mother ship receives each grid data, based on the priority and the dual-machine state parameters, a link quality weighted fusion and time synchronization correction mechanism is applied to dynamically adjust the dual-machine transmission parameters in combination with a micro-vibration and environmental disturbance compensation algorithm; the method disclosed by the application improves the cooperative efficiency, transmission reliability and information quality through dynamic scheduling, adaptive buffering and anti-disturbance fusion.

Description

Technical Field

[0001] This invention relates to the field of unmanned surface vessel (USV) collaborative communication and monitoring technology, specifically to a relay-type USV integrated air-sea surveillance method, system, equipment, and storage medium. Background Technology

[0002] With the increasing demand for marine monitoring, environmental assessment, and maritime operation management, research on unmanned surface vessels (USVs) and air-sea collaborative platforms is continuously advancing. USVs, through autonomous navigation, sensor integration, and networked communication, perform monitoring tasks in complex sea areas, achieving large-scale data acquisition and continuous operation. The development of multi-USV collaborative systems enables hovering UAVs and cruising USVs to form dynamic communication networks. Tasks are allocated according to attributes within a sea area grid, and data transmission and task execution order are managed in conjunction with real-time link status. Related research proposes gridded task allocation and priority scheduling strategies, optimizing task coverage through weight calculation and spatial location coupling, while also attempting to improve the stability of long-distance data transmission by utilizing high-altitude relays or multi-link redundancy. Regarding link design, traditional methods rely on fixed transmission paths or single-link transmission, which are insufficiently responsive to dynamic environmental changes. Especially when USV swarms perform large-scale monitoring tasks, link quality fluctuations, communication interference, and UAV speed variations affect the reliability and consistency of data transmission.

[0003] Existing technologies have limitations in buffer management, bandwidth allocation, data fusion, and time synchronization. Buffer capacity allocation lacks real-time correlation with link status; high-priority task data may not be effectively scheduled under unstable link conditions; when multiple unmanned surface vessels (USVs) participate in grid tasks simultaneously, data transmission time delays and link quality differences lead to misalignment or duplication of information sequences at the receiving end. Environmental disturbances, such as the effects of ocean waves and micro-vibrations of USVs, introduce uncertainty into communication link stability, and existing methods lack systematic handling of these dynamic factors. This makes it difficult to achieve continuous and coordinated operation of data transmission and scheduling mechanisms for multi-USV collaboration. The dynamic changes in link status, real-time adjustment of grid data priorities, and the complexity of multi-link data fusion constitute urgent technical problems to be solved in integrated maritime and air-sea monitoring. Summary of the Invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by the present invention is that the existing unmanned surface vessel air-sea integrated monitoring method has problems such as delayed link status response, disconnect between priority scheduling and link quality, low transmission efficiency of high priority data when the link is unstable, time misalignment in multi-link data fusion, and lack of effective compensation for micro-vibration and environmental disturbance.

[0006] To address the aforementioned technical problems, this invention provides the following technical solution: a relay-type unmanned surface vessel (USV) integrated air-sea surveillance method, comprising constructing a task priority calculation model to generate grid data priorities for each grid; based on the grid data priorities, and combined with a dual-machine communication link status generation dynamic buffer and transmission order generation mechanism, outputting dual-machine status parameters; the combination of dual-machine communication link status includes scheduling relay paths and bandwidth allocation through link status perception and spatial constraints; when the mother vessel receives data from each grid, based on the priority and dual-machine status parameters, applying a link quality weighted fusion and time synchronization correction mechanism, and combining a micro-vibration and environmental disturbance compensation algorithm to dynamically adjust the dual-machine transmission parameters.

[0007] As a preferred embodiment of the relay-type unmanned surface vessel (USV) integrated air-sea surveillance method described in this invention, the task priority calculation model includes: weighted integration of task characteristics for each grid; combining the spatial position and speed of hovering and cruising UAVs above and around the functional vessel; and generating grid data priority for each grid through an exponential decay function and a speed adjustment function; the task characteristics include task number, data type weight, and grid risk index; the task priority calculation formula is expressed as: , , in, Represents a grid At any moment Grid data priority, Represents a grid The data type weights control the contribution ratios of data type weights, risk index, and spatial location and velocity coupling, respectively. Represents a grid The risk index, Indicates time Grid Distance to the hovering drone Indicates the time of the cruise drone In the grid Nearby speed, This represents a spatial distance and velocity adjustment function. This represents the exponential decay coefficient, which is set according to the actual communication distance and transmission stability requirements. For short-range monitoring tasks, a value of 0.1-0.5 is used, while for long-range or high-interference communication environments, a value of 1.0-2.0 is used. This indicates the reference speed of the cruise drone.

[0008] As a preferred embodiment of the relay-type unmanned surface vessel (USV) integrated air-sea surveillance method described in this invention, the dual-machine communication link status includes the link status between the hovering USV and the mothership, the link status between the cruising USV and the hovering USV, and the link status between the cruising USV and the mothership. The overall link quality of the hovering and cruising USVs is evaluated, and dynamic judgment is made regarding link switching and dual-machine status parameters are generated. The dual-machine status parameters include the hovering USV's stationary position parameters, the cruising USV's cruising position parameters, the relative position parameters of the two machines, link switching parameters, and the current transmission path parameters. The overall link quality evaluation formula is expressed as: , in, Indicates at time The overall quality of the dual-machine link is used to determine whether a link switch is needed, and this information serves as input for generating dual-machine status parameters. Indicates the hovering drone at a certain time Received signal strength, Indicates the time of the cruise drone Received signal strength, This represents the weighting coefficient of hovering drones in the link quality calculation. This represents the weighting coefficient of the cruise drone in the link quality calculation. This represents the interference attenuation coefficient, which adjusts the intensity of the impact of total interference on link quality. In low-interference environments, it ranges from 0.1 to 0.3, while in high-interference environments, it ranges from 0.7 to 1.0. Indicates time Total interference in the dual-machine link.

[0009] As a preferred embodiment of the relay-type unmanned surface vessel (USV) integrated air-sea surveillance method described in this invention, the dynamic buffering and transmission order generation mechanism includes: sorting the transmitted data according to the grid data priority of each grid, configuring the buffer capacity of the corresponding grid in combination with the dual-machine communication link status, and generating the transmission order according to the order of priority for hovering UAV relay and supplementary direct transmission from cruising UAV; the buffer capacity includes: obtaining the buffer capacity of each grid based on the grid data priority, grid data generation rate and total dual-machine link quality of each grid, and correcting the buffer capacity under low link quality conditions using the Sigmoid function; when the link quality is good, the value of the Sigmoid function is close to 1, increasing the buffer capacity and allocating physical memory; when the link quality is poor, the value of the Sigmoid function is close to 0, reducing the size of the physical buffer and discarding low-priority data.

[0010] As a preferred embodiment of the relay-type unmanned surface vessel (USV) integrated air-sea surveillance method described in this invention, the data transmission time for each grid is calculated by combining grid data priority, the distance from the grid to the hovering aircraft, and available bandwidth, and the transmission time is adjusted using exponential decay and link quality correction functions; the grid data transmission time is expressed as: , in, This indicates the time when the grid data was sent at the current moment. Indicates available bandwidth. This represents the sum of the priorities of all normalized grid cells. The function represents a correction function that combines distance and total link quality. The spatial constraints include no-fly zones, maximum communication distance limits, and area coverage limits, with path selection priority dynamically adjusted. No-fly zones include areas with no-fly zones or obstacles that need to be avoided; any relay path crossing a no-fly zone will be considered an unsuitable path and requires recalculation or selection of an alternative path. The maximum communication distance limit includes a maximum communication distance between each pair of drones; if the distance between a hovering drone and a cruising drone exceeds the maximum communication distance, the current path is not allowed to be selected as a valid relay path. The area coverage limit also includes a maximum communication distance between each pair of drones; if the distance between a hovering drone and a cruising drone exceeds the maximum communication distance, the current path is not allowed to be selected as a valid relay path.

[0011] As a preferred embodiment of the relay-type unmanned surface vessel air-sea integrated surveillance method described in this invention, the link quality weighted fusion and time synchronization correction mechanism includes: obtaining the link quality weight of the transmission link corresponding to each grid data based on the dual-machine state parameters; performing weighted fusion on the data relayed by the hovering UAV and the data transmitted by the cruising UAV; and performing time synchronization correction according to the arrival time sequence of each transmission link.

[0012] As a preferred embodiment of the relay-type unmanned surface vessel (USV) integrated air-sea surveillance method described in this invention, the micro-vibration and environmental disturbance compensation algorithm includes: acquiring the micro-vibration information and environmental disturbance information of the hovering and cruising USVs under the current link state, generating corresponding transmission power compensation amounts, dynamically adjusting the dual-unit transmission power based on the quality of a single link, and performing time synchronization and weighted fusion of data from each grid based on data latency; the transmission power compensation amount is calculated using the following formula: , in, This indicates the actual transmit power of a hovering or cruising drone. Indicates the nominal transmission power. This represents the antenna gain correction factor. This represents the link quality correction factor. This represents the micro-vibration compensation coefficient of the drone body. This represents the wind and wave disturbance compensation coefficient. The link quality compensation coefficient is represented by: Time synchronization and weighted fusion are represented as: , in, This represents the final data after synchronization of each grid on the mothership side. Indicates the weight of grid data. Indicates the quality of a single link (normalized 0-1). Indicates the current grid Delayed data.

[0013] Another objective of this invention is to provide a relay-type unmanned surface vessel integrated air and sea surveillance system, which solves the problems of priority scheduling and link quality disconnection, time misalignment in multi-link data fusion, and lack of effective compensation for micro-vibrations and environmental disturbances in the prior art through the coordinated work of the task priority calculation module, dual-machine link and transmission scheduling module, and data fusion and transmission control module.

[0014] As a preferred embodiment of the relay-type unmanned surface vessel (USV) integrated air-sea surveillance system described in this invention, the system includes: a task priority calculation module, a dual-machine link and transmission scheduling module, and a data fusion and launch control module. The task priority calculation module generates a grid data priority for each grid based on the sea area grid and the task characteristics of each grid, combined with the spatial position and speed of the hovering and cruising UAVs above and around the functional vessel, through weighted integration, exponential decay, and speed adjustment functions. The dual-machine link and transmission scheduling module generates the buffer capacity, transmission order parameters, and dual-machine status parameters for each grid based on the grid data priority and the dual-machine communication link status, and schedules the data relay path and bandwidth allocation between the hovering and cruising UAVs through link status perception and spatial constraints. The data fusion and launch control module performs link quality weighted fusion and time synchronization correction based on the grid data priority and dual-machine status parameters when the mother vessel receives data from each grid, and dynamically adjusts the launch parameters of the hovering and cruising UAVs using micro-vibration and environmental disturbance compensation algorithms.

[0015] Another object of the present invention is to provide a relay-type unmanned surface vessel (USV) integrated air-sea surveillance method device, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the relay-type USV integrated air-sea surveillance method.

[0016] Another object of the present invention is to provide a storage medium for a relay-type unmanned surface vessel (USV) integrated air-sea surveillance method, wherein a computer program is stored thereon, and when the computer program is executed by a processor, the steps of the relay-type USV integrated air-sea surveillance method are implemented.

[0017] The beneficial effects of this invention are as follows: One scheme of the relay-type unmanned surface vessel (USV) integrated air-sea surveillance method provided by this invention uses a distance-velocity coupled priority calculation model to dynamically integrate the spatial position and velocity of hovering and cruising USVs into grid-based data priority evaluation. This solves the problem of priority scheduling being disconnected from motion state in traditional methods, ensuring the timeliness of critical data in dynamic environments. Through multi-link fusion evaluation and a Sigmoid buffer correction mechanism, the overall quality and buffer capacity of the hovering-mothership, cruising-hovering, and cruising-mothership links are nonlinearly adaptively matched. This allows high-priority data to obtain greater buffer space when links are unstable, solving the problem of data loss under poor link conditions with fixed buffers, and achieving data transmission... The system achieves a balance between high reliability and optimized resource utilization. Through a transmit power compensation algorithm for micro-vibration and environmental disturbances, it dynamically couples micro-vibration of the aircraft, environmental wind and wave disturbances, and link quality into power adjustment quantities, forming a link quality-driven closed-loop control. This solves the problem of insufficient effective compensation for signal fading caused by environmental disturbances, achieving continuous stability of the communication link in complex marine environments. Furthermore, through link quality weighted fusion and time synchronization correction, it performs delay compensation and quality weighted fusion on data relayed by hovering UAVs and directly transmitted by cruising UAVs. The transmission path is optimized according to a scheduling order prioritizing hovering relays and supplementing with cruising direct transmissions, solving the problems of time misalignment and inconsistent quality in multi-link data fusion, and simultaneously improving information consistency and decision reliability. Attached Figure Description

[0018] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is an overall flowchart of a relay-type unmanned surface vessel air-sea integrated surveillance method provided in Embodiment 1 of the present invention.

[0020] Figure 2 This is a flowchart of a relay-type unmanned surface vessel integrated air-sea surveillance method provided in Embodiment 1 of the present invention.

[0021] Figure 3 The graph shows the priority decay curve of grid data with distance for a relay-type unmanned surface vessel integrated air-sea surveillance method provided in Embodiment 1 of the present invention. Detailed Implementation

[0022] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0023] Example 1, referring to Figure 1-3 As an embodiment of the present invention, a relay-type unmanned surface vessel integrated air-sea surveillance method is provided, comprising: S1: Construct task priority calculation model 100 and generate grid data priority 101 for each grid.

[0024] It should be noted that the task priority calculation model 100 includes weighted integration of the task characteristics of each grid, combining the spatial position and speed of hovering UAVs and cruise UAVs above and around the functional boat, and generating grid data priority 101 for each grid through an exponential decay function and a speed adjustment function.

[0025] Task characteristics include task number, data type weight, and grid risk index.

[0026] Load the task attributes of each grid from the task management database, including task number, data type weight, and grid risk index. The data type weight is determined according to the preset sensor priority table, which is dynamically updated according to different task scenarios. For example, in the target recognition scenario, radar data has a higher weight than optical data, and in the environmental monitoring scenario, infrared data has a higher weight than visible light data.

[0027] The grid risk index is generated by fusing real-time data from multiple sources, including: wind and wave level data obtained from the meteorological service center, ship density distribution obtained from the Automatic Identification System (AIS), and risk heat maps from the historical accident statistics database. A weighted fusion algorithm is used to generate the real-time risk index for each grid, and the index is normalized according to the range of 0 to 1.

[0028] Both hovering and cruising drones report their status information in real time through onboard communication terminals. The hovering drone hovers in a fixed position above the mothership, and its onboard differential global positioning system outputs latitude, longitude, and altitude data at a frequency of 10 Hz. The mothership receives the data and converts it into local coordinates relative to the mothership. The cruising drone performs grid coverage flight according to a preset route. The onboard inertial navigation system and the global positioning system combine to output real-time position and velocity vectors. The mothership determines the grid area covered by the cruising drone based on its current coordinates and records the instantaneous velocity corresponding to the current area.

[0029] When a cruise drone covers multiple grids simultaneously, the speed is allocated based on the distance between the drone and the center point of each grid. The closest grid receives the complete speed value, while the remaining grids receive a speed attenuation value by weighting the values ​​according to the reciprocal of the distance.

[0030] The priority calculation model adopts a hierarchical calculation architecture. Priority calculation services are deployed on the mothership side. The calculation task is triggered in 1 Hz cycles. First, the data type weights, risk indices, distances from grids to hovering drones, and speeds of cruise drones near each grid are read from the state cache. The distances from grids to hovering drones are obtained by calculating the spherical distance between the grid center point and the current position of the hovering drone, and are corrected using the Earth ellipsoid model.

[0031] The priority calculation service calculates three components: the product of data type weight and first weight coefficient, the product of risk index and second weight coefficient, and the product of spatial distance and velocity adjustment function and third weight coefficient. The sum of the three components yields the priority value for each grid.

[0032] The formula for calculating task priority is as follows: , , in, Represents a grid At any moment Grid data priority, Represents a grid The data type weights control the contribution ratios of data type weights, risk index, and spatial location and velocity coupling, respectively. Represents a grid The risk index, Indicates time Grid Distance to the hovering drone Indicates the time of the cruise drone In the grid Nearby speed, This represents a spatial distance and velocity adjustment function. This represents the exponential decay coefficient, which is set according to the actual communication distance and transmission stability requirements. For short-range monitoring tasks, a value of 0.1-0.5 is used, while for long-range or high-interference communication environments, a value of 1.0-2.0 is used. This indicates the reference speed of the cruise drone.

[0033] like Figure 3 As shown, the risk index of the blue line is 0.2; the risk index of the red line is 0.4; the risk index of the green line is 0.6; the risk index of the purple line is 0.8; the risk index of the orange line is 1.0; and the gray dashed line represents the high priority threshold of 0.8.

[0034] Near distance (0~10km): All risk levels have high grid priority (≥0.85), especially high-risk grids, which have priority close to or above 1.0 at near distances; Medium to long distance (20~40km): Low-risk grids still maintain priority above 0.5, while high-risk grids quickly drop to below 0.3. The farther the distance, the more obvious the priority decay, and the higher the risk index, the more drastic the decay; Long distance (50km): Only low-risk grids retain a weak priority (0.1), and high-risk grids have dropped to 0, indicating that low-risk data at long distances can be delayed in transmission, and priority is given to protecting high-risk areas at near distances.

[0035] It should also be noted that the dynamic adjustment mechanism of the weighting coefficients includes analyzing the current mission instructions, meteorological environmental data, and input from the mothership operators to determine the current mission scenario type in real time. When the scenario is determined to be an emergency rescue scenario, the system increases the second weighting coefficient to above 0.6 while decreasing the first and third weighting coefficients. When the scenario is determined to be a regular cruise scenario, the system increases the third weighting coefficient to around 0.4, making the UAV's motion state have a more significant impact on priority. After the weighting coefficients are adjusted, the system automatically normalizes the priority of all grids.

[0036] In actual implementation, the spatial distance and speed adjustment function adopts a combination of table lookup and calculation. Under typical sea conditions, the exponential decay coefficient is obtained by conducting data communication tests between the hovering UAV and the mother ship at different distances, recording the link packet loss rate at each distance, and obtaining the exponential decay relationship between distance and packet loss rate through least squares fitting.

[0037] After calibration, the exponential decay coefficient is stored as a system configuration parameter. The reference speed in the speed adjustment item is set according to the flight performance curve of the cruise drone. The speed value with the largest coverage area under unit energy consumption is selected as the reference speed and obtained through drone flight testing.

[0038] After the priority calculation results are generated, they are stored in the priority queue and sorted from high to low according to the priority value. A priority smoothing mechanism is introduced to perform a moving average filter on the priority of each grid. The weighted average of the current calculated value and the historical value is used as the final output priority. The priority is dynamically adjusted according to the link status. When the link is stable, the weight of the historical value is increased; when the link fluctuates, the weight of the current value is increased.

[0039] The smoothed priority list is broadcast to the hovering and cruising UAVs via data link. The two UAVs perform subsequent buffer allocation and transmission scheduling based on the current list, while the mother ship persists the priority calculation results to the mission log database.

[0040] S2: Based on grid data priority 101, combined with the dynamic buffer and transmission order generation mechanism for dual-machine communication link status, output dual-machine status parameters.

[0041] It should be noted that the dual-machine communication link status includes the link status between the hovering UAV and the mothership, the link status between the cruise UAV and the hovering UAV, and the link status between the cruise UAV and the mothership. The overall link quality of the hovering UAV and the cruise UAV is evaluated, and it is dynamically determined whether to switch links and generate dual-machine status parameters.

[0042] The dual-machine status parameters include the hovering drone's dwell position parameters, the cruising drone's cruising position parameters, the relative position parameters of the two drones, the link switching parameters, and the current transmission path parameters.

[0043] The hovering and cruising drones periodically report the received signal strength indication values ​​through their onboard communication terminals. The mothership simultaneously measures the signal strength received from the two drones. For each link, the received signal strength is recorded, and the current total interference is estimated based on a sliding window of historical data.

[0044] The total interference includes measuring the background noise level during link idle periods, measuring the difference between the received signal strength and the noise level during communication periods, obtaining the instantaneous total interference by statistically summing the interference power of multiple time slots, and smoothing it using the exponential weighted moving average method.

[0045] The overall link quality assessment formula is expressed as follows: , in, Indicates at time The overall quality of the dual-machine link is used to determine whether a link switch is needed, and this information serves as input for generating dual-machine status parameters. Indicates the hovering drone at a certain time Received signal strength, Indicates the time of the cruise drone Received signal strength, This represents the weighting coefficient of hovering drones in the link quality calculation. This represents the weighting coefficient of the cruise drone in the link quality calculation. This represents the interference attenuation coefficient, which adjusts the intensity of the impact of total interference on link quality. In low-interference environments, it ranges from 0.1 to 0.3, while in high-interference environments, it ranges from 0.7 to 1.0. Indicates time Total interference in the dual-machine link.

[0046] Simultaneously, a link switching trigger signal is output. When the overall quality of the link is lower than a preset first threshold, the current communication link is determined to be unstable, and the link switching mechanism is triggered.

[0047] The link switching mechanism includes: if the link quality between the hovering UAV and the mothership is better than that between the cruise UAV and the mothership, the data of the cruise UAV will be transmitted via the hovering UAV relay first; if the direct transmission link quality between the cruise UAV and the mothership is better than that of the relay link, the direct transmission mode will be switched.

[0048] During the handover, the system records the link handover parameters, including the handover time, the link quality before the handover, and the link quality after the handover.

[0049] The dynamic buffering and transmission order generation mechanism includes sorting the transmission data according to the grid data priority 101 of each grid, configuring the buffer capacity of the corresponding grid in combination with the dual-machine communication link status, and generating the transmission order according to the order of priority for hovering UAV relay and supplementary direct transmission from cruising UAV.

[0050] The buffer capacity includes obtaining the buffer capacity of each grid based on the grid data priority 101, the grid data generation rate, and the total link quality between the two machines. The buffer capacity is then corrected using the Sigmoid function under low link quality conditions. When the link quality is good, the value of the Sigmoid function is close to 1, increasing the buffer capacity and physical memory allocation. When the link quality is poor, the value of the Sigmoid function is close to 0, reducing the size of the physical buffer and discarding low-priority data.

[0051] Buffer capacity is expressed as: , , in, Indicates time Total buffer capacity, This represents the grid weight coefficient, used to allocate the proportion of different grids in the buffer. Indicates the grid data generation rate. The Sigmoid function depends on the overall link quality. Dynamically adjust buffer capacity. This represents a coefficient that adjusts the steepness of the Sigmoid curve. This represents the link quality threshold, generated based on historical status data.

[0052] At the start of each transmission cycle, the transmission order generation mechanism first checks the link status between the hovering UAV and the mothership. If the current link is available and the link quality meets the transmission requirements, the data in the queue to be transmitted will be relayed to the mothership via the hovering UAV. When the hovering UAV relay link is unavailable or the link quality is lower than the second threshold, the scheduler switches to the cruise UAV direct transmission supplement mode and uses the direct transmission link between the cruise UAV and the mothership to transmit data.

[0053] In both modes, data packets are sent sequentially according to the priority-sorted queue.

[0054] The relay path and bandwidth allocation are scheduled through link state awareness and spatial constraints, including calculating the data transmission time 201 for each grid by combining grid data priority 101, the distance from the grid to the hovering machine and the available bandwidth, and adjusting the transmission time through exponential decay and link quality correction functions.

[0055] The grid data transmission time is 201, which is represented as: , in, This indicates the time when the grid data was sent at the current moment. Indicates available bandwidth. This represents the sum of the priorities of all normalized grid cells. This represents the correction function, which combines distance and total link quality;

[0056] Spatial constraints include no-fly zones, maximum communication distance limits, and area coverage limits, which are addressed by dynamically adjusting path selection priorities.

[0057] No-fly zones include areas with no-fly zones or obstacles that need to be avoided. Any relay path that crosses a no-fly zone will be considered an unsuitable path and will need to be recalculated or an alternative path will need to be selected.

[0058] The maximum communication distance limit includes a maximum communication distance between each pair of drones. If the distance between a hovering drone and a cruising drone exceeds the maximum communication distance, the current path is not allowed to be selected as a valid relay path.

[0059] Area coverage limitations include a maximum communication distance between each pair of drones; if the distance between a hovering drone and a cruising drone exceeds the maximum communication distance, the current path is not allowed to be selected as a valid relay path.

[0060] The corrected function formula is expressed as: , in, The function representing the correction coefficients for grid data transmission. Represents the distance attenuation term. This indicates a link quality correction item.

[0061] S3: When the mothership receives data from each grid, it dynamically adjusts the transmission parameters of the two machines based on priority and dual-machine status parameters, using a link quality weighted fusion and time synchronization correction mechanism, combined with micro-vibration and environmental disturbance compensation algorithms.

[0062] It should be noted that the link quality weighted fusion and time synchronization correction mechanism includes obtaining the link quality weight of the transmission link corresponding to each grid data based on the dual-machine state parameters, performing weighted fusion on the data relayed by the hovering UAV and the data transmitted by the cruise UAV, and performing time synchronization correction according to the arrival time sequence of each transmission link.

[0063] Data packets from the hovering UAV relay link and the cruise UAV direct transmission link are received in parallel using a multi-threaded approach. Each data packet is appended with a GPS-synchronized timestamp and link identifier by the sending end. Upon receiving the packet, the mothership parses the header information, extracts the grid identifier, sending timestamp, transmission path identifier, and link quality indicator, and stores them in the corresponding receiving queue according to grid classification.

[0064] Link quality weighted fusion is performed periodically on a grid-by-grid basis. For each grid, the system extracts the set of data packets in the receive queue that have not yet participated in the fusion, and calculates the quality weight of each link at the current moment based on the link quality indication carried by the data packets and the average link quality within the historical sliding window. A time synchronization correction mechanism aligns the data packets before fusion. The system maintains a dynamic delay estimate for each link, obtained by statistically analyzing the difference between the sending and receiving timestamps, and corrects the data packets to their original time domain based on transmission path differences.

[0065] The micro-vibration and environmental disturbance compensation algorithm includes acquiring micro-vibration information of hovering and cruising UAVs and environmental disturbance information in the current link state, generating a corresponding transmit power compensation amount of 300, dynamically adjusting the transmit power of the two UAVs in combination with the quality of a single link, and performing time synchronization and weighted fusion of data in each grid based on data latency.

[0066] The formula for calculating the transmit power compensation is as follows: , in, This indicates the actual transmit power of a hovering or cruising drone. Indicates the nominal transmission power. This represents the antenna gain correction factor. This represents the link quality correction factor. This represents the micro-vibration compensation coefficient of the drone body. This represents the wind and wave disturbance compensation coefficient. This represents the link quality compensation coefficient;

[0067] Time synchronization and weighted fusion are represented as: , in, This represents the final data after synchronization of each grid on the mothership side. Indicates the weight of grid data. Indicates the quality of a single link (normalized 0-1). Indicates the current grid Delayed data.

[0068] It should also be noted that while the dual-aircraft transmission power is dynamically adjusted, the mothership continuously receives and processes data packets. The fused data is stored in a time-series database according to grid identifiers and timestamps, forming a complete marine monitoring dataset. This dataset also serves as a historical basis for subsequent mission planning, priority model parameter optimization, and link scheduling strategy adjustments, forming a complete closed loop from data acquisition, transmission, fusion to decision feedback.

[0069] Example 2, an embodiment of the present invention, provides a relay-type unmanned surface vessel integrated air and sea surveillance system, including a task priority calculation module, a dual-machine link and transmission scheduling module, and a data fusion and transmission control module.

[0070] The task priority calculation module is used to generate grid data priority 101 for each grid based on the sea area grid and the task characteristics of each grid, combined with the spatial position and speed of hovering UAVs and cruise UAVs above and around the functional vessel, through weighted integration, exponential decay and speed adjustment functions.

[0071] The dual-machine link and transmission scheduling module is used to generate the buffer capacity, transmission order parameters and dual-machine status parameters of each grid based on the grid data priority 101 and the dual-machine communication link status of each grid. It also schedules the data relay path and bandwidth allocation between hovering UAVs and cruising UAVs through link status perception and spatial constraints.

[0072] The data fusion and launch control module is used to perform link quality weighted fusion and time synchronization correction based on the grid data priority 101 and dual-machine status parameters when the mother ship receives data from each grid. It also dynamically adjusts the launch parameters of hovering UAV and cruise UAV by combining micro-vibration and environmental disturbance compensation algorithms.

[0073] This embodiment also provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements a relay-type unmanned surface vessel integrated air and sea surveillance method as proposed in the above embodiment.

[0074] This embodiment also provides a computer-readable storage medium storing a computer program thereon. When the computer program is executed by a processor, it implements a relay-type unmanned surface vessel air-sea integrated surveillance method as proposed in the above embodiment.

[0075] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0076] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0077] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0078] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0079] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A relay-type unmanned surface vessel (USV) integrated air-sea surveillance method, characterized in that, include: Construct a task priority calculation model (100) and generate grid data priority for each grid (101). Based on grid data priority (101), and combined with the dynamic buffer and transmission order generation mechanism for dual-machine communication link status generation, dual-machine status parameters are output. The combined dual-machine communication link status includes scheduling relay paths and bandwidth allocation through link status awareness and spatial constraints. When the mothership receives data from each grid, it dynamically adjusts the transmission parameters of the two machines based on priority and dual-machine status parameters, using a link quality weighted fusion and time synchronization correction mechanism, combined with micro-vibration and environmental disturbance compensation algorithms.

2. The relay-type unmanned surface vessel integrated air-sea surveillance method as described in claim 1, characterized in that: The task priority calculation model (100) includes, The task characteristics of each grid are weighted and integrated. The grid data priority of each grid is generated by combining the spatial position and speed of hovering UAV and cruise UAV above and around the functional boat through exponential decay function and speed adjustment function (101). Task characteristics include task number, data type weight, and grid risk index; The task priority calculation formula is expressed as follows: ， ， in, Represents a grid At any moment Grid data priority, Represents a grid The data type weights control the contribution ratios of data type weights, risk index, and spatial location and velocity coupling, respectively. Represents a grid The risk index, Indicates time Grid Distance to the hovering drone Indicates the time of the cruise drone In the grid Nearby speed, This represents a spatial distance and velocity adjustment function. This represents the exponential decay coefficient, which is set according to the actual communication distance and transmission stability requirements. For short-range monitoring tasks, a value of 0.1-0.5 is used, while for long-range or high-interference communication environments, a value of 1.0-2.0 is used. This indicates the reference speed of the cruise drone.

3. The relay-type unmanned surface vessel integrated air-sea surveillance method as described in claim 1 or 2, characterized in that: The status of the dual-machine communication link includes: The link status between hovering UAV and mothership, the link status between cruise UAV and hovering UAV, and the link status between cruise UAV and mothership are evaluated to assess the overall link quality of hovering and cruise UAVs, dynamically determine whether to switch links, and generate dual-aircraft status parameters. The dual-machine status parameters include the hovering drone's dwell position parameters, the cruising drone's cruising position parameters, the relative position parameters of the two drones, the link switching parameters, and the current transmission path parameters. The overall link quality assessment formula (200) is expressed as: ， in, Indicates at time The overall quality of the dual-machine link is used to determine whether a link switch is needed, and this information serves as input for generating dual-machine status parameters. Indicates the hovering drone at a certain time Received signal strength, Indicates the time of the cruise drone Received signal strength, This represents the weighting coefficient of hovering drones in the link quality calculation. This represents the weighting coefficient of the cruise drone in the link quality calculation. This represents the interference attenuation coefficient, which adjusts the intensity of the impact of total interference on link quality. In low-interference environments, it ranges from 0.1 to 0.3, while in high-interference environments, it ranges from 0.7 to 1.

0. Indicates time Total interference in the dual-machine link.

4. The relay-type unmanned surface vessel integrated air-sea surveillance method as described in claim 3, characterized in that: The dynamic buffering and transmission order generation mechanism includes: The transmitted data is sorted according to the grid data priority (101) of each grid, and the buffer capacity of the corresponding grid is configured in combination with the dual-machine communication link status. The transmission order is generated in the order of priority for hovering UAV relay and supplementary direct transmission from cruising UAV. The buffer capacity includes obtaining the buffer capacity of each grid based on the grid data priority (101), grid data generation rate and total link quality of the two machines, and correcting the buffer capacity under low link quality conditions by using the Sigmoid function. When the link quality is good, the value of the Sigmoid function is close to 1, which increases buffer capacity and physical memory allocation; When the link quality is poor, the value of the Sigmoid function is close to 0, reducing the size of the physical buffer and discarding low-priority data.

5. The relay-type unmanned surface vessel integrated air-sea surveillance method as described in any one of claims 1, 2, and 4, characterized in that: The method of scheduling relay paths and bandwidth allocation through link state awareness and spatial constraints includes... The data transmission time for each grid is calculated (201) by combining the grid data priority (101), the distance from the grid to the hovering machine, and the available bandwidth. The transmission time is then adjusted using exponential decay and link quality correction functions. The grid data transmission time (201) is expressed as: ， in, This indicates the time when the grid data was sent at the current moment. Indicates available bandwidth. This represents the sum of the priorities of all normalized grid cells. This represents the correction function, which combines distance and total link quality; The spatial constraints include no-fly zones, maximum communication distance limits, and area coverage limits, and the priority of path selection is dynamically adjusted. The no-fly zone includes areas with no-fly zones or obstacles that need to be avoided. Any relay path that crosses a no-fly zone will be considered an unsuitable path and will need to be recalculated or an alternative path will need to be selected. The maximum communication distance limit includes a maximum communication distance between each pair of drones. If the distance between a hovering drone and a cruising drone exceeds the maximum communication distance, the current path is not allowed to be selected as a valid relay path. The area coverage restrictions include a maximum communication distance between each pair of drones. If the distance between a hovering drone and a cruising drone exceeds the maximum communication distance, the current path is not allowed to be selected as a valid relay path.

6. The relay-type unmanned surface vessel integrated air-sea surveillance method as described in claim 5, characterized in that: The link quality weighted fusion and time synchronization correction mechanism includes, Based on the dual-machine state parameters, the link quality weight of the transmission link corresponding to each grid data is obtained. The data relayed by hovering UAV and the data transmitted by cruising UAV are weighted and fused, and time synchronization correction is performed according to the arrival time sequence of each transmission link.

7. The relay-type unmanned surface vessel integrated air-sea surveillance method as described in any one of claims 1, 2, 4, and 6, characterized in that: The micro-vibration and environmental disturbance compensation algorithm includes, Acquire micro-vibration information and environmental disturbance information of hovering and cruising UAVs under the current link state, generate corresponding transmit power compensation amount (300), dynamically adjust the transmit power of the two UAVs in combination with the quality of a single link, and perform time synchronization and weighted fusion of data for each grid based on data latency; The formula for calculating the transmit power compensation (300) is as follows: ， in, This indicates the actual transmit power of a hovering or cruising drone. Indicates the nominal transmission power. This represents the antenna gain correction factor. This represents the link quality correction factor. This represents the micro-vibration compensation coefficient of the drone body. This represents the wind and wave disturbance compensation coefficient. This represents the link quality compensation coefficient; Time synchronization and weighted fusion are represented as: ， in, This represents the final data after synchronization of each grid on the mothership side. Indicates the weight of grid data. Indicates the quality of a single link (normalized 0-1). Indicates the current grid Delayed data.

8. A relay-type unmanned surface vessel (USV) integrated air-sea surveillance system, employing the relay-type USV integrated air-sea surveillance method as described in any one of claims 1 to 7, characterized in that: This includes a task priority calculation module, a dual-machine link and transmission scheduling module, and a data fusion and transmission control module; The task priority calculation module is used to generate grid data priority (101) for each grid based on the sea area grid and the task characteristics of each grid, combined with the spatial position and speed of hovering UAVs and cruise UAVs above and around the functional boat, through weighted integration, exponential decay and speed adjustment functions. The dual-machine link and transmission scheduling module is used to generate the buffer capacity, transmission order parameters and dual-machine status parameters of each grid based on the grid data priority (101) and dual-machine communication link status of each grid, and to schedule the data relay path and bandwidth allocation between hovering UAV and cruise UAV through link status perception and spatial constraints. The data fusion and launch control module is used to perform link quality weighted fusion and time synchronization correction based on the grid data priority (101) and dual-machine status parameters when the mother ship receives data from each grid, and to dynamically adjust the launch parameters of the hovering UAV and the cruise UAV in combination with micro-vibration and environmental disturbance compensation algorithms.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the relay-type unmanned surface vessel integrated air and sea surveillance method as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the relay-type unmanned surface vessel integrated air and sea surveillance method as described in any one of claims 1 to 7.

Images