Cooperative dynamic energy charging method and system for open-sea unmanned surface vehicle based on grid management

Abstract

The invention discloses an open sea unmanned ship cooperative dynamic energy charging method and system based on grid management, and relates to the technical field of unmanned ship dynamic energy charging management, and the method comprises the steps: carrying out the grid division of a target sea area, distributing an unmanned ship for each grid, and carrying out the resident monitoring; current environment information and the electric quantity of the unmanned ship are collected in real time, and when the electric quantity of the unmanned ship meets an energy charging condition, a collaborative energy charging strategy is started; according to the method, a sea area division strategy based on grid management is constructed, so that distributed resident monitoring and ordered scheduling of space tasks of the unmanned surface vehicle are realized; a cooperative energy charging mechanism triggered by environment information and an electric quantity state is combined, autonomous floating charging or butt joint with a maintenance boat for energy complementation is dynamically selected, the energy management flexibility in an open sea complex environment is improved, the closed-loop optimization capability of system operation is constructed, and the energy management efficiency is improved. According to the overall technical scheme, the task continuity, the energy utilization efficiency and the autonomous intelligence level of the offshore multi-unmanned ship system are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of dynamic energy charging management for unmanned boats, and specifically to a collaborative dynamic energy charging method and system for deep-sea unmanned boats based on grid management. Background Technique

[0002] With the increasing demand for deep-sea operations such as ocean resource development, maritime security, environmental monitoring, and climate observation, the technology of intelligent maritime equipment for wide-area, complex, and long-duration mission scenarios has developed rapidly. Among them, as a surface intelligent platform with autonomous navigation, mission execution, and information perception capabilities, unmanned boats are gradually replacing traditional manned boats to perform various tasks in deep-sea waters due to their high efficiency, flexibility, and scalability, such as ocean exploration, communication relay, border patrol, hydrometeorological collection, and emergency response. However, limited by environmental constraints such as the vast sea area, difficult communication coverage, and difficult energy supply, the traditional single-boat control strategy based on a predetermined path and static energy management method can no longer meet the practical needs of multi-boat collaboration and long-term mission execution. Therefore, the dynamic energy charging collaboration strategy combining grid-based sea area division, multi-unmanned boat distributed deployment, and environment perception-driven has become a frontier direction in the research of deep-sea unmanned systems. In related research and engineering applications, some solutions attempt to construct a remote control platform to implement periodic scheduling for unmanned boats and supplement on-board energy with clean energy such as solar energy. However, most of these methods focus on the task scheduling algorithm itself or the optimization of the energy collection hardware efficiency, and fail to effectively integrate the overall mechanism of sea area space management, dynamic energy consumption status feedback, and multi-platform collaborative response.

[0003] From the perspective of system architecture evolution, most current deployment strategies for deep-sea unmanned boats lack a reasonable modeling of the sea area spatial structure, resulting in a low matching degree between the boat positions and the task density, and problems such as regional blind spots or redundant deployments. At the same time, due to the great influence of environmental factors (such as wind and waves, flow velocity, light intensity) on the charging conditions, traditional static charging threshold strategies often cause waste of charging opportunities or risks of abnormal energy consumption. Furthermore, most current systems ignore the performance analysis and historical backtracking mechanism of the charging process, and are unable to evaluate the deterioration of the boat body performance or the deviation of the charging behavior based on actual operation data, resulting in a lack of adaptive optimization ability of the system. Therefore, the existing technologies have obvious deficiencies in the following aspects: First, the design of the sea area monitoring spatial structure is extensive, and a reusable and extensible regional unit cannot be constructed, restricting the ability of multi-boat task resource collaborative scheduling; Second, the energy supply strategy is rigid, and the charging decision cannot be dynamically adjusted by combining real-time environmental information and the boat body state. Especially in harsh sea conditions, the system cannot reliably determine whether it is possible to surface for charging or whether it is necessary to cooperate with a docking functional boat for energy replenishment; Third, there is a lack of data closed-loop analysis ability during the system operation process, and it is impossible to achieve performance tracking and abnormal warning based on historical data. Based on the above problems, there is an urgent need for a new design method for deep-sea unmanned boat systems, which can integrate a spatial grid structure, a collaborative charging decision mechanism based on environmental perception, and an analysis and feedback mechanism for the whole-process behavior data, so as to achieve intelligent, autonomous, and refined management of deep-sea multi-unmanned boat platforms and improve the continuity and reliability of deep-sea operation tasks. Summary of the Invention

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

[0005] Therefore, the technical problems solved by the present invention are: the existing methods for energy management and regional scheduling control of unmanned boats have problems of extensive space division, rigid charging strategies, and lack of data feedback, and how to achieve intelligent collaborative charging and autonomous energy replenishment path scheduling of deep-sea multi-boats in a dynamic environment.

[0006] To solve the above technical problems, the present invention provides the following technical solution, a collaborative dynamic charging method for deep-sea unmanned boats based on grid management, including: dividing the target sea area into grids, allocating unmanned boats to each grid for permanent monitoring; collecting the current environmental information and the battery power of the unmanned boats in real time, and starting the collaborative charging strategy when the battery power of the unmanned boats meets the charging conditions; analyzing and feedback on the charging process.

[0007] As a preferred embodiment of the method for collaborative dynamic charging of remote-controlled unmanned boats based on grid management according to the present invention, the steps are as follows: dividing the target sea area into grids, including obtaining the boundary coordinate data of the target sea area, setting the monitoring radius of each unmanned boat according to the task type and monitoring coverage requirements, calculating the total number of grids according to the monitoring radius and the total area of the target sea area, and dividing the target sea area into equivalent regional grids according to longitude and latitude.

[0008] The unmanned boats include signal boats, maintenance boats, seabed exploration boats, and airspace extension boats.

[0009] As a preferred embodiment of the method for collaborative dynamic charging of remote-controlled unmanned boats based on grid management according to the present invention, the steps are as follows: allocating unmanned boats to each grid for permanent monitoring, including selecting different types of unmanned boats according to the grid task type and allocating them to the grid as permanent monitoring units.

[0010] As a preferred embodiment of the method for collaborative dynamic charging of remote-controlled unmanned boats based on grid management according to the present invention, the steps are as follows: collecting the current environmental information and the battery power of the unmanned boat in real time, including collecting wind speed data and wave data through the meteorological sensors on the unmanned boat, obtaining the current battery power, voltage, and current, and uploading the collected information to the remote management platform.

[0011] As a preferred embodiment of the method for collaborative dynamic charging of remote-controlled unmanned boats based on grid management according to the present invention, the collaborative charging strategy is as follows: when the battery power of the unmanned boat is lower than the preset threshold, it is judged whether the sea area where the unmanned boat is currently located meets the safe surfacing condition according to the environmental information. If the wind speed data and wave data are within the preset threshold range, the unmanned boat is controlled to surface and deploy the solar panels for charging. If the wind speed data and wave data are outside the preset threshold range, the unmanned boat is charged according to the boat selection algorithm.

[0012] As a preferred embodiment of the method for collaborative dynamic charging of remote-controlled unmanned boats based on grid management according to the present invention, the boat selection algorithm is as follows: retrieving the maintenance boats that can provide energy supply near the current sea area, and based on the relative position relationship between the unmanned boat and the maintenance boats, planning the shortest path and the optimal docking time, which is expressed as:

[0013]

[0014] where m * is the maintenance boat that is currently most suitable to be selected for energy replenishment. is the function to obtain the optimal solution of the comprehensive energy replenishment cost. m i ∈M is the set of candidate maintenance boats, α is the distance weight factor, β is the waiting time weight factor, d(u, m i ) is the distance between the unmanned boat u and the i-th maintenance boat mi The sea navigation distance, t wait (m i ) is the current queuing waiting time of the i-th maintenance boat.

[0015] As a preferred solution of the method for collaborative dynamic charging of remote-controlled unmanned boats based on grid management according to the present invention, wherein: analyzing and feeding back the charging process includes recording the start and end times of each charging, generating corresponding charging event numbers, during the charging process, collecting voltage, current, and battery temperature in real time, synchronously storing the collected data with timestamps, calculating the charging efficiency per unit time according to the start and end times of charging and the change in battery power, performing trend comparison and analysis based on the historical charging data of the unmanned boat, evaluating whether there is an abnormality in the current charging performance, generating a charging feedback label based on the analysis result, and uploading the feedback information to the remote management platform.

[0016] Another object of the present invention is to provide a system for collaborative dynamic charging of remote-controlled unmanned boats based on grid management, which can solve the problems of high response delay and low energy utilization rate in the current static charging control through an intelligent collaborative energy replenishment mechanism that combines environmental perception and boat selection algorithms.

[0017] As a preferred solution of the system for collaborative dynamic charging of remote-controlled unmanned boats based on grid management according to the present invention, wherein: it includes a sea area grid division module, a collaborative charging control module, and a charging feedback analysis module; the sea area grid division module includes a grid structure generation module and a grid boat allocation module. The grid structure generation module is used to obtain the boundary coordinate data of the target sea area, calculate the total number of grids according to the task coverage requirements and the monitoring radius of the unmanned boat, and divide the target sea area into equivalent regional grids according to longitude and latitude. The grid boat allocation module is used to allocate permanent unmanned boats to each grid and match unmanned boats with different functions according to the grid task type; the collaborative charging control module includes an environmental information collection module and a charging method judgment module. The environmental information collection module is used to collect wind speed and wave height in real time through a meteorological sensor and obtain the current battery power, voltage, and current of the unmanned boat. The charging method judgment module is used to judge whether it is allowed for the unmanned boat to surface for autonomous solar charging based on whether the wind speed and wave height are within the preset safety threshold. When the surfacing condition is not met, the boat selection algorithm is called to retrieve the maintenance boat resources, and the shortest charging path and the optimal docking time are planned based on the relative position relationship; the charging feedback analysis module includes a charging data collection module and a charging efficiency evaluation and feedback module. The charging data collection module is used to record the start and end times of each charging, collect real-time voltage, current, and battery temperature and set timestamps. The charging efficiency evaluation and feedback module is used to calculate the charging efficiency per unit time according to the change in battery power and time, call the historical charging data for comparison and analysis, judge whether there is an abnormality or performance decay in the current charging, generate a charging feedback label, and upload it to the remote scheduling management platform.

[0018] A computer device includes a memory and a processor. The memory stores a computer program. It is characterized in that when the processor executes the computer program, the steps of any one of the methods of the collaborative dynamic energy charging method for unmanned boats in the open sea based on grid management are implemented.

[0019] A computer-readable storage medium stores a computer program. It is characterized in that when the computer program is executed by a processor, the steps of any one of the methods of the collaborative dynamic energy charging method for unmanned boats in the open sea based on grid management are implemented.

[0020] Advantages of the present invention: By constructing a sea area division strategy based on grid management, the present invention realizes distributed permanent monitoring of unmanned boats and orderly scheduling of space tasks; combined with a collaborative energy charging mechanism triggered by environmental information and power status, it dynamically selects to autonomously surface for charging or dock with a maintenance boat for energy replenishment, effectively improving the flexibility of energy management in the complex open sea environment; and through the whole-process data collection and performance feedback analysis of the energy charging process, a closed-loop optimization ability for system operation is constructed. The overall technical solution realizes a comprehensive improvement in the task continuity, energy utilization efficiency, and autonomous intelligence level of the multi-unmanned boat system in the open sea. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0022] Figure 1 It is a schematic flow chart of the collaborative dynamic energy charging method for unmanned boats in the open sea based on grid management provided by the first embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0023] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following will make a detailed description of the specific embodiments of the present invention with reference to the drawings of the specification. Obviously, the described embodiments are some embodiments of the present invention, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0024] Example 1, referring to Figure 1 , which is the first embodiment of the present invention. This embodiment provides a collaborative dynamic energy charging method for unmanned boats in the open sea based on grid management, including:

[0025] S1: Divide the target sea area into a grid, and allocate unmanned boats to each grid for permanent monitoring.

[0026] It should be noted that dividing the target sea area into a grid includes obtaining the boundary coordinate data of the target sea area, setting the monitoring radius of each unmanned boat according to the task type and monitoring coverage requirements, calculating the total number of grids based on the monitoring radius and the total area of the target sea area, and dividing the target sea area into equivalent regional grids according to longitude and latitude.

[0027] The unmanned boats include signal boats, maintenance boats, seabed exploration boats, and airspace extension boats.

[0028] It should also be noted that obtaining the boundary coordinate data of the target sea area, which can be obtained from satellite remote sensing images, electronic nautical charts, or maritime GIS systems. According to the task demand type (such as water quality monitoring, communication relay, deep sea exploration, cruise protection, etc.) and the monitoring coverage accuracy requirements, set the monitoring radius of each unmanned boat. The monitoring radius is the maximum effective sensing and communication coverage range of the unmanned boat under specific sea conditions. The total number of grids required is calculated as follows:

[0029]

[0030] Where N is the number of grids, S is the total area of the sea area, R is the monitoring radius, and η is the grid overlap coefficient (used to improve the coverage rate of the edge area). Indicates rounding up. Divide the target sea area into equivalent regional grids according to the longitude and latitude coordinate system. It is preferably divided into hexagonal or square cells to reduce boundary overlap and blind areas. Each grid is an independent scheduling and monitoring unit, which can be independently identified by the system, assigned tasks, and dynamically adjusted for configuration.

[0031] To achieve multi-task adaptation and efficient cooperation, the unmanned boats include but are not limited to the following types: signal boats, which are used to establish a regional communication relay network to ensure boundary communication and platform interconnection; maintenance boats, which are used to provide energy supply and fault repair support near the shore or maintenance nodes; seabed exploration boats, which have the ability to dive and scan the seabed terrain, and are suitable for marine resource exploration and seabed monitoring scenarios; airspace extension boats, which have the ability to carry large vertical takeoff and landing drones or long-endurance storm-resistant drones, and are used to perform high-altitude data relay, air-sea coordinated operations, and cross-grid rapid response tasks.

[0032] Furthermore, allocating unmanned boats to each grid for permanent monitoring includes selecting different types of unmanned boats according to the grid task type and allocating them to the grid as permanent monitoring units.

[0033] It should also be noted that according to indicators such as the task type, geographical environment characteristics, communication coverage requirements, and security level corresponding to each grid, an appropriate type of unmanned boat is selected as the permanent monitoring unit. The grid task types may include, but are not limited to: boundary monitoring type, communication relay type, deep-sea exploration type, resource sampling type, dynamic warning type, etc. The task requirements corresponding to different types of grids have significant differences, so the allocated unmanned boat types also need to have corresponding capability structures.

[0034] Specifically, boundary monitoring type grids are usually located at the periphery or strategic boundary positions of the task sea area and need to have high endurance and stable video or radar transmission capabilities. For this type of grid, signal boats or maintenance boats can be preferably deployed, which are equipped with high-gain communication devices and multi-modal monitoring equipment to ensure the uninterrupted information in the edge area. For communication relay type grids, they are usually set at key nodes of the sea area communication link and are used to build a data transfer bridge between multiple grids. It is recommended to configure airspace extension boats for this type of grid, which have the ability of a lifting platform and can carry relay-type unmanned aerial vehicles to form an air-sea communication channel, effectively extending the communication distance and redundancy ability of the system. The deep-sea exploration type grids are mainly used for seabed geomorphology mapping, underwater target recognition, or environmental data acquisition and are often deployed around deep-sea trenches and seamounts. This type of grid is suitable for configuring submersible underwater exploration boats, and the boat body is equipped with multi-beam sonar, underwater camera systems, and deep-sea buoyancy control modules to meet the task execution requirements in the complex deep-sea environment. For resource sampling type or dynamic warning type grids, which are located in ecologically sensitive areas, sea current convergence areas, or meteorologically highly disturbed areas, the monitoring tasks change frequently and the data acquisition density requirements are high. At this time, maintenance boats or multi-functional hybrid boats can be selected, which are equipped with environmental sensor arrays, automatic sampling modules, and emergency response systems to take into account sampling and rapid support. Through the unmanned boat allocation strategy, the dynamic matching of the unmanned boat type and the grid task attributes is realized, which not only improves the resource allocation efficiency but also significantly enhances the adaptability and stability of the system in multi-tasks, multi-time periods, and multi-emergency situations, and finally constructs a highly autonomous, function-coordinated, and scalable far-sea unmanned boat permanent monitoring system.

[0035] S2: Real-time collect the current environmental information and the battery power of the unmanned boat. When the battery power of the unmanned boat meets the charging conditions, start the collaborative charging strategy.

[0036] It should be noted that real-time collecting the current environmental information and the battery power of the unmanned boat includes collecting wind speed data and wave data through the meteorological sensors on the unmanned boat, obtaining the current battery power, voltage, and current, and uploading the collected information to the remote management platform.

[0037] It should also be noted that meteorological parameter such as wind speed, wind direction, air pressure, temperature and humidity are collected through the meteorological sensor module deployed on the unmanned boat. Sea condition data such as wave height, period and direction are collected through a wave radar, a wave height meter or an inertial measurement unit. The solar radiation flux index is obtained through a light intensity sensor to evaluate the effectiveness of the solar charging condition. Key indicators such as the current remaining power, voltage, current, internal resistance and temperature of the battery are obtained. After the collected data is standardized by the data encoding module, the data is uploaded to the remote management platform by using the on-board communication device.

[0038] Furthermore, the collaborative charging strategy includes that when the power of the unmanned boat is lower than the preset threshold, it is judged whether the sea area where the unmanned boat is currently located meets the condition of safe surfacing according to the environmental information. If the wind speed data and the wave data are within the preset threshold range, the unmanned boat is controlled to surface and the solar panel is deployed for charging. If the wind speed data and the wave data are outside the preset threshold range, the unmanned boat is charged according to the selected boat algorithm.

[0039] It should also be noted that the preferred threshold of the power of the unmanned boat is 20% of the battery capacity. If the current power of the unmanned boat is lower than 20% of the battery capacity, the system automatically starts the charging judgment process. By comprehensively analyzing the current environmental information, it is judged whether the sea area where the unmanned boat is located meets the condition of safe surfacing and charging. Specifically, it includes: collecting the wind speed data and the wave height data at the current moment, and comparing the data with the safe charging environment threshold set in the system. The preferred safe threshold of the wind speed is set to not more than 8 m / s, and the preferred safe threshold of the wave height is set to not higher than 2.0 m. This threshold setting is based on a large amount of ship engineering experience and real sea condition simulation results, and comprehensively considers the stability, safety of the unmanned boat under different sea conditions and the reliability of the solar panel deployment operation. When the wind speed exceeds 8 m / s, the disturbance on the hull surface intensifies, and there is a risk that the solar panel cannot be fully deployed, the structure is damaged or the charging efficiency is significantly reduced. When the wave height exceeds 2.0 m, the surfacing process may be unstable due to wave surge interference, and the probability of capsizing increases.

[0040] Therefore, when both the wind speed and the wave data are within the above preset threshold range, the system will determine that the current sea condition is safe, control the unmanned boat to slowly float to the water surface and deploy the solar panel for autonomous charging; if any data exceeds the threshold range, it is considered that the current sea condition does not meet the surfacing condition. The system will retrieve the resources of maintenance boats or functional boats available for energy replenishment near the current position through the on-board collaborative charging algorithm, and combine the relative distance and the available docking time window to plan the shortest charging path, and instruct the unmanned boat to go to the collaborative boat to complete the charging task. While ensuring the safety of the charging operation, it takes into account the flexible switching between different energy supply methods, improves the adaptability of the system in complex sea conditions and the intelligent level of energy management, and ensures that the far-sea mission process is not interrupted, the energy supply is not interrupted, and the platform state is stable and controllable.

[0041] Furthermore, the boat selection algorithm includes retrieving maintenance boats that can provide energy replenishment near the current sea area, and based on the relative position relationship between the unmanned boat and the maintenance boats, planning the shortest path and the optimal docking time, which is expressed as:

[0042]

[0043] where m * is the maintenance boat that is currently most suitable to be selected for energy replenishment, is the function to obtain the optimal solution of the comprehensive energy replenishment cost. m i ∈M is the set of candidate maintenance boats, α is the distance weight factor, β is the waiting time weight factor, d(u, m i ) is the sea navigation distance between the unmanned boat u and the i-th maintenance boat m i , and t wait (m i ) is the current queuing waiting time of the i-th maintenance boat.

[0044] It should also be noted that after the system determines that the current unmanned boat does not have the condition to surface for charging, it first retrieves the candidate set M composed of all maintenance boats within a certain sea area range near the current position and in the current available state. Then, based on factors such as the relative position relationship, waiting queue status, and energy replenishment ability between the unmanned boat and each maintenance boat, a multi-factor evaluation function is constructed to quantify the energy replenishment cost. Finally, the target boat with the minimum cost is selected. The boat selection algorithm takes into account the energy consumption during energy replenishment on the spatial path and also includes the resource busyness of the target boat in the optimization decision-making scope, so that the selected maintenance boat is both close and responsive, avoiding resource allocation imbalance caused by selecting a "nearest but busy" or "idle but too far" maintenance boat. The distance calculation can adopt the shortest feasible path planning method based on nautical charts, such as the Dijkstra algorithm or the A* pathfinding algorithm, to avoid the influence of restricted areas, obstacle avoidance routes, or channel rules; the waiting time can be dynamically estimated based on the current task queue status of the maintenance boat and the expected completion time of the previous task.

[0045] S3: Analyze and feedback on the charging process.

[0046] It should be noted that analyzing and feedback on the charging process includes recording the start and end times of each charging, generating corresponding charging event numbers. During the charging process, voltage, current, and battery temperature are collected in real time, and the collected data is stored synchronously with the time stamp. The charging efficiency per unit time is calculated based on the start and end times of charging and the change in battery power. Trend comparison analysis is performed based on the historical charging data of the unmanned boat to evaluate whether there is an abnormality in the current charging performance. Based on the analysis results, a charging feedback label is generated, and the feedback information is uploaded to the remote management platform.

[0047] It should also be noted that at the start and end of each charging operation, the corresponding start time and end time are automatically recorded, and a unique charging event number is generated based on the timestamp for subsequent data association and retrieval. During the charging process, energy parameters such as voltage, current, battery temperature, and power change are collected in real time, and the current environmental conditions (such as solar irradiation intensity, wind speed, sea state level, etc.) are recorded simultaneously. This type of raw data is synchronously stored in the on-board data management module with the timestamp to construct the raw data sequence of the charging operation. According to the start and end times of charging and the power change, the charging efficiency per unit time of this charging process is calculated. Through methods such as trend comparison, standard deviation analysis, and moving average, it is evaluated whether the current charging behavior significantly deviates from the historical normal range. Under the same lighting conditions and battery state, if the unit charging efficiency drops by more than 30%, it can be regarded as a mild performance anomaly, and a "charging deviation" label is generated; if multiple parameters are abnormal simultaneously, the system can further determine it as a "potential failure" state and give priority to including it in the subsequent maintenance scheduling plan. The system generates corresponding charging feedback labels based on the above analysis results. These labels can include categories such as normal, mild deviation, performance degradation, charging interruption, etc., and are uploaded to the remote management platform together with the charging event number. The remote platform can construct a regional performance map, an operation health trend map, an energy scheduling priority table, etc. based on the aggregation of multi-boat behavior data, providing a decision-making basis for global task scheduling and maintenance strategy optimization.

[0048] Embodiment 2 is an embodiment of the present invention, providing a method for collaborative dynamic charging of remote-controlled unmanned boats in the open sea based on grid management. To verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0049] The experimental sea area is set as an inshore test area of 25 square kilometers, divided into 50 equivalent grid areas, with an average coverage of 0.5 square kilometers per grid. The experimental scenario simulates typical ocean operation situations, including 72 hours of continuous environmental monitoring, intermittent sudden charging tasks, and dynamic communication relay requirements. Two groups of systems are respectively deployed in the experiment: one group is a traditional scheduling and control type unmanned boat system, and the other group is an intelligent collaborative type unmanned boat system using the method of the present invention. 12 boats are deployed in each group of systems, divided into three sample batches of A / B / C, and the average value of the operation for 3 days is taken for each batch of data.

[0050] The traditional system adopts a fixed route and timed charging strategy, without grid division and collaboration mechanism; the system of the present invention, through the grid-based sea area management strategy, configures task-adapted unmanned boats for each grid, collects the environmental wind and waves and power status in real time, dynamically decides to surface or dock for charging according to the judgment strategy, and records the whole process behavior data and gives feedback for optimization at the same time. All boat bodies are equipped with the same type of energy module and sensing unit to ensure the consistency of experimental conditions. The experimental data is shown in Table 1.

[0051] Table 1 Data Sheet of Performance Comparison Test of Unmanned Boat Collaborative Energy Charging System

[0052]

[0053]

[0054] From the horizontal comparison in the table, it can be observed that the system of the present invention is significantly superior to the traditional unmanned boat system in all core performance indicators, demonstrating the technical advantages of the present invention in sea area grid management, intelligent collaborative energy replenishment, and task continuity guarantee. In terms of the "task completion rate" indicator, the system of the present invention has an average increase of about 12 percentage points (from about 82% of the traditional system to 95%), reflecting that under the grid configuration and resident monitoring mechanism, each regional task can be continuously covered and quickly responded to, greatly reducing the monitoring blind area and scheduling conflict problems.

[0055] In terms of the "average charging efficiency", the present invention adopts dynamic decision-making and environmental perception optimization, and the charging efficiency is increased by more than 30%. The traditional system still performs energy charging when the wind and waves are large and the light is weak due to the adoption of a timed energy replenishment strategy, resulting in significant energy waste; while the system of the present invention avoids inefficient charging under such conditions, and selects the optimal energy replenishment path through the floating judgment or collaborative energy replenishment switching mechanism, greatly reducing losses.

[0056] In terms of the "average response charging delay", the system of the present invention optimizes the energy replenishment response path through a real-time trigger strategy and a boat selection algorithm, shortening the response time from 18.8 minutes of the traditional system to about 9.7 minutes, and improving the energy replenishment response speed by about 48%, which is of crucial significance for the continuity of tasks in the open sea.

[0057] The "energy charging interruption rate" is reduced from 6.6% of the traditional system to 1.1%, indicating that the strategy of the present invention is more stable in terms of charging continuity and path planning rationality; the "maintenance frequency" is reduced from 3.3 times per day to 1.4 times, reflecting that the system realizes energy consumption prediction and task matching through a feedback mechanism, with higher autonomy and stronger reliability.

[0058] For the two indicators of "grid average coverage density" and "data reporting success rate", the former reflects the spatial configuration efficiency, and the latter reflects the information feedback quality. The system of the present invention accurately divides 50 grid areas and precisely allocates unmanned boats to each grid, and the average density is increased from the traditional 0.54 boat / km 2 to 0.94 boat / km 2 , significantly enhancing the regional coverage intensity; at the same time, with the help of the hull feedback mechanism and the collaborative design of communication relays, the data reporting success rate is close to 98%, far superior to 91% of the traditional system, greatly improving the reliability of the system's remote command.

[0059] This embodiment effectively demonstrates that the present invention not only proposes an innovative grid division and collaborative energy replenishment method in terms of theoretical structure, but also exhibits multi-dimensional practical advantages in experimental data, including task continuity, intelligent energy management, feedback optimization mechanism, and system maintainability. It has significant novelty and creativity, can be widely applied to complex deep-sea operation task scenarios, and has good engineering practicality and technical promotion value.

[0060] Embodiment 3, an embodiment of the present invention, provides a collaborative dynamic charging system for deep-sea unmanned boats based on grid management, including a sea area grid division module 100, a collaborative charging control module 200, and a charging feedback analysis module 300.

[0061] Among them, S4: The sea area grid division module 100 includes a grid structure generation module 101 and a grid boat allocation module 102. The grid structure generation module 101 is used to obtain the boundary coordinate data of the target sea area, calculate the total number of grids according to the task coverage requirement and the monitoring radius of the unmanned boat, and divide the target sea area into equivalent regional grids according to longitude and latitude. The grid boat allocation module 102 is used to allocate resident unmanned boats to each grid and match unmanned boats with different functions according to the grid task type.

[0062] It should also be noted that the grid numbers, position coordinates, and corresponding unmanned boat identity information output by the sea area grid division module 100 serve as the basic indexes for the collaborative charging control module 200 to judge the charging strategy.

[0063] S5: The collaborative charging control module 200 includes an environmental information collection module 201 and a charging method judgment module 202. The environmental information collection module 201 is used to collect the wind speed and wave height in real time through a meteorological sensor, and obtain the current battery level, voltage, and current of the unmanned boat. The charging method judgment module 202 is used to judge whether to allow the unmanned boat to surface for autonomous solar charging based on whether the wind speed and wave height are within the preset safety threshold. When the surfacing condition is not met, the selected boat algorithm is called to retrieve the maintenance boat resources, and the shortest energy replenishment path and the optimal docking time are planned based on the relative position relationship.

[0064] It should also be noted that the collaborative charging control module 200 implements environmental perception, charging strategy judgment, and behavior control, and makes a spatial position determination based on the information of the sea area grid division module 100 to judge whether to surface for charging or select a boat for collaborative energy replenishment.

[0065] S6: The charging feedback analysis module 300 includes a charging data acquisition module 301 and a charging efficiency evaluation and feedback module 302. The charging data acquisition module 301 is used to record the start and end times of each charging, collect real-time voltage, current, and battery temperature, and set time stamps. The charging efficiency evaluation and feedback module 302 is used to calculate the charging efficiency per unit time based on the change in battery charge and time, call historical charging data for comparative analysis, determine whether there is any abnormality or performance degradation in the current charging, generate a charging feedback label, and upload it to the remote scheduling and management platform.

[0066] It should also be noted that the charging feedback analysis module 300 completes the acquisition of charging process data and intelligent feedback evaluation, and applies the analysis results to the collaborative charging control module 200 or the remote platform to achieve closed-loop optimization of the system performance.

[0067] If a function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this 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 for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in various embodiments of the present invention. The aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs, etc., which can store program codes.

[0068] The logic and / or steps represented in the flowchart or described in other ways herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch instructions from the instruction execution system, apparatus, or device and execute the instructions), or in combination with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device.

[0069] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection (electronic device) having one or more wirings, a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable media can even be paper or other suitable media on which a program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or otherwise processing it in a suitable manner if necessary, and then storing it in a computer memory.

[0070] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above-described embodiments, the multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), and the like.

[0071] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. A method for collaborative dynamic charging of unmanned surface vehicles in the open sea based on grid management, characterized in that: Including: Dividing the target sea area into grids and assigning unmanned boats to each grid for permanent monitoring; Collecting the current environmental information and the battery power of the unmanned boat in real time. When the battery power of the unmanned boat meets the charging condition, start the collaborative charging strategy; Analyze and feedback on the charging process.

2. The collaborative dynamic energy charging method for remote-controlled unmanned boats based on grid management according to claim 1, characterized in that: The dividing the target sea area into grids includes obtaining the boundary coordinate data of the target sea area, setting the monitoring radius of each unmanned boat according to the task type and monitoring coverage requirements, calculating the total number of grids according to the monitoring radius and the total area of the target sea area, and dividing the target sea area into equivalent regional grids according to longitude and latitude; The unmanned boats include signal boats, maintenance boats, seabed exploration boats, and airspace extension boats.

3. The method for collaborative dynamic charging of unmanned surface vessels in the open sea based on grid management according to claim 1 or 2, characterized in that: The assigning unmanned boats to each grid for permanent monitoring includes selecting different types of unmanned boats according to the grid task type and assigning them to the grid as permanent monitoring units.

4. The method for collaborative dynamic energy charging of unmanned surface vessels in the open sea based on grid management according to claim 3, characterized in that: The collecting the current environmental information and the battery power of the unmanned boat in real time includes collecting wind speed data and wave data through the meteorological sensors on the unmanned boat, obtaining the current battery power, voltage, and current, and uploading the collected information to the remote management platform.

5. The collaborative dynamic energy charging method for unmanned surface vessels in the open sea based on grid management according to claim 1 or 4, characterized in that: The collaborative charging strategy includes, when the battery power of the unmanned boat is lower than the preset threshold, judging whether the sea area where the unmanned boat is currently located meets the condition of safely surfacing according to the environmental information. If the wind speed data and wave data are within the preset threshold range, control the unmanned boat to surface and deploy the solar panels for charging. If the wind speed data and wave data are outside the preset threshold range, charge the unmanned boat according to the boat selection algorithm.

6. The collaborative dynamic energy charging method for unmanned surface vessels in the open sea based on grid management according to claim 5, wherein: The boat selection algorithm includes retrieving the maintenance boats that can provide energy supply near the current sea area, and planning the shortest path and the optimal docking time based on the relative position relationship between the unmanned boat and the maintenance boat, expressed as: Among them, m * is the maintenance boat that is currently most suitable to be selected for energy replenishment, To obtain the optimal solution function of the comprehensive energy replenishment cost, m i ∈M is the set of candidate maintenance boats, α is the distance weight factor, β is the waiting time weight factor, d(u, m i ) is the sea navigation distance between the unmanned boat u and the i-th maintenance boat m i , and t wait (m i ) is the current queuing waiting time of the i-th maintenance boat.

7. The collaborative dynamic energy charging method for remote-controlled unmanned boats based on grid management according to any one of claims 1, 2, 4, or 6, characterized in that: The analyzing and feedback on the charging process includes recording the start and end times of each charging, generating the corresponding charging event number, collecting the voltage, current, and battery temperature in real time during the charging process, synchronously storing the collected data with the timestamp, calculating the charging efficiency per unit time according to the start and end times of charging and the change in battery power, conducting trend comparison analysis based on the historical charging data of the unmanned boat, evaluating whether there is an abnormality in the current charging performance, generating a charging feedback label based on the analysis result, and uploading the feedback information to the remote management platform.

8. An offshore unmanned boat collaborative dynamic charging system based on grid management, characterized in that: Including a sea area grid division module (100), a collaborative charging control module (200), and a charging feedback analysis module (300); The sea area grid division module (100) includes a grid structure generation module (101) and a grid boat assignment module (102). The grid structure generation module (101) is used to obtain the boundary coordinate data of the target sea area, calculate the total number of grids according to the task coverage requirements and the monitoring radius of the unmanned boat, and divide the target sea area into equivalent regional grids according to longitude and latitude. The grid boat assignment module (102) is used to assign permanent unmanned boats to each grid and match unmanned boats with different functions according to the grid task type; The collaborative charging control module (200) includes an environmental information acquisition module (201) and a charging method determination module (202). The environmental information acquisition module (201) is used to collect the wind speed and wave height in real time through a meteorological sensor, and obtain the current battery power, voltage, and current of the unmanned boat. The charging method determination module (202) is used to determine whether to allow the unmanned boat to surface for autonomous solar charging based on whether the wind speed and wave height are within a preset safety threshold. When the surfacing condition is not met, it calls the boat selection algorithm to retrieve the maintenance boat resources, and plans the shortest charging path and the optimal docking time based on the relative position relationship; The charging feedback analysis module (300) includes a charging data acquisition module (301) and a charging efficiency evaluation and feedback module (302). The charging data acquisition module (301) is used to record the start and end times of each charging, collect the real-time voltage, current, and battery temperature and set time stamps. The charging efficiency evaluation and feedback module (302) is used to calculate the charging efficiency per unit time according to the change in battery power and time, call the historical charging data for comparative analysis, determine whether there is an abnormality or performance decay in the current charging, generate a charging feedback label and upload it to the remote scheduling and management platform.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to 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 method according to any one of claims 1 to 7.

Images