Dynamic charging coordination method, system, device and medium under far sea grid monitoring

Abstract

The application discloses a dynamic charging coordination method, system, equipment and medium under open sea grid monitoring, relates to the technical field of open sea monitoring and energy management, and comprises grid dynamic division and equipment priority allocation; the light receiving efficiency is optimized by adjusting the inclination angle of the photovoltaic film, a task adjustment and energy management balance mechanism is constructed, and abnormal detection and cooperative response are carried out based on a multi-sensor fusion technology. The method disclosed by the application carries out grid dynamic division and equipment priority allocation, optimizes the grid boundary by using a hierarchical quadtree algorithm and real-time data, improves the utilization rate and monitoring accuracy of monitoring resources, optimizes the inclination angle of the photovoltaic film and the task energy management balance mechanism, improves the task completion efficiency while ensuring long-time endurance of the equipment, and accurately identifies complex abnormal events and quickly allocates response tasks based on the abnormal detection and cooperative response of the multi-modal sensor fusion technology, thereby improving the efficiency and intelligent level of the monitoring system as a whole.

Description

Technical Field

[0001] This invention relates to the field of offshore monitoring and energy management technology, specifically to a dynamic energy charging coordination method, system, equipment, and medium under offshore grid monitoring. Background Technology

[0002] In recent years, monitoring and management technologies in offshore areas have seen significant development, particularly in areas such as marine resource development, ecological protection, and security monitoring. The application of intelligent equipment such as unmanned surface vessels (USVs) and drones has become increasingly widespread. These devices, relying on real-time data acquisition, automatic navigation, and remote control technologies, have achieved large-scale regional monitoring and data transmission. Meanwhile, the concept of grid-based management has been applied in marine monitoring, improving monitoring efficiency through the division of monitoring areas and the deployment of distributed equipment. In terms of energy management, the application of solar energy technology in marine equipment has made long-term endurance possible, with some systems supplementing their power through fixed solar panels or wind power equipment. However, the complex and variable offshore environment, including factors such as lighting conditions, wave intensity, and frequent abnormal events, places higher demands on the continuous and stable operation of existing technologies.

[0003] Despite some progress in offshore monitoring and energy management technologies, existing technologies still have significant shortcomings and are unable to meet the needs of efficient collaborative monitoring in complex environments. Existing grid-based monitoring systems have limited dynamic adjustment capabilities, typically relying on fixed grid division methods and failing to optimize grid shape and task allocation based on real-time environmental data, resulting in uneven distribution of monitoring resources. Current energy management strategies for unmanned surface vessels are relatively simple, and the fixed installation of solar panels makes it difficult to adjust in real time according to the sun's angle, leading to insufficient charging efficiency. When high-priority tasks conflict with charging needs, the reliability of equipment operation is difficult to guarantee. The fusion and analysis capabilities of multimodal sensor data are limited, and most existing systems adopt single-mode anomaly detection technologies, resulting in low efficiency in identifying complex anomalies such as illegal vessels or floating objects in the ocean, and delays in response. Summary of the Invention

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

[0005] Therefore, the technical problem solved by this invention is that existing offshore monitoring and energy management methods have insufficient dynamic adjustment capabilities of monitoring grids, low equipment charging efficiency, and inaccurate and inefficient anomaly detection and response capabilities, as well as the problem of how to achieve efficient monitoring and collaborative energy management in complex offshore environments.

[0006] To address the aforementioned technical problems, this invention provides the following technical solution: a dynamic energy charging coordination method under offshore grid-based monitoring, comprising dynamic grid division and equipment priority allocation; optimizing light reception efficiency by adjusting the photovoltaic film tilt angle, and constructing a task adjustment and energy management balance mechanism; and performing anomaly detection and coordinated response based on multi-sensor fusion technology.

[0007] As a preferred embodiment of the dynamic energy charging coordination method under grid-based monitoring in the open sea described in this invention, the dynamic grid division includes dynamically adjusting the grid boundary based on real-time environmental data, historical risk distribution, and monitoring targets in the open sea area.

[0008] As a preferred embodiment of the dynamic charging coordination method under the grid-based monitoring of the open sea described in this invention, the dynamic adjustment of the grid boundary includes: generating an initial grid based on a predetermined algorithm, adjusting the grid shape by superimposing the grid weight value with the actual needs of the monitoring area; when the real-time monitoring data is updated, recalculating the grid boundary through the system, and sending the adjustment result to the device for navigation path adjustment.

[0009] As a preferred embodiment of the dynamic charging coordination method under the grid-based monitoring of the open sea described in this invention, the device priority allocation includes: calculating the priority based on the remaining power of the device, the distance to the target grid, and the importance of the task; the system selects the best device based on the device priority, continuously monitors the task execution status of the device after task allocation, and readjusts the priority according to real-time conditions.

[0010] As a preferred embodiment of the dynamic energy charging coordination method under the grid-based monitoring system in the open sea described in this invention, the optimization of light reception efficiency includes: the photovoltaic film is connected to an angle adjustment mechanism via a mechanical support; the adjustment mechanism monitors the angle of sunlight incidence via a light sensor; the angle of the photovoltaic film is dynamically adjusted according to the sensor data to maintain the photovoltaic film in the best light-receiving state; power generation modules are installed in sections on the surface of the photovoltaic film; the inefficient modules are automatically switched to optimize energy charging efficiency by monitoring the performance status of the modules; and the photovoltaic film angle adjustment is coordinated with the navigation path.

[0011] As a preferred embodiment of the dynamic charging coordination method under grid-based monitoring in the open sea described in this invention, the balancing mechanism includes: when the unmanned surface vessel enters a low-energy consumption mode, it prioritizes completing low-priority tasks within the grid while simultaneously deploying a photovoltaic film for charging; when a high-priority task is detected, the unmanned surface vessel automatically retracts the photovoltaic film and switches to the task execution state; the task switching threshold is dynamically adjusted by monitoring the remaining power, and the switching mechanism is remotely adjusted by the command system to adapt to environmental changes.

[0012] As a preferred embodiment of the dynamic charging coordination method under the grid-based monitoring of the open sea described in this invention, the anomaly detection includes: acquiring multimodal data of the monitoring area through a sea surface visual sensor, sonar detection equipment and underwater multibeam sensor; the data is fused through a neural network to extract anomaly features and identify floating objects, illegal vessels and abnormal marine ecological events; the identification results are uploaded to the command system and the relevant grid monitoring priorities are automatically adjusted.

[0013] As a preferred embodiment of the dynamic charging coordination method under the grid-based monitoring of the open sea described in this invention, the coordinated response includes: after the command system detects an anomaly, it reallocates tasks according to the equipment location and remaining power, with the equipment closest to the anomaly area responding first, different equipment adjusting their paths to support monitoring, the command system adjusting the monitoring range according to equipment feedback, and restoring the original tasks of the equipment after the anomaly ends.

[0014] Another objective of this invention is to provide a dynamic energy charging coordination system under grid-based monitoring in the open sea, which can allocate monitoring tasks according to equipment status and task requirements, and adjust the task allocation in real time to adapt to environmental changes, thus solving the problem that current open sea monitoring and energy management technologies lack the ability to dynamically adjust the monitoring grid.

[0015] As a preferred embodiment of the dynamic charging and collaborative system under offshore grid-based monitoring described in this invention, the system includes: a dynamic management module for the offshore monitoring area, an energy optimization module, and an anomaly detection and response module; the dynamic management module for the offshore monitoring area includes a grid division module and a priority allocation module. The grid division module is used to dynamically divide the monitoring grid according to real-time environmental data and historical monitoring data. The priority allocation module is used to allocate monitoring tasks according to equipment status and task requirements, and adjust the task allocation in real time to adapt to environmental changes; the energy optimization module includes a charging efficiency optimization module and an energy balance module. The charging efficiency optimization module is used to dynamically adjust the photovoltaic film angle and the power generation module to maximize the light energy utilization efficiency. The energy balance module is used to dynamically switch the charging and task execution modes according to task priority and equipment power status; the anomaly detection and response module includes an anomaly detection module and a collaborative response module. The anomaly detection module is used to fuse multimodal sensor data to identify and classify abnormal events. The collaborative response module is used to achieve collaborative response between devices through dynamic task reallocation after an abnormal event occurs.

[0016] A computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement a dynamic energy charging coordination method under grid-based monitoring in the open sea.

[0017] A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of a dynamic energy charging coordination method under offshore grid monitoring.

[0018] The beneficial effects of this invention are as follows: The dynamic charging and coordination method under grid-based monitoring in the open sea provided by this invention optimizes the grid boundary through dynamic grid division and device priority allocation, using a hierarchical quadtree algorithm and real-time data to ensure priority coverage of high-risk areas, thereby improving the utilization rate and accuracy of monitoring resources. Through photovoltaic film tilt angle optimization and task energy management balancing mechanism, efficient charging and task switching in complex environments are achieved, improving task completion efficiency while ensuring long-term equipment operation. Based on multimodal sensor fusion technology, anomaly detection and coordinated response accurately identify complex abnormal events and quickly allocate response tasks, shortening processing latency and enhancing the practicality and reliability of the system in complex open sea environments. Overall, the efficiency and intelligence level of the monitoring system are improved, and this invention achieves better results in terms of efficiency, accuracy, and reliability. Attached Figure Description

[0019] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. 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.

[0020] Figure 1 The flowchart illustrates the overall process of the dynamic energy charging coordination method under grid-based monitoring in the open sea, as provided in the first embodiment of the present invention.

[0021] Figure 2 The overall flowchart of the dynamic charging and coordination system under grid-based monitoring in the open sea provided in the third embodiment of the present invention is shown. 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 As one embodiment of the present invention, a dynamic energy charging coordination method under offshore grid monitoring is provided, comprising:

[0024] S1: Perform dynamic mesh partitioning and device priority allocation.

[0025] Furthermore, the grid is dynamically divided, including dynamically adjusting the grid boundaries based on real-time environmental data, historical risk distribution, and monitoring targets in the offshore area.

[0026] It should be noted that dynamically adjusting the grid boundary includes generating an initial grid based on a predetermined algorithm, adjusting the grid shape by superimposing the grid weight values ​​with the actual needs of the monitored area, and recalculating the grid boundary through the system when real-time monitoring data is updated, and sending the adjustment results to the device for navigation path adjustment.

[0027] It should also be noted that a preferred algorithm for the predetermined algorithm includes a region partitioning algorithm based on a hierarchical quadtree. The quadtree algorithm can recursively divide a region into different levels of grids, providing finer-grained partitioning for high-risk areas and coarser-grained grids for low-risk areas, thus improving the flexibility and efficiency of monitoring resource allocation. Specific steps include inputting the geographical extent and historical risk distribution data of the initial monitoring area; using the center point of the monitoring area as the initial partitioning point, dividing the entire area into four sub-regions; calculating the risk weight for each sub-region; if the risk weight of a region is greater than a preset threshold, further subdivision is performed; repeating the subdivision steps until… If the weight of all sub-regions is below the threshold, or the subdivision reaches the set maximum level, a hierarchical grid structure is output, generating an initial grid shape. During the adjustment process, the system analyzes real-time environmental data and historical data to determine whether the current grid boundary meets the monitoring requirements. When it is determined that the grid boundary needs adjustment, the shape and distribution of the grid are recalculated through re-optimization. The re-optimization adopts a regional grid refinement strategy, densely dividing high-risk areas and sparsely dividing low-risk areas. Finally, the system distributes new navigation paths and task instructions to the device based on the adjusted grid shape to ensure efficient allocation and dynamic adaptability of monitoring resources.

[0028] It should also be noted that the device priority allocation includes calculating priority based on the device's remaining power, distance from the target grid, and task importance; the system selects the best device based on the device priority, continuously monitors the device's task execution status after task allocation, and readjusts the priority based on real-time conditions.

[0029] It should also be noted that a preferred method for prioritizing tasks based on remaining battery power, distance from the target grid, and task importance is expressed as follows:

[0030]

[0031] Wherein, P is the task priority score, representing the overall priority of the device in executing a certain task; E is the remaining battery power of the device, used to measure the current battery life of the device; D is the distance between the device and the target grid, used to measure the proximity of the device to the task target, the shorter the distance, the higher the priority; R is the task importance, used to measure the urgency of the current task and its importance to the overall operation of the system; W1, W2, and W3 are the weighting coefficients of battery power, distance, and task importance, respectively, used to adjust the relative importance of the three factors in the priority calculation.

[0032] It should also be noted that the grid shape is dynamically adjusted based on real-time data to ensure that high-risk areas are prioritized for coverage; the system combines historical risk data with current monitoring targets to optimize the grid range in real time; dynamic grid division effectively avoids resource waste, ensuring that the area covered by the equipment is highly matched with the risk distribution, thus improving the accuracy of monitoring tasks; it achieves adaptive monitoring of complex offshore environments, improving the efficiency of the monitoring system and the rationality of resource allocation; by calculating the remaining power of the equipment, the importance of the task, and the distance, the system allocates reasonable tasks to the equipment, prioritizing the equipment in the best condition to perform tasks; this allocation mechanism avoids the problem of uneven task allocation among equipment, ensuring efficient use of equipment resources, while reducing the risk of task failure due to insufficient energy or unsuitable location; it improves the working efficiency and task completion rate of the equipment, extends the task duration of the equipment, and reduces delays caused by task errors.

[0033] S2: Optimize light reception efficiency by adjusting the tilt angle of the photovoltaic film, and construct a balance mechanism between task adjustment and energy management.

[0034] Furthermore, optimizing light reception efficiency includes: the photovoltaic film is connected to an angle adjustment mechanism via a mechanical support; the adjustment mechanism monitors the angle of sunlight incidence via a light sensor; the angle of the photovoltaic film is dynamically adjusted based on sensor data to maintain optimal light reception; power generation modules are installed in sections on the surface of the photovoltaic film, and inefficient modules are automatically switched to optimize charging efficiency by monitoring module performance; and the photovoltaic film angle adjustment is coordinated with the navigation path.

[0035] It should also be noted that a preferred scheme for dynamically adjusting the photovoltaic film angle based on sensor data includes introducing a wind speed sensor to detect changes in wind speed in the environment in real time. When the wind speed exceeds a safety threshold, the adjustment range of the photovoltaic film tilt angle is limited, or the photovoltaic film is automatically folded to avoid equipment damage. When the wind speed is below 10 m / s, the photovoltaic film angle can be dynamically adjusted to the maximum tilt angle (e.g., 45 degrees) to obtain optimal illumination; when the wind speed reaches 10-20 m / s, the system limits the tilt angle adjustment range to within 15 degrees to reduce the pressure of wind resistance on the photovoltaic film structure; when the wind speed exceeds 20 m / s, the photovoltaic film automatically folds to the main body of the equipment and enters a safety protection mode.

[0036] It should be noted that the balancing mechanism includes: when the unmanned surface vessel enters a low-energy consumption mode, it prioritizes completing low-priority tasks within the grid while simultaneously deploying the photovoltaic film for charging; when a high-priority task is detected, the unmanned surface vessel automatically retracts the photovoltaic film and switches to task execution mode; the task switching threshold is dynamically adjusted through monitoring the remaining power, and the switching mechanism is remotely adjusted through the command system to adapt to environmental changes.

[0037] It should also be noted that a preferred approach to dynamically adjust the task switching threshold through remaining power monitoring includes setting a dynamic switching threshold based on the importance of the task; for example, high-priority tasks can exceed power limits, while low-priority tasks need to strictly adhere to the remaining power switching threshold; normal cruise tasks (low priority): when the power is below 60%, cruise stops and switches to charging mode; emergency anomaly response tasks (high priority): even if the power is as low as 30%, the task continues to be executed, and an emergency charging strategy (such as full-power deployment of photovoltaic film) is initiated; special monitoring tasks (medium priority): the threshold is dynamically adjusted according to the current task time requirements to ensure that there is enough power to return to the safe area after the task is completed.

[0038] It should also be noted that the angle of the photovoltaic film is adjusted dynamically based on real-time data from the light sensor to maintain the optimal incident angle; the zoned power generation module automatically switches to inefficient modules through status monitoring to ensure charging efficiency; this optimization method improves the utilization efficiency of solar energy, enabling efficient charging even in environments with insufficient sunlight or poor sea surface reflection conditions; by adjusting the angle in real time, the photovoltaic film can improve charging efficiency, ensuring the energy supply required for the equipment to perform tasks for extended periods; it enters a low-energy consumption mode during low-priority tasks while simultaneously using the photovoltaic film for charging; when a high-priority task is triggered, the unmanned surface vessel retracts the photovoltaic film and immediately responds to the task; this mechanism establishes an efficient balance between energy supply and task execution, avoiding situations where insufficient energy affects task execution, while maximizing the equipment's endurance during non-critical tasks; it improves the autonomy and task completion rate of the unmanned surface vessel, and significantly reduces monitoring interruptions caused by energy depletion of equipment in the open ocean.

[0039] S3: Anomaly detection and collaborative response based on multi-sensor fusion technology.

[0040] Furthermore, anomaly detection includes acquiring multimodal data of the monitored area through surface visual sensors, sonar detection equipment, and underwater multibeam sensors; the data is fused through neural networks to extract anomaly features and identify floating objects, illegal vessels, and abnormal marine ecological events; the identification results are uploaded to the command system, and the relevant grid monitoring priorities are automatically adjusted.

[0041] It should be noted that a preferred scheme for anomaly detection specifically includes: acquiring optical image data of the monitored area using a sea surface visual sensor, the optical image data including features such as the shape, size, and color of sea surface objects; acquiring acoustic echo signals of underwater targets using sonar detection equipment, the acoustic signals including target reflection intensity and distance information; acquiring three-dimensional spatial distribution data of the target area using an underwater multibeam sensor, the three-dimensional distribution data reflecting the position, size, and structural features of the underwater targets; denoising the acquired optical image data to eliminate interference caused by sea surface light reflection or weather conditions, and highlighting the edge and color features of target objects using image enhancement techniques; performing spectral analysis on the acoustic signal data, decomposing the original signal into frequency characteristic components, filtering out background noise and retaining target reflection features; performing three-dimensional reconstruction of the underwater multibeam data, and restoring the target spatial distribution within the monitored area using interpolation algorithms; and utilizing... Feature extraction is performed on optical images, acoustic signals, and 3D distributed data using neural network models. Specifically, this includes extracting target shape and color features from optical images using convolutional neural networks, extracting time-series features from acoustic signals using recurrent neural networks, and extracting structural features from 3D spatial data using autoencoder networks. These features are then mapped to a unified multi-dimensional feature space using a multimodal fusion algorithm, generating feature vectors that include target shape, dynamic changes, reflection characteristics, and positional relationships. By comparing these feature vectors with a pre-trained anomaly classification model, abnormal events within the monitored area are identified. These abnormal events include floating objects on the sea surface, illegal vessels, and marine ecological anomalies. The identification results and corresponding feature vectors are uploaded to the command system. The command system dynamically adjusts the monitoring priority of relevant grids based on the type and risk level of the abnormal events and triggers task allocation and path optimization processes to schedule relevant equipment to respond to the abnormal events.

[0042] It should be noted that the coordinated response includes the command system redistributing tasks based on device location and remaining power after detecting an anomaly, prioritizing the response of devices closest to the anomaly area, adjusting the paths of different devices to support monitoring, adjusting the monitoring range based on device feedback, and restoring the original tasks of the devices after the anomaly ends.

[0043] It should also be noted that by utilizing surface visual sensors, sonar equipment, and underwater multibeam sensors to acquire multimodal data, and combining this with neural network models for fusion analysis, abnormal events (such as illegal vessels, floating objects on the sea surface, etc.) can be accurately identified. Multi-sensor fusion technology improves the system's ability to identify abnormal events, enabling rapid response even in complex marine environments. It achieves real-time and accurate identification of abnormal events, reduces false alarm and missed alarm rates, and provides a reliable data foundation for subsequent responses. The command system dynamically allocates tasks based on equipment status (location, power level), prioritizing the response of equipment closest to the abnormal area, while other equipment adjusts its path to assist in monitoring. After the response is completed, the system restores the normal task paths of the equipment. This collaborative response mechanism significantly shortens the response time for handling abnormal events. At the same time, the collaborative work of multiple devices improves the overall efficiency of task completion, enhances the anomaly handling capability of the offshore monitoring system, and ensures rapid response to abnormal events and optimal resource utilization.

[0044] Example 2 is an embodiment of the present invention, which provides a dynamic energy charging coordination method under grid-based monitoring in the open sea. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiment.

[0045] First, the experimental area was selected in a coastal sea area, covering approximately 100 square kilometers, including high-risk areas (dense fishing vessel areas and ecologically sensitive areas) and low-risk areas (open water). The experimental equipment included three unmanned surface vessels (USVs), each equipped with a photovoltaic film charging device, a sea surface visual sensor, sonar detection equipment, and an underwater multibeam sensor. The command center used a hierarchical quadtree algorithm for dynamic grid partitioning and priority task allocation. The initial grid partitioning was based on historical and real-time environmental data, with fine-grained partitioning (level 4 grid, approximately 0.5 km side length) for dense fishing vessel areas and ecologically sensitive areas, and coarse-grained grid partitioning (level 2 grid, approximately 2 km side length) for open water. The system dynamically allocated tasks based on equipment battery power (70%-100% high battery, 40%-70% medium battery, <40% low battery), task importance, and grid distance. In the priority calculation, the weights are set as follows: 50% for battery power, 30% for distance, and 20% for task importance. The system adjusts the photovoltaic film tilt angle in real time: 45 degrees for low wind speeds (<10 m / s), within 15 degrees for medium wind speeds (10-20 m / s), and retracts the photovoltaic film for high wind speeds (>20 m / s). When a high-priority task is triggered (such as an abnormal event response), the device interrupts charging and switches to task execution mode. Monitoring data is collected in real time through a sea surface visual sensor, sonar detection equipment, and a multi-beam sensor. After detecting an illegal vessel, features are extracted through neural network analysis, and data is uploaded to the command center after confirming the anomaly. The command center allocates response tasks based on the device's battery power, location, and task status, with the nearest device responding first and other devices monitoring collaboratively. Refer to Table 1 for the recording and analysis of experimental data.

[0046] Table 1 Experimental Data Recording Table

[0047]

[0048] Experiments show that under different wind speed conditions, the grid coverage rate remains above 90%, indicating that the hierarchical quadtree algorithm combined with real-time data can dynamically optimize the grid boundary and ensure that high-risk areas are prioritized for coverage. The equipment task completion rate reaches over 95% under low wind speed conditions, fully verifying the rationality of the priority allocation mechanism. Data shows that through photovoltaic film angle optimization and dynamic charging mechanism, the charging efficiency is increased to 85% under low wind speed conditions, and even under medium to high wind speed conditions (>10 m / s), the charging efficiency can still maintain over 60%. Compared with the traditional fixed-angle charging method, this invention can adapt to complex environmental changes and extend the equipment's battery life. In the experiment, the abnormal response latency was reduced to within 10 seconds under high-priority task triggering scenarios, indicating that the multi-modal sensor fusion and command center collaborative scheduling mechanism can quickly identify anomalies and effectively allocate tasks. In addition, through multi-device collaborative work, the efficiency of abnormal event handling is improved, and the task completion rate exceeds 89%, avoiding the delay problem caused by a single device handling anomalies.

[0049] Traditional fixed grid division methods are difficult to dynamically adapt to real-time data, while this invention achieves high efficiency and flexibility in resource allocation by optimizing grid boundaries in real time; fixed photovoltaic film charging methods are inefficient in complex wind speed environments, while this invention dynamically adjusts the tilt angle of the photovoltaic film to improve charging efficiency; single sensor anomaly detection has a high false alarm rate and low processing efficiency, while this invention significantly shortens response latency and improves processing accuracy through multimodal data fusion and collaborative response.

[0050] Example 3, referring to Figure 2 As an embodiment of the present invention, a dynamic energy charging coordination system under grid-based monitoring in the open sea is provided, including a dynamic management module 100 for the open sea monitoring area, an energy optimization module 200, and an anomaly detection and response module 300.

[0051] S4: The offshore monitoring area dynamic management module 100 includes a grid division module 101 and a priority allocation module 102. The grid division module 101 is used to dynamically divide the monitoring grid according to real-time environmental data and historical monitoring data. The priority allocation module 102 is used to allocate monitoring tasks according to equipment status and task requirements, and adjust the task allocation in real time to adapt to environmental changes.

[0052] It should be noted that after the system starts, the offshore monitoring area dynamic management module 100 obtains real-time environmental data of the offshore area through the grid division module 101, including meteorological conditions, wave height and current direction. Based on a predetermined algorithm, it generates an initial grid to divide the monitoring area. The priority allocation module 102 simultaneously collects equipment status, location, power, task load, etc., and allocates tasks to the equipment according to the priority calculation formula to ensure that high-priority tasks are executed first. The grid division module 101 and priority allocation module 102 in the offshore monitoring area dynamic management module 100 update the monitoring tasks in real time during operation and pass the update results to the energy optimization module 200 to optimize the task and energy balance of the equipment.

[0053] S5: The energy optimization module 200 includes a charging efficiency optimization module 201 and an energy balance module 202. The charging efficiency optimization module 201 is used to dynamically adjust the angle of the photovoltaic film and the power generation module to maximize the light energy utilization efficiency. The energy balance module 202 is used to dynamically switch the charging and task execution modes according to the task priority and the power status of the equipment.

[0054] It should be noted that the charging efficiency optimization module 201 dynamically monitors the lighting conditions, obtains solar incidence angle data through a light sensor, and adjusts the photovoltaic film tilt angle in real time to optimize power generation efficiency. If it detects that the performance of some power generation modules of the photovoltaic film is inefficient, the module will automatically switch to a high-efficiency module to maintain energy output. The energy balance module 202 adjusts the equipment operation mode according to task priority and remaining power status. For example, when the equipment is performing a low-priority task and the power is insufficient, the energy balance module instructs the equipment to enter a low-energy consumption mode and start charging the photovoltaic film. If a high-priority task is triggered, the equipment automatically switches to the task execution mode, turns off the photovoltaic film to focus on the task objective. During the task execution and charging switching process, the energy optimization module 200 synchronizes the equipment power status to the anomaly detection and response module 300 so that the equipment can be quickly deployed in the event of an abnormal event.

[0055] S6: The anomaly detection and response module 300 includes an anomaly detection module 301 and a collaborative response module 302. The anomaly detection module 301 is used to fuse multimodal sensor data to identify and classify abnormal events. The collaborative response module 302 is used to achieve collaborative response between devices through dynamic task reallocation after an abnormal event occurs.

[0056] It should be noted that the anomaly detection module 301 collects data through multimodal sensors, including surface visual sensors, sonar detection equipment, and underwater multibeam sensors, and fuses and analyzes anomaly characteristics, such as identifying illegal vessels, floating objects, or ecological anomalies. After detecting an anomaly, the module immediately uploads the event information to the command center and coordinates with the grid division module 101 to dynamically adjust the priority of relevant grids. The collaborative response module 302, based on the urgency and type of the anomaly event, works in conjunction with the priority allocation module 102 to dynamically adjust task allocation. Devices closest to the anomaly area and with sufficient power respond first, while other devices adjust their paths as needed to provide peripheral support. After the response is completed, the system automatically restores the devices to their original task paths and updates the grid priority. When processing events, the collaborative response module 302 in the anomaly detection response module 300 calls the priority allocation module 102 to dynamically adjust tasks and simultaneously notifies the grid division module 101 to adjust the monitoring density of relevant grid areas based on real-time event conditions.

[0057] 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 of 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.

[0058] 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-included 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.

[0059] More specific examples (a non-exhaustive list) of computer-readable media 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 programs can be printed, because programs 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.

[0060] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using 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. It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended 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.

[0061] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended 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 dynamic energy charging coordination method under grid-based monitoring in the open sea, characterized in that, include: Perform dynamic grid partitioning and device priority allocation; By adjusting the tilt angle of the photovoltaic film, the light reception efficiency is optimized, and a balance mechanism between task adjustment and energy management is constructed. Anomaly detection and collaborative response based on multi-sensor fusion technology; The dynamic grid division includes dynamically adjusting the grid boundaries based on real-time environmental data, historical risk distribution, and monitoring targets in the offshore area. The dynamic adjustment of the grid boundary includes, An initial grid is generated based on a predetermined algorithm, and the grid shape is adjusted by superimposing the grid weight values ​​with the actual needs of the monitoring area. When real-time monitoring data is updated, the system recalculates the grid boundary and sends the adjustment results to the device for navigation path adjustment. Using the center point of the monitored area as the initial dividing point, the entire area is divided into four sub-areas; a risk weight is calculated for each sub-area, and if the risk weight of a certain area is greater than a preset threshold, it is further subdivided. Repeat the subdivision step until the weight of all sub-regions is below the threshold, or the subdivision reaches the set maximum level; output a hierarchical grid structure. The optimized light reception efficiency includes connecting the photovoltaic film to an angle adjustment mechanism via a mechanical support, and the adjustment mechanism monitoring the incident angle of sunlight via a light sensor; The angle of the photovoltaic film is dynamically adjusted based on sensor data to keep the photovoltaic film in the best light-receiving state. The photovoltaic film surface is partitioned with power generation modules, and the inefficient modules are automatically switched to optimize charging efficiency by monitoring the performance status of the modules. Photovoltaic film angle adjustment and navigation path coordination; The angle of the photovoltaic film is adjusted based on real-time data from the light sensor to dynamically maintain the optimal incident angle; The zoned power generation module automatically switches to inefficient modules through status monitoring to ensure charging efficiency; it enters a low-energy consumption mode during low-priority tasks while using the photovoltaic film for charging; when a high-priority task is triggered, the unmanned surface vessel retracts the photovoltaic film and immediately responds to the task. By introducing a wind speed sensor, changes in wind speed in the environment are detected in real time. When the wind speed exceeds a safe threshold, the adjustment range of the photovoltaic film tilt angle is limited, or the photovoltaic film is automatically folded to avoid damage to the equipment. When the wind speed is below 10 m / s, the photovoltaic film angle can be dynamically adjusted to a maximum tilt angle of 45 degrees to obtain optimal illumination. When the wind speed reaches 10-20 m / s, the system limits the tilt angle adjustment range to within 15 degrees to reduce the pressure of wind resistance on the photovoltaic film structure. When the wind speed exceeds 20 m / s, the photovoltaic film automatically folds into the main body of the equipment. The anomaly detection includes, Multimodal data of the monitored area is acquired through surface visual sensors, sonar detection equipment, and underwater multibeam sensors. The data is fused and processed through neural networks to extract abnormal features and identify floating objects on the sea surface, illegal vessels, and abnormal marine ecological events. The identification results are uploaded to the command system, and the priority of relevant grid monitoring is automatically adjusted; Device priority allocation, including, Priority is calculated based on the device's remaining battery power, distance from the target grid, and task importance; ， in, As a score for task priority, This refers to the remaining battery power of the device. The distance between the device and the target grid. Due to the importance of the mission, , , These are the weighting coefficients for battery power, distance, and mission importance, respectively. The system selects the best device based on device priority, continuously monitors the task execution status of the device after assigning the task, and readjusts the priority according to real-time conditions. Collaborative response, including, After detecting an anomaly, the command system reassigns tasks based on device location and remaining battery power. Devices closest to the anomaly area respond first, and different devices adjust their paths to support monitoring. The command system adjusts the monitoring range based on device feedback and restores the original tasks of the devices after the anomaly ends.

2. The dynamic charging coordination method under offshore grid monitoring as described in claim 1, characterized in that: The balancing mechanism includes, When the unmanned surface vessel enters low-energy mode, it prioritizes completing low-priority tasks within the grid and simultaneously deploys a photovoltaic film for charging. When a high-priority task is detected, the unmanned surface vessel automatically retracts the photovoltaic film and switches to task execution mode; The task switching threshold is dynamically adjusted by monitoring remaining battery power, and the switching mechanism is remotely adjusted by the command system to adapt to environmental changes.

3. A dynamic energy charging and coordination system under grid-based monitoring in the open sea, characterized in that: It includes a dynamic management module for offshore monitoring areas (100), an energy optimization module (200), and an anomaly detection and response module (300). The offshore monitoring area dynamic management module (100) includes a grid division module (101) and a priority allocation module (102). The grid division module (101) is used to dynamically divide the monitoring grid according to real-time environmental data and historical monitoring data. The priority allocation module (102) is used to allocate monitoring tasks according to equipment status and task requirements, and adjust the task allocation in real time to adapt to environmental changes. The energy optimization module (200) includes a charging efficiency optimization module (201) and an energy balance module (202). The charging efficiency optimization module (201) is used to dynamically adjust the angle of the photovoltaic film and the power generation module to maximize the light energy utilization efficiency. The energy balance module (202) is used to dynamically switch the charging and task execution modes according to the task priority and the power status of the equipment. The anomaly detection and response module (300) includes an anomaly detection module (301) and a collaborative response module (302). The anomaly detection module (301) is used to fuse multimodal sensor data to identify and classify abnormal events. The collaborative response module (302) is used to achieve collaborative response between devices through dynamic task reallocation after an abnormal event occurs.

4. 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 dynamic charging coordination method under the grid-based monitoring of the open sea as described in claim 1 or 2.

5. 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 dynamic charging coordination method under the grid-based monitoring of the open sea as described in claim 1 or 2.

Images