Ocean ecological environment automatic monitoring and analyzing system based on intelligent unmanned ship

Abstract

The application relates to the field of marine ecological environment protection, and specifically discloses an automatic monitoring and analyzing system for marine ecological environment based on an intelligent unmanned ship, which comprises the following modules: a pollution identification module that identifies pollution areas by monitoring real-time sea pollution concentration data through the unmanned ship and combining threshold values; a boundary construction module that constructs the boundary of a pollution core area by grid division of the pollution area and extraction of the highest concentration interval node; a path analysis module that generates pollution diffusion flow lines by adjacent node data comparison based on secondary grid division, water flow velocity, direction and a pollution concentration correction algorithm; and a source positioning module that locates pollution sources according to flow line direction, intersection density and divergence width and dynamically dispatches the unmanned ship for detection. Through the collaborative analysis of the modules, the system realizes the rapid identification of a pollution area, dynamic tracking of a diffusion path and automatic positioning of a pollution source, and improves the efficiency of marine environment monitoring and the response capability of pollution control.

Description

Technical Field

[0001] This invention relates to the field of marine ecological environment protection, and specifically to an automatic monitoring and analysis system for the marine ecological environment based on intelligent unmanned vessels. Background Technology

[0002] With the intensification of global climate change and the increasing frequency of human activities, the marine ecological environment is under unprecedented pressure. The stability of marine ecosystems is crucial for global climate regulation, biodiversity conservation, and the sustainable development of human society. However, the marine ecological environment currently faces numerous problems such as marine pollution, biodiversity loss, and ocean acidification. Accurate and timely monitoring of the marine ecological environment is essential for formulating effective protection and governance measures.

[0003] Traditional methods for monitoring the marine ecological environment mainly include manual sampling and buoy monitoring. However, buoy monitoring cannot dynamically track pollution sources, resulting in low source tracing efficiency and delayed emergency response; while manual patrols cannot quickly locate pollution leak sources, leading to an expansion of the polluted area and a surge in cleanup costs. Summary of the Invention

[0004] To address the aforementioned problems, this invention proposes an automatic monitoring and analysis system for the marine ecological environment based on intelligent unmanned vessels, thereby enabling the protection of the marine ecological environment.

[0005] The technical solution adopted by the present invention to solve its technical problem is as follows: The present invention provides an automatic monitoring and analysis system for marine ecological environment based on intelligent unmanned vessels, including a pollution identification module, a boundary construction module, a path analysis module and a source location module, and each module is interconnected through a wireless communication network.

[0006] The pollution identification module monitors the pollution concentration data of the target sea area in real time through unmanned vessels, and identifies and marks the polluted areas based on preset pollution concentration thresholds.

[0007] The boundary construction module divides the polluted area into grids and collects the pollution concentration of each grid node in real time. Based on the maximum and minimum values ​​of the pollution concentration, it divides the area into several concentration intervals and records the line connecting the grid nodes corresponding to the highest concentration interval as the boundary line of the core pollution area.

[0008] The path analysis module performs secondary grid division of the core pollution area and detects the pollution concentration, water flow velocity and direction of each grid node. Based on the comparison of detection data of adjacent grid nodes, it generates several pollution diffusion flow lines.

[0009] The source location module initially locates pollution sources based on the direction and density of pollution diffusion streams, and dynamically allocates unmanned vessels for detection.

[0010] Compared with existing technologies, the marine ecological environment automatic monitoring and analysis system based on intelligent unmanned vessels described in this invention has the following beneficial effects: 1. Accurately defining the core pollution area: This invention, through grid division and concentration interval division, selects grid nodes of the highest concentration interval and constructs closed boundary lines, which can accurately identify the range of the core pollution area, avoid the boundary ambiguity problem caused by data dispersion in traditional monitoring, and provide a reliable spatial basis for pollution diffusion analysis.

[0011] 2. Dynamically track pollution diffusion paths: This invention generates pollution diffusion streamlines by combining secondary grid division with water flow velocity, direction and pollution concentration correction algorithms. It can dynamically simulate the diffusion trend of pollutants and predict their possible impact range, providing a scientific basis for formulating targeted prevention and control strategies.

[0012] 3. Efficiently locate pollution sources: By analyzing the direction, convergence density, and divergence of pollution diffusion streams, and combining them with a priority evaluation algorithm, this invention can quickly locate multiple potential pollution source areas and dynamically allocate unmanned surface vessel detection, thereby improving the efficiency and accuracy of pollution source location and reducing resource waste. Attached Figure Description

[0013] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying 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.

[0014] Figure 1 This is a system module connection diagram of the present invention.

[0015] Figure 2 This is a schematic diagram illustrating the construction of the pollution core area boundary according to the present invention.

[0016] Figure 3 This is a schematic diagram of the pollution diffusion flow lines for different pollution sources according to the present invention.

[0017] Attached diagram labels: 1. Grid node for low concentration zone; 2. Grid node for high concentration zone; 3. Boundary line of the pollution core area; 4. Pollution core area. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] Please see Figure 1 As shown, the present invention provides an automatic monitoring and analysis system for marine ecological environment based on intelligent unmanned vessels, including a pollution identification module, a boundary construction module, a path analysis module, and a source location module.

[0020] The boundary construction module is connected to the pollution identification module and the path analysis module, respectively, and the source location module is connected to the path analysis module.

[0021] The pollution identification module monitors the pollution concentration data of the target sea area in real time through unmanned vessels, and identifies and marks the polluted area based on a preset pollution concentration threshold.

[0022] Furthermore, the specific working process of the pollution identification module includes: dividing the target sea area into regions and setting up several monitoring points within the regions; planning the inspection route of the unmanned vessel based on the distribution of the monitoring points; monitoring the pollution concentration data of each monitoring point in the target sea area in real time during the inspection process using the water quality detection sensors carried by the unmanned vessel; and performing spatiotemporal alignment processing on the pollution concentration data in conjunction with the geographical location of the monitoring points and the data acquisition time to generate a three-dimensional pollution feature matrix of the monitoring points.

[0023] It should be noted that the generated three-dimensional pollution feature matrix of each monitoring point within the target sea area will be sent to the remote monitoring terminal in real time. The three-dimensional pollution feature matrix can help track pollution sources or identify pollution propagation paths, analyze long-term trends or periodic fluctuations in pollution concentration to provide a data basis for predicting pollution events, and analyze data redundancy or blind spots at monitoring points to dynamically adjust the unmanned vessel inspection route and improve monitoring efficiency.

[0024] Furthermore, the specific working process of the pollution identification module also includes: comparing the pollution concentration data of each monitoring point in the target sea area with the preset pollution concentration threshold, obtaining the area where the monitoring point with the pollution concentration exceeds the threshold, splicing them together to obtain the pollution area, and marking it.

[0025] The boundary construction module divides the polluted area into grids and collects the pollution concentration of each grid node in real time. Based on the maximum and minimum values ​​of the pollution concentration, it divides the area into several concentration intervals and records the line connecting the grid nodes corresponding to the highest concentration interval as the boundary line of the pollution core area.

[0026] Furthermore, the specific working process of the boundary construction module includes: dividing the polluted area into grids and collecting the pollution concentration of each grid node in real time; obtaining the maximum and minimum values ​​of the pollution concentration through numerical comparison and forming the range of pollution concentration; and further dividing the range of pollution concentration according to the set principles to obtain several concentration intervals.

[0027] It should be noted that, based on actual needs or statistical rules such as equal intervals, quantiles, and cluster analysis, the range of pollution concentrations, which consists of the maximum and minimum values, is divided into several continuous intervals.

[0028] Furthermore, the specific working process of the boundary construction module also includes: (See below) Figure 2 As shown, grid nodes with pollution concentrations within the highest concentration range are selected, and connected regions formed by these grid nodes are obtained. The outer grid nodes of the connected regions are then obtained and connected in spatial order to form a closed polygon, thus forming the boundary line of the pollution core area.

[0029] As a preferred approach, connectivity detection is used to determine whether grid nodes with pollution concentrations within the highest concentration range constitute a connected region. If they are dispersed into multiple independent connected regions, they are processed separately.

[0030] It should be noted that the outer grid nodes of the connected region refer to the nodes adjacent to the areas where the grid nodes in the low pollution concentration range are located.

[0031] It should be noted that this invention, through gridding and concentration range division, filters the grid nodes of the highest concentration range and constructs closed boundary lines, which can accurately identify the scope of the pollution core area, avoid the boundary ambiguity problem caused by data dispersion in traditional monitoring, and provide a reliable spatial basis for pollution diffusion analysis.

[0032] The path analysis module performs secondary grid division of the core pollution area and detects the pollution concentration, water flow velocity and direction of each grid node. Based on the comparison of detection data of adjacent grid nodes, it generates several pollution diffusion flow lines.

[0033] Furthermore, the specific working process of the path analysis module is as follows: S1: Divide the core pollution area into secondary grids and detect the pollution concentration, water flow velocity and direction of each grid node.

[0034] S2: Obtain the pollution concentration and water flow velocity of each grid node adjacent to the outer grid node in the pollution core area. If the deviation of the water flow velocity between the outer grid node and its adjacent grid nodes is within the set range, then execute S3. If the deviation of the water flow velocity between the outer grid node and its adjacent grid nodes exceeds the set range, then execute S4.

[0035] S3: Directly compare the pollution concentration of the outer grid node with the pollution concentration of its neighboring grid nodes, count the neighboring grid nodes whose pollution concentration is higher than that of the outer grid node, and record them as the suspected superior nodes of the outer grid node.

[0036] S4: Using the water flow velocity of the outer grid nodes as a benchmark, analyze the reference pollution concentration of each adjacent grid node at the benchmark water flow velocity to correct the pollution concentration of each adjacent grid node. Compare the corrected pollution concentration of each adjacent grid node with the pollution concentration of the outer grid nodes. Count the adjacent grid nodes with pollution concentrations higher than those of the outer grid nodes and record them as the suspected superior nodes of the outer grid nodes.

[0037] S5: Determine the superior nodes of the outer grid nodes based on the water flow direction of each suspected superior node, and count the superior nodes of each outer grid node.

[0038] S6: Similarly, according to the analysis steps of S2-S5, obtain the higher-level nodes of the higher-level nodes of each peripheral grid node, and so on.

[0039] S7: Connect each peripheral grid node to its corresponding superior node in sequence to obtain each pollution diffusion streamline, and the direction of the pollution diffusion streamline is from the center to the periphery.

[0040] It should be noted that the grid-based division of the core pollution area is more detailed than the grid-based division of the pollution zone.

[0041] It should be noted that the method for detecting the pollution concentration at each grid node within the core pollution area is based on the same principle as the method for detecting the pollution concentration at each grid node within the pollution area.

[0042] This invention, through grid-based division and multi-level node analysis technology, can improve the sensitivity to minute changes in pollution concentration while ensuring monitoring efficiency, which helps to detect early signs of pollution and prevent the expansion of ecological disasters.

[0043] Further, the specific process of correcting the pollution concentration of each adjacent grid node in step S4 is as follows: the water flow velocity of the outer grid node and the pollution concentration and water flow velocity of each grid node adjacent to the outer grid node are respectively denoted as... and , Indicates the adjacent first The number of each grid node, .

[0044] By analyzing the formula Obtain the correction amount of pollution concentration for each adjacent grid node. ,in This indicates the change in pollution concentration corresponding to a preset unit change in water flow velocity.

[0045] The pollution concentration of each adjacent grid node and its correction amount Substitute into the calculation formula Obtain the reference pollution concentration at each adjacent grid node under the reference water flow velocity. .

[0046] As a preferred approach, obtaining the change in pollutant concentration corresponding to a unit change in water flow velocity can be achieved by experimentally establishing the relationship between concentration and flow velocity and calculating its derivative. The specific operational procedure is as follows: Step 1: Keep pollutant discharge, temperature, water body cross-sectional area, and other factors constant; Step 2: Measure the corresponding pollutant concentration at different water flow velocities to obtain multiple sets of data points; Step 3: Determine the functional relationship between pollutant concentration and water flow velocity through regression analysis; Step 4: Differentiate the fitted function to obtain the change in concentration corresponding to a unit change in flow velocity.

[0047] It should be noted that water flow velocity affects the detection results of pollution concentration. Excessive flow velocity will result in an underestimation of the pollution concentration, while excessively slow flow velocity will result in an overestimation. Therefore, when comparing the pollution concentration between an outer grid node and its neighboring grid nodes, if the difference in flow velocity between the outer grid node and its neighboring grid nodes is too large, the pollution concentration detection results need to be corrected and compared based on the corrected results. This ensures that comparisons of pollution concentrations are performed at the same flow velocity to reduce errors.

[0048] Furthermore, the specific process of determining the superior node of the outer grid node based on the water flow direction of each suspected superior node in step S5 is as follows: obtain the water flow direction of each suspected superior node, obtain the direction from each suspected superior node to the outer grid node according to the position of each suspected superior node and the outer grid node, and if the direction from a certain suspected superior node to the outer grid node is in the same direction as the water flow direction of the suspected superior node, then the suspected superior node is recorded as the superior node of the outer grid node.

[0049] It should be noted that this invention generates pollution diffusion streamlines by combining secondary grid division with water flow velocity, direction and pollution concentration correction algorithms. This can dynamically simulate the diffusion trend of pollutants and predict their possible impact range, providing a scientific basis for formulating targeted prevention and control strategies.

[0050] The source location module initially locates the pollution source based on the direction and density of the pollution diffusion streamline, and dynamically allocates unmanned vessels for detection.

[0051] Furthermore, the specific working process of the source location module includes: (See below) Figure 3 As shown, the direction of each pollution diffusion flow line in the core pollution area is obtained, and it is determined whether the pollution diffusion flow lines belong to the same pollution source and classified. Furthermore, the area where the intersection density of pollution diffusion flow lines exceeds a set threshold is marked as the pollution source area, and the pollution source areas are statistically analyzed.

[0052] It should be noted that pollution diffusion lines corresponding to the same pollution source radiate outward from the same point, and the angle between adjacent pollution diffusion lines is acute; pollution diffusion lines corresponding to different pollution sources radiate outward from different points, and the angle between adjacent pollution diffusion lines is obtuse. Based on the above rules, the direction of each pollution diffusion line within the pollution core area is combined to determine whether the pollution diffusion lines belong to the same pollution source and classify them accordingly.

[0053] Furthermore, the specific working process of the source location module also includes: obtaining the dispersion breadth of pollution diffusion streamlines and the pollution concentration decay rate of each pollution source area, and combining the convergence density of pollution diffusion streamlines in each pollution source area to assess the priority of each pollution source area, and dynamically allocating unmanned vessels for detection.

[0054] As a preferred approach, the specific method for obtaining the dispersion extent of pollution diffusion streamlines in the pollution source area is as follows: The pollution source area is divided into quadrants according to a preset principle; the ratio between the number of pollution diffusion streamlines in each quadrant is obtained; and the ratio is substituted into a preset pollution diffusion streamline dispersion extent analysis model to obtain the dispersion extent of pollution diffusion streamlines in the pollution source area. The pollution diffusion streamline dispersion extent analysis model includes a quantitative mapping relationship between the ratio between the number of pollution diffusion streamlines in each quadrant and the dispersion extent of pollution diffusion streamlines.

[0055] As a preferred approach, the specific method for obtaining the pollution concentration decay rate in the pollution source area is as follows: obtain the pollution concentration decay amount per unit distance along the flow direction of each pollution diffusion streamline in the pollution source area and record it as the pollution concentration decay rate of each pollution diffusion streamline; calculate the pollution concentration decay rate of the pollution source area by taking the mean or mode of the pollution concentration decay rate of each pollution diffusion streamline.

[0056] As a preferred approach, a specific method for assessing the priority of pollution source areas is through analysis of formulas. Obtain the priority coefficient of the pollution source area ,in These represent the dispersion extent of pollution diffusion streamlines, the rate of pollution concentration decay, and the convergence density of pollution diffusion streamlines in the pollution source area, respectively. and The mean values ​​and weights of the pollution diffusion streamline divergence, pollution concentration decay rate, and pollution diffusion streamline convergence density are respectively represented. The priority coefficient of the pollution source area is substituted into the mapping relationship between the priority coefficient and the priority to obtain the priority of the pollution source area.

[0057] It should be noted that when setting the weights for the dispersion extent of pollution diffusion streamlines, the rate of pollution concentration decay, and the convergence density of pollution diffusion streamlines, historical data or experimental data are used to quantify the relative importance of each parameter through methods such as regression analysis and principal component analysis, and then the weights are assigned.

[0058] It should be noted that inspection resources are dynamically allocated based on the priority of pollution source areas. In one specific embodiment, when the number of unmanned surface vessels (USVs) is limited, USVs are first assigned to high-priority pollution source areas for detection. In another specific embodiment, high-precision detection USVs are assigned to high-priority pollution source areas, while rapid inspection USVs are assigned to low-priority pollution source areas. The high-precision detection USVs perform spiral progressive sampling along the main direction of pollution diffusion and update the three-dimensional pollution feature matrix in real time, while the rapid inspection USVs perform fan-shaped scanning. If a sudden increase in pollution concentration is detected, the source tracing mode is triggered.

[0059] It should be noted that by analyzing the direction, convergence density, and divergence of pollution diffusion streamlines, and combining them with a priority evaluation algorithm, this invention can quickly locate multiple potential pollution source areas and dynamically allocate unmanned surface vessel detection, thereby improving the efficiency and accuracy of pollution source location and reducing resource waste.

[0060] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0061] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, in the form of a computer program product.

[0062] Those skilled in the art will recognize that the modules and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0063] In addition, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0064] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0065] Finally, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. An automatic monitoring and analysis system for marine ecological environment based on intelligent unmanned vessels, characterized in that, include: The pollution identification module monitors pollution concentration data of the target sea area in real time through unmanned vessels, and identifies and marks polluted areas based on preset pollution concentration thresholds; The boundary construction module divides the polluted area into grids and collects the pollution concentration of each grid node in real time. Based on the maximum and minimum values ​​of the pollution concentration, it divides the area into several concentration intervals and records the line connecting the grid nodes corresponding to the highest concentration interval as the boundary line of the pollution core area. The path analysis module performs secondary grid division of the core pollution area and detects the pollution concentration, water flow velocity and direction of each grid node. Based on the comparison of detection data of adjacent grid nodes, it generates several pollution diffusion flow lines. The specific working process of the path analysis module is as follows: S1: Perform secondary grid division on the core pollution area and detect the pollution concentration, water flow velocity, and direction of each grid node; S2: Obtain the pollution concentration and water flow velocity of each grid node adjacent to the outer grid node in the core pollution area. If the deviation of the water flow velocity between the outer grid node and its adjacent grid nodes is within the set range, then execute S3. If the deviation of the water flow velocity between the outer grid node and its adjacent grid nodes exceeds the set range, then execute S4; S3: Directly compare the pollution concentration of the outer grid node with the pollution concentration of its adjacent grid nodes, count the adjacent grid nodes with pollution concentrations higher than the outer grid node, and record them as the suspected superior nodes of the outer grid node; S4: Using the water flow velocity of the outer grid nodes as a benchmark, analyze the reference pollution concentration of each adjacent grid node at the benchmark water flow velocity to correct the pollution concentration of each adjacent grid node. Compare the corrected pollution concentration of each adjacent grid node with the pollution concentration of the outer grid nodes, and count the adjacent grid nodes with pollution concentrations higher than those of the outer grid nodes. Record these as the suspected superior nodes of the outer grid nodes. S5: Determine the superior nodes of the outer grid nodes based on the water flow direction of each suspected superior node, and count the superior nodes of each outer grid node. S6: Similarly, obtain the superior nodes of each superior node of the outer grid nodes according to the analysis steps of S2-S5, and so on. S7: Connect each outer grid node and its corresponding superior nodes at each level in sequence to obtain each pollution diffusion streamline, and the direction of the pollution diffusion streamline is from the center to the periphery. The source location module initially locates pollution sources based on the direction and density of pollution diffusion streamlines, and dynamically allocates unmanned vessels for detection; The specific working process of the source location module includes: obtaining the direction of each pollution diffusion flow line in the core pollution area, determining whether the pollution diffusion flow lines belong to the same pollution source and classifying them, further marking the area where the intersection density of pollution diffusion flow lines exceeds a set threshold as the pollution source area, and statistically analyzing each pollution source area.

2. The marine ecological environment automatic monitoring and analysis system based on intelligent unmanned vessels according to claim 1, characterized in that: The specific working process of the pollution identification module includes: The target sea area is divided into regions and several monitoring points are set up within the regions. Based on the distribution of the monitoring points, the inspection route of the unmanned vessel is planned. During the inspection, the water quality detection sensors carried by the unmanned vessel monitor the pollution concentration data of each monitoring point in the target sea area in real time. The pollution concentration data is then spatiotemporally aligned by combining the geographical location of the monitoring points and the data acquisition time to generate a three-dimensional pollution feature matrix of the monitoring points.

3. The marine ecological environment automatic monitoring and analysis system based on intelligent unmanned vessels according to claim 2, characterized in that: The specific working process of the pollution identification module also includes: The pollution concentration data of each monitoring point in the target sea area is compared with the preset pollution concentration threshold. The areas where the pollution concentration exceeds the threshold are located are obtained, and the polluted areas are obtained by splicing them together and marking them.

4. The marine ecological environment automatic monitoring and analysis system based on intelligent unmanned vessels according to claim 1, characterized in that: The specific working process of the boundary construction module includes: The polluted area is divided into grids and the pollution concentration of each grid node is collected in real time. The maximum and minimum values ​​of the pollution concentration are obtained by numerical comparison, which constitute the range of pollution concentration. The range of pollution concentration is further divided into several concentration intervals according to the set principles.

5. The marine ecological environment automatic monitoring and analysis system based on intelligent unmanned vessels according to claim 1, characterized in that: The specific working process of the boundary construction module also includes: Grid nodes with pollution concentrations within the highest concentration range are selected and connected regions formed by these grid nodes are obtained. The outer grid nodes of the connected regions are then obtained and connected in spatial order to form a closed polygon, thus forming the boundary line of the pollution core area.

6. The marine ecological environment automatic monitoring and analysis system based on intelligent unmanned vessels according to claim 5, characterized in that: The specific process of correcting the pollution concentration of each adjacent grid node in step S4 is as follows: The water flow velocity at the outer grid node and the pollution concentration and water flow velocity at each adjacent grid node are respectively denoted as: and , Indicates the adjacent first The number of each grid node, ; By analyzing the formula Obtain the correction amount of pollution concentration for each adjacent grid node. ,in This indicates the change in pollution concentration corresponding to a preset unit change in water flow velocity; The pollution concentration of each adjacent grid node and its correction amount Substitute into the calculation formula Obtain the reference pollution concentration at each adjacent grid node under the reference water flow velocity. .

7. The marine ecological environment automatic monitoring and analysis system based on intelligent unmanned vessels according to claim 5, characterized in that: The specific process of determining the superior node of the outer grid node based on the water flow direction of each suspected superior node in step S5 is as follows: Obtain the water flow direction of each suspected superior node. Based on the positions of each suspected superior node and the outer grid node, obtain the direction from each suspected superior node to the outer grid node. If the direction from a suspected superior node to the outer grid node is in the same direction as the water flow direction of the suspected superior node, then record the suspected superior node as the superior node of the outer grid node.

8. The marine ecological environment automatic monitoring and analysis system based on intelligent unmanned vessels according to claim 1, characterized in that: The specific working process of the source location module also includes: The system acquires the dispersion extent of pollution diffusion streamlines and the rate of pollution concentration decay in each pollution source area. Combined with the convergence density of pollution diffusion streamlines in each pollution source area, the system assesses the priority of each pollution source area and dynamically allocates unmanned surface vessels for detection.

Images