Autonomous water quality monitoring unmanned ship navigation control method and system based on multimode communication

Abstract

The invention relates to the field of unmanned ship path planning, in particular to an autonomous water quality monitoring unmanned ship navigation control method and system based on multimode communication. The method comprises the following steps: collecting regional water quality monitoring parameters based on a shipborne water quality monitoring sensor, carrying out space pollution distribution excavation, and constructing a regional pollution concentration distribution diagram; obtaining a regional satellite remote sensing map, carrying out water flow distribution dynamic evolution, and constructing a water flow path distribution network; carrying out pollutant migration logic evolution and multi-region gradient diffusion prediction on the water flow path distribution network according to the regional pollution concentration distribution map, and constructing a water quality pollution diffusion prediction situation map; and according to the water quality pollution diffusion prediction situation map, carrying out highest diffusion progressive gradient identification, carrying out optimal navigation monitoring sequence analysis, and constructing an optimal navigation monitoring sequence. According to the invention, through dynamic and real-time unmanned ship water quality cruise path adjustment, the accuracy and efficiency of water quality monitoring are improved.

Description

Technical Field

[0001] The present invention relates to the field of unmanned vessel path planning, and in particular to a navigation control method and system for an autonomous water quality monitoring unmanned vessel based on multi-mode communication. Background Art

[0002] With the growing severity of global environmental pollution, water pollution has become a significant factor constraining the ecological environment and human health. Water pollution not only affects the safety of drinking water sources but also has a profound impact on the survival of aquatic organisms, the balance of ecosystems, and the sustainable development of economic activities. Traditional water quality monitoring methods rely primarily on manual sampling and on-site analysis. This approach suffers from long sampling cycles, limited coverage, and slow response times, making it difficult to meet the needs of large-scale, real-time, and high-frequency water quality monitoring. With the continuous advancement of science and technology, especially the rapid development of unmanned and intelligent control technologies, autonomous water quality monitoring technology has gradually become an important means of solving water quality monitoring challenges.

[0003] As a new type of water quality monitoring equipment, autonomous water quality monitoring unmanned boats offer high efficiency, accuracy, and flexibility. They can navigate autonomously and are equipped with water quality sensors to monitor water quality in real time, avoiding the limitations of traditional manual monitoring and enabling continuous and comprehensive monitoring of water pollution. However, the complexity of water pollution and the variability of aquatic environments place higher demands on the navigation and control systems of unmanned boats. Unmanned boats must be able to autonomously navigate complex aquatic environments and perform precise navigation control based on the distribution of water pollution concentrations to achieve efficient and accurate tracking and monitoring of water pollution.

[0004] Currently, research on unmanned vessel navigation and control methods mostly focuses on technologies such as autonomous obstacle avoidance and path planning. However, research on unmanned vessel navigation and control methods based on water pollution concentration tracking is still in its infancy. In practical applications, due to the extremely uneven spatial distribution of water pollution concentration and the influence of environmental factors such as water flow and wind, how to intelligently guide the navigation of unmanned vessels based on the concentration distribution of water pollution and optimize the navigation path while monitoring in real time has become a difficult problem that needs to be solved. In addition, due to the real-time changes in water pollution concentration, how to timely adjust the navigation path through precise navigation control to ensure that the unmanned vessel can effectively cover the polluted area and thereby improve monitoring efficiency and accuracy is also a key research direction. Summary of the Invention

[0005] In order to solve the above technical problems, the present invention proposes a navigation control method and system for an autonomous water quality monitoring unmanned vessel based on multi-mode communication to solve at least one of the above technical problems.

[0006] To achieve the above objectives, the present invention provides a navigation control method for an autonomous water quality monitoring unmanned vessel based on multi-mode communication, wherein the unmanned vessel is equipped with an onboard water quality monitoring sensor and a multi-mode communication module; the method comprises the following steps:

[0007] Step S1: Collect regional water quality monitoring parameters based on shipborne water quality monitoring sensors, conduct spatial pollution distribution mining, and construct a regional pollution concentration distribution map;

[0008] Step S2: Obtain regional satellite remote sensing maps, perform dynamic evolution of water flow distribution, and construct a water flow path distribution network;

[0009] Step S3: Based on the regional pollution concentration distribution map, the pollutant migration logic evolution and multi-region gradient diffusion prediction of the water flow path distribution network are carried out to construct a water pollution diffusion prediction situation map;

[0010] Step S4: Identify the highest diffusion gradient according to the water pollution diffusion prediction situation map, analyze the optimal navigation monitoring sequence, and construct the optimal navigation monitoring sequence;

[0011] Step S5: planning a pollution source coverage cruise path according to the optimal navigation monitoring sequence, performing dynamic navigation cruise monitoring, and collecting full-process cruise monitoring data;

[0012] Step S6: Based on the full-process cruise monitoring data, conduct real-time cruise concentration distribution change analysis and dynamic path adjustment to build an intelligent pollution source tracing and positioning model.

[0013] This invention uses onboard water quality monitoring sensors to collect multiple water quality parameters (such as dissolved oxygen, ammonia nitrogen, and pH) in real time, providing an accurate data foundation for water quality assessment. Using data mining and spatial analysis techniques, the unmanned vessel can monitor and identify the spatial distribution of pollution in real time. This distribution map clearly displays pollution hotspots, helping to determine the location and spread of pollution sources in real time. Using the unmanned vessel's multi-mode communication system, water quality data is uploaded to the cloud in real time. Different communication networks (such as 4G / 5G and satellite) ensure stable data transmission in different environments, ensuring the accuracy and timeliness of information. The integration of high-resolution satellite remote sensing images with data from water quality monitoring sensors enables comprehensive environmental information about the water area, including important dynamic factors such as water flow direction and velocity. Using a hydrodynamic model, the evolution of water flow can be simulated, accurately depicting the water flow path network. This allows the unmanned vessel to better understand the flow direction and velocity of the water area, providing a basis for subsequent route planning and pollution prediction. Constructing a water flow path distribution network provides a comprehensive understanding of water flow dynamics, optimizes the unmanned vessel's navigation path in complex waters, and ensures accurate pollutant monitoring. Based on water flow paths and pollution concentration distribution maps, unmanned vessels can predict pollutant diffusion trends in real time. The system dynamically analyzes the migration of pollutants along the water flow to accurately predict their future locations and concentrations. It simulates pollution gradients across multiple areas within a water body to analyze regional differences in pollution diffusion. This diffusion trend map helps assess the potential impact of pollutants on individual water bodies, ensuring comprehensive monitoring and prevention. By predicting pollution diffusion, the potential impact areas of pollutants can be identified in advance, preventing further escalation of pollution incidents. Multi-mode communication ensures that diffusion prediction results are fed back to the command center or other unmanned vessels in real time, forming an efficient decision-making and emergency response mechanism. By analyzing the diffusion trend map, the system can identify areas with the largest pollution diffusion gradients and prioritize monitoring areas with the fastest and most severe pollution migration. This analysis ensures efficient and targeted monitoring. Based on pollution diffusion and water flow paths, the system uses intelligent algorithms (such as reinforcement learning and genetic algorithms) to optimize the unmanned vessel's monitoring route, ensuring that pollution sources are covered as early as possible and maximizing patrol monitoring efficiency. Multi-mode communication technology ensures real-time data synchronization between unmanned vessels and other monitoring platforms. Adjustments to different routes are instantly fed back to the cloud, coordinating the actions of other unmanned vessels in the same waters to avoid duplicate monitoring or missed pollution hotspots. Based on the optimal navigation monitoring sequence, unmanned vessels can accurately cover the entire pollution source and its diffusion path, avoiding missed polluted areas. Unmanned vessels dynamically navigate according to route planning, while adaptively adjusting their routes based on real-time water quality data. For example, when rapid changes in pollution concentration in a certain area are detected, the route can be adjusted in real time to obtain more accurate pollution data. Through full real-time monitoring, unmanned vessels can collect high-frequency water quality data and upload it to the cloud, ensuring the comprehensiveness and integrity of the data. Multi-mode communication technology ensures efficient and stable data transmission.Based on real-time monitoring data, the system analyzes trends in pollution concentrations and promptly identifies pollution hotspots or areas of sudden change. It responds immediately based on the patterns of change, optimizing routes and preventing further spread of pollution. Through source tracing analysis, the system quickly locates pollution sources and their sources of spread, forming an accurate pollution source tracing model and providing precise data support for pollution source control. Based on pollution source location data and concentration trends, the system intelligently adjusts the unmanned vessel's route, making monitoring more refined and maximizing its timeliness and accuracy. Dynamic route adjustment is particularly important in responding to sudden pollution incidents.

[0014] In this specification, a multi-mode communication-based autonomous water quality monitoring unmanned vessel navigation control system is provided, which is used to execute the multi-mode communication-based autonomous water quality monitoring unmanned vessel navigation control method as described above, including:

[0015] The spatial pollution distribution module is used to collect regional water quality monitoring parameters based on ship-borne water quality monitoring sensors, conduct spatial pollution distribution mining, and construct regional pollution concentration distribution maps;

[0016] The water flow distribution evolution module is used to obtain regional satellite remote sensing maps, conduct dynamic evolution of water flow distribution, and construct a water flow path distribution network;

[0017] The diffusion prediction module is used to perform pollutant migration logic evolution and multi-region gradient diffusion prediction on the water flow path distribution network based on the regional pollution concentration distribution map, and to construct a water pollution diffusion prediction situation map;

[0018] The navigation sequence module is used to identify the highest diffusion gradient based on the water pollution diffusion prediction situation map, analyze the optimal navigation monitoring sequence, and construct the optimal navigation monitoring sequence;

[0019] The path planning module is used to plan the pollution source coverage cruise path according to the optimal navigation monitoring sequence, conduct dynamic navigation cruise monitoring, and collect full-process cruise monitoring data;

[0020] The path adjustment module is used to conduct real-time cruise concentration distribution change analysis and dynamic path adjustment based on the full-process cruise monitoring data, and to build an intelligent pollution source tracing and positioning model.

[0021] This invention uses onboard sensors to collect various water quality data in real time, enabling rapid location of pollution hotspots and ensuring timely detection of pollution issues within water bodies. The construction of spatial pollution distribution maps clearly displays pollution concentrations in different regions, providing crucial data support for subsequent water flow and pollution diffusion analysis. Data mining techniques can effectively extract pollution information from large amounts of data, enabling efficient pollution monitoring and control. Using satellite remote sensing maps and water flow evolution models, unmanned vessels can obtain dynamic water flow evolution information, including flow velocity and direction, providing a foundation for path planning and pollution diffusion prediction. The establishment of a water flow path distribution network helps understand the propagation path of water within a water body, making subsequent path planning more accurate and avoiding monitoring errors caused by changes in water flow direction. Predicting the migration and evolution of pollutants enables the path and speed of pollution diffusion to be identified in advance, facilitating the timely development of countermeasures. Multi-region gradient diffusion prediction can assess pollution diffusion in different regions, helping to determine the potential impact range of pollution and providing an accurate basis for subsequent monitoring and control. Based on diffusion prediction situation maps, early warning can be achieved, preventing the spread of pollution and reducing the difficulty and cost of pollution control. By analyzing the optimal navigation and monitoring sequence, unmanned vessels prioritize monitoring in areas with the most severe pollution spread, improving the overall efficiency of water quality monitoring. Optimizing the navigation sequence avoids duplicate monitoring or missed detection of polluted areas, thereby increasing the coverage and accuracy of water quality monitoring. Multiple unmanned vessels can work together according to the optimized navigation and monitoring sequence to avoid conflicts and enhance the efficiency of the entire monitoring system. The path planning module enables unmanned vessels to accurately cover pollution sources, ensuring comprehensive monitoring and data collection. Path planning allows unmanned vessels to avoid unnecessary route duplication and time waste, thereby improving monitoring efficiency and saving energy. Dynamic navigation allows unmanned vessels to flexibly adjust their navigation paths based on real-time conditions (such as water flow changes and sudden pollution incidents), ensuring efficient completion of monitoring tasks. By analyzing changes in cruising concentrations in real time, the system can quickly respond to sudden changes in water quality and adjust its path in a timely manner, ensuring the effective tracking and location of pollution sources. Dynamic path adjustment optimizes the unmanned vessel's monitoring path in real time based on changes in pollution concentration, enabling accurate tracing and location of pollution sources. Path adjustment allows unmanned vessels to adjust their cruising paths based on environmental and pollutant changes, achieving continuous and efficient monitoring and avoiding limitations in path design. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 This is a schematic flow chart of the steps of a navigation control method for an autonomous water quality monitoring unmanned vessel with multi-mode communication according to the present invention;

[0023] Figure 2 Detailed implementation flow chart of step S1;

[0024] Figure 3 Detailed implementation flow chart of step S2;

[0025] Figure 4 Schematic diagram of the detailed implementation steps of step S3. DETAILED DESCRIPTION

[0026] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0027] This application example provides a multi-mode communication autonomous water quality monitoring unmanned vessel navigation control method and system. The execution subjects of the multi-mode communication autonomous water quality monitoring unmanned vessel navigation control method and system include but are not limited to: mechanical equipment, data processing platform, cloud server node, network upload device, etc. equipped with the system, which can be regarded as the general computing nodes of this application. The data processing platform includes but is not limited to: at least one of an audio and image management system, an information management system, and a cloud data management system.

[0028] See also Figures 1 to 4 The present invention provides a navigation control method for an autonomous water quality monitoring unmanned vessel based on multimode communication, the navigation control method for an autonomous water quality monitoring unmanned vessel based on multimode communication comprising the following steps:

[0029] Step S1: Collect regional water quality monitoring parameters based on shipborne water quality monitoring sensors, conduct spatial pollution distribution mining, and construct a regional pollution concentration distribution map;

[0030] Step S2: Obtain regional satellite remote sensing maps, perform dynamic evolution of water flow distribution, and construct a water flow path distribution network;

[0031] Step S3: Based on the regional pollution concentration distribution map, the pollutant migration logic evolution and multi-region gradient diffusion prediction of the water flow path distribution network are carried out to construct a water pollution diffusion prediction situation map;

[0032] Step S4: Identify the highest diffusion gradient according to the water pollution diffusion prediction situation map, analyze the optimal navigation monitoring sequence, and construct the optimal navigation monitoring sequence;

[0033] Step S5: planning a pollution source coverage cruise path according to the optimal navigation monitoring sequence, performing dynamic navigation cruise monitoring, and collecting full-process cruise monitoring data;

[0034] Step S6: Based on the full-process cruise monitoring data, conduct real-time cruise concentration distribution change analysis and dynamic path adjustment to build an intelligent pollution source tracing and positioning model.

[0035] This invention uses onboard water quality monitoring sensors to collect multiple water quality parameters (such as dissolved oxygen, ammonia nitrogen, and pH) in real time, providing an accurate data foundation for water quality assessment. Using data mining and spatial analysis techniques, the unmanned vessel can monitor and identify the spatial distribution of pollution in real time. This distribution map clearly displays pollution hotspots, helping to determine the location and spread of pollution sources in real time. Using the unmanned vessel's multi-mode communication system, water quality data is uploaded to the cloud in real time. Different communication networks (such as 4G / 5G and satellite) ensure stable data transmission in different environments, ensuring the accuracy and timeliness of information. The integration of high-resolution satellite remote sensing images with data from water quality monitoring sensors enables comprehensive environmental information about the water area, including important dynamic factors such as water flow direction and velocity. Using a hydrodynamic model, the evolution of water flow can be simulated, accurately depicting the water flow path network. This allows the unmanned vessel to better understand the flow direction and velocity of the water area, providing a basis for subsequent route planning and pollution prediction. Constructing a water flow path distribution network provides a comprehensive understanding of water flow dynamics, optimizes the unmanned vessel's navigation path in complex waters, and ensures accurate pollutant monitoring. Based on water flow paths and pollution concentration distribution maps, unmanned vessels can predict pollutant diffusion trends in real time. The system dynamically analyzes the migration of pollutants along the water flow to accurately predict their future locations and concentrations. It simulates pollution gradients across multiple areas within a water body to analyze regional differences in pollution diffusion. This diffusion trend map helps assess the potential impact of pollutants on individual water bodies, ensuring comprehensive monitoring and prevention. By predicting pollution diffusion, the potential impact areas of pollutants can be identified in advance, preventing further escalation of pollution incidents. Multi-mode communication ensures that diffusion prediction results are fed back to the command center or other unmanned vessels in real time, forming an efficient decision-making and emergency response mechanism. By analyzing the diffusion trend map, the system can identify areas with the largest pollution diffusion gradients and prioritize monitoring areas with the fastest and most severe pollution migration. This analysis ensures efficient and targeted monitoring. Based on pollution diffusion and water flow paths, the system uses intelligent algorithms (such as reinforcement learning and genetic algorithms) to optimize the unmanned vessel's monitoring route, ensuring that pollution sources are covered as early as possible and maximizing patrol monitoring efficiency. Multi-mode communication technology ensures real-time data synchronization between unmanned vessels and other monitoring platforms. Adjustments to different routes are instantly fed back to the cloud, coordinating the actions of other unmanned vessels in the same waters to avoid duplicate monitoring or missed pollution hotspots. Based on the optimal navigation monitoring sequence, unmanned vessels can accurately cover the entire pollution source and its diffusion path, avoiding missed polluted areas. Unmanned vessels dynamically navigate according to route planning, while adaptively adjusting their routes based on real-time water quality data. For example, when rapid changes in pollution concentration in a certain area are detected, the route can be adjusted in real time to obtain more accurate pollution data. Through full real-time monitoring, unmanned vessels can collect high-frequency water quality data and upload it to the cloud, ensuring the comprehensiveness and integrity of the data. Multi-mode communication technology ensures efficient and stable data transmission.Based on real-time monitoring data, the system analyzes trends in pollution concentrations and promptly identifies pollution hotspots or areas of sudden change. It responds immediately based on the patterns of change, optimizing routes and preventing further spread of pollution. Through source tracing analysis, the system quickly locates pollution sources and their sources of spread, forming an accurate pollution source tracing model and providing precise data support for pollution source control. Based on pollution source location data and concentration trends, the system intelligently adjusts the unmanned vessel's route, making monitoring more refined and maximizing its timeliness and accuracy. Dynamic route adjustment is particularly important in responding to sudden pollution incidents.

[0036] In the embodiment of the present invention, see Figure 1 , is a flowchart of the steps of a navigation control method for an autonomous water quality monitoring unmanned vessel based on multimode communication of the present invention. In this example, the steps of the navigation control method for an autonomous water quality monitoring unmanned vessel based on multimode communication include:

[0037] Step S1: Collect regional water quality monitoring parameters based on shipborne water quality monitoring sensors, conduct spatial pollution distribution mining, and construct a regional pollution concentration distribution map;

[0038] In this embodiment, first, ensure that the configuration and calibration of the onboard water quality monitoring sensors are intact. A combination of multiple sensors, such as pH sensors, turbidity sensors, dissolved oxygen sensors, and ammonia nitrogen sensors, are selected to comprehensively monitor water quality parameters. The selection of each sensor should be based on the pollution characteristics of the target area. For example, if nitrogen pollution is known to occur in the area, special attention should be paid to the accuracy of the ammonia nitrogen sensor. Before deployment, each sensor is calibrated to ensure its measurement accuracy. The calibration process includes comparing with a standard solution and adjusting the sensor output to ensure that its measured value is consistent with the standard value. The initial calibration parameters are recorded, and the stability and accuracy of the sensor are guaranteed throughout the monitoring process. When the unmanned vessel performs a navigation mission, the frequency and sample points of data collection are set. Generally speaking, it is recommended to record water quality parameters every 5 minutes and collect samples every 10 meters during navigation to ensure the timeliness of the data and the comprehensiveness of the spatial distribution. The geographic location of each sample point is recorded using the onboard GPS system, and the data collected by the sensor (such as pH value, turbidity, dissolved oxygen concentration, etc.) is combined with its corresponding longitude and latitude to form a data set with spatial coordinates. For example, during navigation, if a sensor detects a pH value of 7.5, turbidity of 15 NTU, and dissolved oxygen of 8 mg / L at a certain point, its coordinates (x, y) are recorded as (120.5, 30.2) to facilitate subsequent analysis. After completing monitoring data collection, data organization and preprocessing are performed. First, the collected data is screened to remove obvious outliers and interference data (such as sensor failure or external influences). For example, if the turbidity data at a certain measurement point suddenly changes to 100 NTU, while the values ​​at surrounding measurement points are all around 15 NTU, this data is considered an anomaly. Second, missing values ​​are processed, and interpolation methods (such as linear interpolation or kriging interpolation) are used to fill in missing values ​​to ensure the integrity of the dataset. Finally, the data format is unified, and all monitored parameters are organized into a structured data table containing timestamps, coordinates, and corresponding water quality parameter values. Using this preprocessed data, spatial pollution distribution is explored. Select a suitable spatial analysis method. Geographic Information System (GIS) technology and interpolation algorithms (such as inverse distance weighted interpolation or Kriging interpolation) are usually used to construct pollution concentration distribution maps. These methods can effectively convert discrete monitoring point data into continuous regional distribution maps. In specific implementation, first import the sorted data set into the GIS software and use the interpolation algorithm to generate a regional pollution concentration distribution map. By setting appropriate parameters (such as neighborhood range and interpolation method), the generated distribution map will show the changes in pollution concentration in different regions. For example, after interpolation, the ammonia nitrogen concentration in a certain area shows a gradual change from point A (concentration 20 mg / L) to point B (concentration 40 mg / L), forming a clear concentration gradient. Finally, use GIS software to visualize the generated regional pollution concentration distribution map, apply appropriate color gradients and legends to intuitively display areas with different concentrations.Combining concentration distribution maps with base maps identifies key water features and potential pollution sources, facilitating subsequent analysis and decision-making. During visualization, high-pollution concentration points and flow paths within the region are recorded. This information will provide crucial evidence for subsequent pollution source tracking and remediation strategies. For example, if ammonia nitrogen concentrations in a particular area are found to be significantly higher than those in surrounding areas through analysis of the distribution map, this may indicate a potential pollution source, thus providing guidance for subsequent water quality monitoring.

[0039] Step S2: Obtain regional satellite remote sensing maps, perform dynamic evolution of water flow distribution, and construct a water flow path distribution network;

[0040] In this embodiment, satellite remote sensing technology is used to obtain high-resolution satellite images of the target area from open data platforms (such as NASA, ESA or Google Earth Engine). Ensure that the spatial resolution of the image is high enough (for example, 10 meters) to clearly identify water bodies and surface features. Record the acquisition time, resolution, sensor type and other metadata of the acquired image to facilitate subsequent data analysis. For example, the acquired image is from the Sentinel-2 satellite with a resolution of 10 meters and the acquisition time is March 1, 2023. Perform necessary preprocessing on the acquired satellite remote sensing image, including geometric correction, radiation correction and atmospheric correction. Ensure that the geometric accuracy and radiation characteristics of the image meet the analysis requirements. For example, an atmospheric correction algorithm (such as the 6S model) is used to eliminate atmospheric effects and ensure that the spectral characteristics of the image accurately reflect the surface features. The processed satellite image is classified to identify surface features such as water bodies, soil, and vegetation. Supervised classification or unsupervised classification methods can be used, such as K-means clustering or random forest classification algorithms. For example, the random forest algorithm is used to classify the image, successfully identify the water body area, and generate a classified image. Extract the geometric features of water bodies from the classified satellite imagery, including their shape, area, and drainage boundaries. These features will be used for subsequent hydrodynamic analysis. Record relevant parameters of the water body, such as its area (e.g., 1000 square meters) and the elevation of the surrounding terrain, to facilitate calculations of flow velocity and direction. Select an appropriate hydrodynamic model for water flow distribution, typically a physics-based hydrological model (such as SWMM or HEC-RAS), to analyze the distribution and variability of water flow within the region. Determine the model's input parameters, including rainfall, evaporation, drainage area, and soil type. Based on the selected water flow model, input the relevant parameters and perform simulations, recording the dynamic changes in water flow under different conditions. For example, simulate the flow velocity and direction of water after a rainfall event. For example, if the simulation results show a flow velocity of 0.5 m / s for a particular water body after 50 mm of rainfall, record this result for subsequent analysis. Select an appropriate path extraction method, typically using a watershed analysis algorithm (such as DEM analysis) to identify flow paths within the watershed using a digital elevation model (DEM). Ensure that the elevation data and satellite imagery are aligned in geospatial space to accurately extract water flow paths. Use the watershed analysis tool to identify water flow paths in the area, extract multiple water flow paths and record their characteristics, including path length, flow direction, flow rate and other information. For example, identify the three main water flow paths in the area, and record the characteristic information of path 1 (north direction), path 2 (southeast direction) and path 3 (southwest direction). Based on the extracted water flow paths, construct them into a water flow path distribution network. Using graph theory methods, treat water flow paths as nodes and edges in the network, and establish connection relationships between paths. Record the flow rate, flow rate and its connection relationship of each path to form a complete water flow path distribution network dataset.

[0041] Step S3: Based on the regional pollution concentration distribution map, the pollutant migration logic evolution and multi-region gradient diffusion prediction of the water flow path distribution network are carried out to construct a water pollution diffusion prediction situation map;

[0042] In the present embodiment, the pollutant concentration data in the area is obtained from the water quality monitoring system, usually in mg / L. Ensure that the data covers the entire monitoring area, including the concentration changes at different time points. For example, it is recorded that the pollutant concentration in area A is 40mg / L, in area B is 60mg / L, and in area C is 30mg / L during a certain monitoring period. GIS software is used to generate a pollution concentration distribution map with the collected pollution concentration data. The blank areas in the area are filled by interpolation methods (such as Kriging interpolation or inverse distance weighted method) to obtain a continuous concentration distribution. For example, the generated pollution concentration distribution map clearly shows the spatial distribution hotspots of pollutant concentration, which is convenient for subsequent analysis. The pollution concentration distribution map is subjected to time series analysis to identify the changing trend of pollutant concentration in different areas. This process will help understand the diffusion of pollutants. Select a suitable pollutant migration model, usually based on fluid dynamics or hydrological models (such as Advance-Diffusion equations), to analyze the migration law of pollutants in the water flow path. Determine the input parameters of the model, including water flow velocity, pollutant concentration, diffusion coefficient, etc. According to the selected migration model, input relevant parameters to simulate and record the migration of pollutants under different flow rates and concentration conditions. Monitor how pollutants spread through the water flow path. For example, in the simulation, assume that the water flow velocity is 0.5m / s and the diffusion coefficient is 0.1m 2 / s, recording the temporal changes in pollutant concentrations in each watershed. The simulated pollutant migration results are recorded to form a pollutant migration pattern report. This report details the concentration changes and spatiotemporal distribution of pollutants along the water flow path. For example, at a certain point in time, the pollutant concentration in Path 1 is 50 mg / L, in Path 2 is 30 mg / L, and in Path 3 is 10 mg / L. A concentration trend chart is then generated. Based on the pollutant migration pattern, a multi-region gradient diffusion prediction model is constructed. Mathematical models (such as the diffusion equation) or machine learning models are typically used to predict pollutant concentration changes in multiple regions. The model's input parameters, including initial concentration, flow rate, diffusion coefficient, and environmental factors (such as temperature and humidity), are determined. The model predicts pollutant diffusion within the region, recording the changes in pollutant concentrations in each region at a future point in time. For example, the model predicts that within 48 hours, the pollutant concentration in Region A will diffuse from 40 mg / L to 25 mg / L, and in Region B from 60 mg / L to 35 mg / L. The pollution concentration distribution, migration logic evolution, and diffusion prediction results are integrated to generate a water quality pollution diffusion prediction map. Ensure data is formatted uniformly to facilitate subsequent visualization. Record pollution concentrations and their changing trends in each area for subsequent presentation. Use GIS software or data visualization tools to construct a water pollution spread prediction map. Associate pollutant concentrations with geographic location to generate heat maps or distribution maps. For example, a map showing pollution concentrations in different areas, combined with water flow paths, can facilitate understanding of pollutant migration and spread trends.

[0043] Step S4: Identify the highest diffusion gradient according to the water pollution diffusion prediction situation map, analyze the optimal navigation monitoring sequence, and construct the optimal navigation monitoring sequence;

[0044] In this embodiment, pollutant concentration data is extracted from the water pollution diffusion prediction situation map to ensure that the data covers the entire monitoring area. The data is organized into a grid format, with each grid representing the pollutant concentration value (in mg / L) at a specific location. For example, assuming that the area is divided into 10 meters by 10 meters grid, the pollutant concentration of each grid is recorded to ensure data integrity for subsequent analysis. A suitable diffusion progressive gradient calculation method is selected, usually using a numerical differentiation method or a gradient calculation algorithm to calculate the concentration change between adjacent grids. The Sobel operator or a simple difference method can be used to identify the maximum position of the concentration change. The progressive gradient is defined as the concentration difference between adjacent grids, and the calculation formula is set to: gradient = |C1-C2| / d, where C1 and C2 are the concentration values ​​of adjacent grids, and d is the grid spacing. The diffusion progressive gradient is calculated for each pair of adjacent grids, and the highest gradient value is identified. This process will help determine the location where the pollutant diffusion is most significant. For example, if the concentration in grid A is 50 mg / L and the concentration in grid B is 80 mg / L, the calculated progressive gradient is (80 - 50) / 10 m = 3 mg / L / m. The gradient values ​​for all grids are recorded to identify the highest progressive gradient. The optimal navigation and monitoring sequence is defined as the process by which the unmanned vessel plans its monitoring route during water quality monitoring based on the priority of pollutant concentration and diffusion gradient. The goal is to ensure coverage of areas with higher pollution concentrations. Monitoring priorities are set, for example, prioritizing the area with the highest diffusion progressive gradient, followed by adjacent grids with higher concentrations. An appropriate path planning method, typically a greedy algorithm or a shortest path algorithm, is selected to calculate the optimal navigation path for the unmanned vessel between pollution sources. This ensures that path planning considers not only concentration but also flow rate and path feasibility. The starting and end points of the path planning are determined, the initial position of the unmanned vessel is set, and the path is ensured to effectively connect all monitoring points. Based on the identified highest diffusion progressive gradient and its location, the optimal navigation and monitoring sequence for the unmanned vessel is calculated. For example, the location with the highest gradient may be selected as the first monitoring point, followed by adjacent grids with higher concentrations. Record the planned path, including the order, location and corresponding pollutant concentration of each monitoring point, to form the final monitoring sequence. For example, the order of monitoring points is point 1 (x1, y1), point 2 (x2, y2), and point 3 (x3, y3). Integrate the previously identified monitoring points and path sequence to form a complete navigation monitoring sequence. Ensure that the location, concentration and gradient information of each monitoring point are clearly recorded to facilitate subsequent navigation and data collection. For example, record the coordinates, pollutant concentration, diffusion gradient and expected monitoring time of each monitoring point to form a detailed navigation plan. During the navigation of the unmanned ship, dynamically adjust the navigation monitoring sequence according to real-time monitoring data. For example, if the concentration in a certain area suddenly rises, the navigation path will be adjusted to that area for monitoring first. Record the changes in the monitoring path before and after the dynamic adjustment to analyze its impact on the pollution monitoring effect.

[0045] Step S5: planning a pollution source coverage cruise path according to the optimal navigation monitoring sequence, performing dynamic navigation cruise monitoring, and collecting full-process cruise monitoring data;

[0046] In this embodiment, based on the previously identified optimal navigation monitoring sequence, an appropriate path planning algorithm is selected, typically a heuristic algorithm (such as the A* algorithm) or a shortest path algorithm, to achieve coverage of all potential pollution sources and minimize navigation time. The starting and end points of the monitoring path are determined, the initial position of the unmanned vessel is set, and the path is ensured to effectively connect all monitoring points. Based on the optimal navigation monitoring sequence, a coverage cruise path for the unmanned vessel between pollution sources is calculated. Areas with higher pollutant concentrations are prioritized for monitoring to ensure that the path covers all key monitoring points. For example, if the monitoring sequence is point 1 (x1, y1), point 2 (x2, y2), and point 3 (x3, y3), the unmanned vessel navigates in this order, recording the actual navigation path for each monitoring point. The unmanned vessel's navigation system is configured to ensure it can dynamically adjust according to the planned coverage cruise path. The system should be able to receive real-time water velocity, concentration data, and other environmental information to adjust the navigation strategy. The operating parameters of the navigation system, such as GPS positioning accuracy and navigation algorithm selection, are recorded to ensure the unmanned vessel can navigate accurately. Based on the coverage cruise path, the unmanned vessel is controlled to dynamically navigate along the planned path. Monitor water quality parameters in real time, ensuring data such as pollutant concentration, temperature, and pH is recorded during the cruise. For example, the unmanned vessel should collect water quality data every five minutes during navigation and record changes in relevant parameters for subsequent analysis. During navigation, the monitoring system should be able to provide real-time feedback on water quality data and dynamically adjust the navigation route based on the monitoring results. For example, if pollutant concentrations in a certain area increase, the navigation route should be adjusted to prioritize that area for more detailed monitoring. Dynamically adjusted navigation route changes should be recorded for subsequent analysis of their impact on pollution monitoring. The water quality monitoring equipment on the unmanned vessel should be configured to ensure it can accurately collect various water quality parameters, including pollutant concentration, temperature, pH, and dissolved oxygen. Ensure that the equipment is calibrated and in good condition. For example, using multi-parameter water quality monitoring instruments can collect multiple water quality parameters at the same time, ensuring the timeliness and accuracy of the data. During navigation, the unmanned vessel monitors along the pre-set monitoring route and records the collected water quality data in real time. Ensure the integrity and accuracy of the data. For example, water quality data for each monitoring point should be recorded, including timestamps, location coordinates, pollutant concentrations, and other information, for subsequent analysis and use.

[0047] Step S6: Based on the full-process cruise monitoring data, conduct real-time cruise concentration distribution change analysis and dynamic path adjustment to build an intelligent pollution source tracing and positioning model.

[0048] In this embodiment, real-time water quality data is collected from the full-process cruise monitoring, including timestamp, location information, pollutant concentration (in mg / L), temperature, pH value, etc. Ensure the integrity and accuracy of the data for subsequent analysis. For example, record the water quality data of each monitoring point. Assume that the pollutant concentration at a certain monitoring point is 45 mg / L, the temperature is 22°C, and the pH value is 7.5, and ensure that these data are arranged in chronological order. Use statistical analysis methods to calculate the changes in pollutant concentrations between each monitoring point. Compare the data at different time points to identify areas with significant concentration changes. For example, by comparing the two monitoring data before and after, if the pollutant concentration in a certain area increases from 30 mg / L to 50 mg / L, the concentration change is calculated to be 20 mg / L, record this change and mark the area as a pollution concern. Use GIS software or data visualization tools to generate a concentration distribution map for the collected water quality data. Fill the gaps in the area using interpolation methods (such as Kriging interpolation) to obtain a continuous concentration distribution map. For example, the generated concentration distribution map can clearly show the pollutant concentrations in each area, help identify pollution hotspots, and provide a basis for subsequent dynamic path adjustments. Based on the results of concentration change analysis, dynamic route adjustment rules are set for the UAV. For example, if the pollutant concentration in a certain area rises to a certain threshold (e.g., 50 mg / L), the navigation route is prioritized to that area for more detailed monitoring. Adjustment rules are recorded, such as "If the concentration at a monitoring point exceeds 40 mg / L, immediately adjust the route to that point." During the cruise, a real-time monitoring and feedback mechanism is established to ensure that the UAV can dynamically adjust its navigation route based on changes in water quality data. When concentration changes are detected, the system automatically sends a feedback signal to instruct the UAV to adjust its route. For example, if the UAV detects that the pollutant concentration at a certain monitoring point reaches 60 mg / L during monitoring, the system automatically generates a new navigation route, directing the UAV to that area for a detailed investigation. Based on the set route adjustment rules and real-time feedback information, the UAV is controlled to navigate along the new route, ensuring that the adjusted route effectively covers areas with higher pollutant concentrations. For example, the adjusted route might point to a new monitoring point (x2, y2). The adjusted monitoring point and its concentration data are recorded to ensure data continuity and integrity. Select a suitable intelligent pollution source tracing and positioning model, usually using machine learning algorithms (such as random forests and support vector machines) to analyze the source of pollutants. Set the input parameters of the model, including environmental factors such as pollutant concentration, flow rate, and wind speed. Determine the feature data needed for the model, such as historical concentration data of monitoring points, topographic information of the watershed, and water flow direction. Construct a training data set based on historical monitoring data and real-time cruise monitoring data. Integrate the concentration changes, environmental conditions, and pollution source information of different monitoring points into one data set to facilitate subsequent model training.For example, collect monitoring data from the past few months and construct a training set that includes concentration changes, flow rate, and monitoring point characteristics to ensure the diversity and representativeness of the data set. Use the constructed data set to train the selected intelligent model and perform cross-validation to ensure the accuracy and generalization ability of the model. Adjust the model parameters to improve the prediction effect. For example, by training the model, it is possible to predict the possible sources and diffusion paths of pollutants under different environmental conditions, and record the accuracy and recall rate of the model to evaluate its performance. Use the trained intelligent pollution tracing model to analyze the real-time monitoring data and identify the possible location of the pollution source. According to the prediction results of the model, adjust the monitoring strategy and give priority to possible pollution source areas. For example, if the model predicts that a certain area is the main source of pollutants, record the characteristic data of the area and formulate a corresponding monitoring plan.

[0049] In this embodiment, refer to Figure 2 , is a flowchart of the detailed implementation steps of step S1. In this embodiment, the detailed implementation steps of step S1 include:

[0050] Based on the ship-borne water quality monitoring sensors, regional water quality monitoring parameters are collected and uploaded to the cloud for data optimization to obtain optimized regional water quality monitoring parameters;

[0051] Identify water pollution by optimizing regional water quality monitoring parameters and generate regional water pollution characteristics;

[0052] Infer the source of water pollution based on the regional water pollution characteristics and obtain the regional water pollution source;

[0053] Calculate the pollution concentration of the optimized regional water quality monitoring parameters to generate regional pollution concentration values;

[0054] Based on the regional water pollution sources, the spatial pollution distribution of regional pollution concentration values ​​is mined to construct a regional pollution concentration distribution map.

[0055] In this embodiment, a variety of water quality monitoring sensors are installed on board, including pH sensors, turbidity sensors, dissolved oxygen sensors, and conductivity sensors. These sensors should have real-time data acquisition capabilities and be able to work stably under different water conditions. Determine the installation position of the sensor to ensure that it can evenly cover the water area and avoid being affected by the hull or other obstacles. For example, choose a position slightly forward of the center of the hull to improve the representativeness of the data. Configure the data acquisition system and set the sampling frequency to once per minute to obtain dynamic information on water quality changes. Record the timestamp of each acquisition, the sensor type, and its corresponding monitoring parameters. For example, record the pH value of 7.2, the turbidity of 5NTU, the dissolved oxygen of 8mg / L, and the conductivity of 500μS / cm at a certain time point to ensure that the data is complete and the format is consistent.

[0056] Collected water quality monitoring data is uploaded to a cloud database via a wireless network to ensure real-time data accessibility. MQTT or HTTP protocols are used for data transmission to ensure data reliability and security. In the cloud database, data is categorized and stored by timestamp and sensor type to facilitate subsequent data optimization and analysis. The uploaded water quality monitoring data is cleaned, including removing missing values, outliers, and duplicates. Statistical analysis methods, such as the Z-score method, are used to identify outliers to ensure data accuracy. For example, if the dissolved oxygen value at a specific time point is abnormally above the normal range (e.g., exceeding 15 mg / L), it is marked as an outlier and removed. Data optimization algorithms (such as weighted average or moving average) are used to smooth the cleaned data to eliminate noise and obtain more accurate water quality monitoring parameters. For example, a time window of 10 minutes is set, and the final monitoring parameters are optimized by calculating the average dissolved oxygen value within this time window. Regional averages for each water quality monitoring parameter are generated based on the optimized data, and corresponding reports are generated. These parameters are used for subsequent water pollution identification and analysis. For example, the optimized pH is 7.1, the turbidity is 4 NTU, and the dissolved oxygen is 7.5 mg / L. These values ​​will serve as the benchmarks for subsequent analyses.

[0057] Based on national or regional water quality standards, set thresholds for identifying water pollution. For example, a pH value below 6.5 or above 8.5 may indicate water pollution. Record all relevant threshold standards to facilitate subsequent pollution identification and data analysis. Pollution identification is performed on the optimized water quality monitoring parameters to determine whether they exceed the set pollution threshold. Each monitoring parameter is compared with the corresponding standard to identify the type of pollution. For example, if the turbidity monitored during a certain period is 10 NTU, exceeding the set threshold of 5 NTU, the area is marked as "polluted." Based on the identification results, corresponding water pollution characteristics are generated, including the type of pollution, the degree of pollution, and its frequency of occurrence. These characteristics will be used for subsequent pollution source inference. For example, if an area records turbidity exceeding the standard multiple times within a week, the pollution characteristic for that area can be recorded as "frequent high turbidity." Based on the water pollution characteristics, a pollution source inference model is constructed. Statistical models (such as linear regression) or machine learning models (such as decision trees) can be used to analyze the relationship between pollution sources and water quality parameters. Set the model's input variables, including historical water quality monitoring parameters, pollution characteristics and their corresponding time and location. Use historical data to train the inference model and perform cross-validation to evaluate the model's accuracy. Record the model's performance indicators, such as the root mean square error (RMSE) or the coefficient of determination (R 2 ). For example, if the model's R 2A value of 0.85 indicates that the model can well explain the relationship between water quality parameters and pollution sources. Use the trained model to infer the pollution source of the current water pollution situation and identify potential pollution sources. For example, if the model output indicates a high correlation between wastewater discharge from a certain industrial area and pollution parameters, infer that industrial area as a pollution source. Record the inference results, including the name and type of pollution source and its potential impact range.

[0058] Select an appropriate method for calculating pollution concentration based on water quality monitoring parameters. A standardized method can be used to convert monitoring parameters into pollution concentration values. For example, the concentration of a pollutant can be calculated using the formula: Concentration (mg / L) = Monitoring value × Dilution factor. Calculate the pollution concentration for the optimized water quality monitoring parameters and record the pollution concentration values ​​for each time period and region. Ensure that the recorded concentration values ​​are consistent with the actual monitoring data. For example, the pollution concentration in a certain area is calculated to be 50 mg / L, and this value will be used for subsequent spatial pollution distribution mining. Prepare visualization data based on the calculated regional pollution concentration values. Ensure that the data format is clear to facilitate the generation of a pollution concentration distribution map. Record the coordinate position, pollution concentration value, and related information of each area for subsequent visualization.

[0059] Use geographic information system (GIS) software or data visualization tools to construct regional pollution concentration distribution maps. Associate pollution concentration values ​​with geographic locations to generate heat maps or distribution maps. For example, use heat maps to display the distribution of pollution concentrations in different regions, with light and dark colors representing high and low concentrations, making it easier to visually identify severely polluted areas. Analyze the generated pollution concentration distribution map to identify concentrated pollution areas and generate corresponding reports that detail the pollution situation and its potential impacts. For example, if the pollution concentration in a certain area is significantly higher than in other areas, record the characteristics of the area and possible treatment recommendations to provide a basis for subsequent water quality management.

[0060] In this embodiment, the specific steps of collecting regional water quality monitoring parameters based on the ship-borne water quality monitoring sensor and uploading them to the cloud for data optimization to obtain optimized regional water quality monitoring parameters are as follows:

[0061] identifying a plurality of available networks in an area according to the multimodal communication module;

[0062] Calculating the communication distance, bandwidth, and anti-interference capability of the multiple available networks and performing a comprehensive network status evaluation to obtain the real-time signal status of each available network;

[0063] Perform real-time optimal network evaluation based on the real-time signal status of each available network and mark the real-time optimal available network;

[0064] Determining the dynamic change characteristics of the real-time signal status of each available network;

[0065] Dynamically switching the best available network in real time according to the dynamic change characteristics to build a multi-modal intelligent switching strategy;

[0066] Collect regional water quality monitoring parameters based on ship-borne water quality monitoring sensors;

[0067] Uploading the regional water quality monitoring parameters to the cloud for cloud data optimization based on a multimodal intelligent switching strategy to obtain optimized regional water quality monitoring parameters;

[0068] The cloud data optimization is specifically as follows:

[0069] Identify sensor anomalies and errors for regional water quality monitoring parameters and extract sensor error parameters;

[0070] Performing data elimination processing on the sensor error parameters to obtain error optimization monitoring parameters;

[0071] Perform spatiotemporal loss detection on error optimization monitoring parameters and identify spatiotemporal loss locations;

[0072] Calculate the average value of the prime error optimization monitoring parameter;

[0073] The interpolation filling optimization is performed on the missing positions in time and space based on the average value to construct the optimized regional water quality monitoring parameters.

[0074] In this embodiment, a multimodal communication module is integrated into the device, capable of scanning and identifying available wireless networks. These networks may include Wi-Fi, Bluetooth, cellular networks, etc. Configure the module's operating frequency band and scanning mode to ensure coverage of the required communication range. Set the scanning frequency, for example, scanning every 5 seconds, to obtain the latest network status information. Record the timestamp of each scan and the identified network information, including network name, signal strength, type, etc. Start the multimodal communication module and perform a network scan. The module will automatically identify available networks in the surrounding area and record their basic information, such as SSID, MAC address, signal strength (dBm), access point type, etc. For example, suppose three networks are identified in a scan: Network A (signal strength -45dBm), Network B (signal strength -60dBm), and Network C (signal strength -75dBm). This information is recorded for subsequent analysis. Based on the signal strength of each network, its theoretical communication distance is calculated. The free space propagation model (FSPL) is used to estimate the effective signal propagation distance, and the conversion is performed in dBm units. For example, if the signal strength of network A is -45dBm, use the formula to calculate the effective communication distance, which yields an effective distance of 300 meters (assuming ideal conditions). Record this result. Collect bandwidth information for each network. If the available network supports multiple bandwidth options (e.g., 20MHz, 40MHz), record the optimal bandwidth configuration. In theory, the wider the bandwidth, the faster the data transmission speed. For example, if network B supports 40MHz bandwidth, record its maximum transmission rate (e.g., 300Mbps) for subsequent comprehensive evaluation. Evaluate each network's interference resistance, taking into account network type and environmental factors. Use historical data or actual measurement results to record the network's stability in interference environments. For example, if network C maintains a good connection in complex environments, record its interference resistance as "high" and generate an evaluation report. Construct a comprehensive scoring model based on the calculated communication distance, bandwidth, and interference resistance. Assign weights to each parameter to comprehensively evaluate the real-time signal status of each network. For example, set a weight of 0.5 for signal strength, 0.3 for bandwidth, and 0.2 for interference resistance to facilitate comprehensive evaluation. Based on the evaluation model, the real-time signal status of each available network is evaluated and a comprehensive score is calculated. The score and status of each network are recorded. For example, if Network A scores 85, Network B scores 70, and Network C scores 60, the combined score will be used to subsequently select the optimal network. Based on the comprehensive evaluation results, criteria are set for selecting the optimal real-time network. For example, the network with the highest score is selected as the optimal real-time network. The selection criteria are recorded for future reference during network switching. The comprehensive scores of all available networks are compared, and the network with the highest score is marked as the optimal real-time network.

[0075] Record detailed network information, including signal status and evaluation scores. For example, if Network A has the highest score, mark it as the real-time optimal network and record its signal strength and bandwidth. Monitor the signal status of the real-time optimal network and observe the dynamic changes in its signal strength and other relevant parameters to make timely network switching decisions. For example, if the signal strength of Network A drops to -70dBm within a short period of time, consider switching to the suboptimal network. Analyze the real-time signal status of each network to identify trends and characteristics of signal strength changes. Use a moving average method to smooth signal change data to clearly observe dynamic changes. For example, if the signal strength of Network A has gradually decreased over the past five minutes, record its dynamic change characteristics as "downward trend." Record the dynamic change characteristics of each network, including the speed and direction of signal change. These characteristics will provide a basis for subsequent network switching strategies. For example, if the signal of Network B remains stable while the signal of Network C fluctuates significantly, Network B can be considered more reliable. Store dynamic change characteristics in a database for subsequent analysis and querying. Ensure that the data format is clear and easy to extract and analyze. For example, a data table can be established to record the dynamic characteristics and change trends of each network to facilitate the subsequent implementation of intelligent switching strategies.

[0076] Design dynamic switching strategies based on the dynamic characteristics of real-time signal status. For example, automatically switch to a suboptimal network when signal strength falls below a threshold. Record switching conditions and switching priorities to ensure rapid response to signal changes. Implement dynamic switching processing, monitor signal status in real time, and immediately switch to the marked suboptimal network if the signal status of the currently preferred network deteriorates. For example, if the signal strength of Network A continues to decline, immediately switch to Network B and record the switch event. After the switch, continue to monitor the signal status and performance of the newly selected network to evaluate the effectiveness of the switching strategy. Record signal status changes before and after the switch to optimize the strategy. For example, if the signal strength of Network B after the switch is -50dBm, which is better than that of Network A before the switch, the switch is considered successful. Install water quality monitoring sensors on board, including those for pH, turbidity, and dissolved oxygen, to monitor water quality parameters in real time. Ensure that the sensors are properly calibrated and can operate normally under different water conditions. Set the sampling frequency to once per minute, and record the timestamp and monitored parameters of each acquisition. Upload the collected water quality parameters to a cloud database via the multimodal communication module.

[0077] Ensure stable data transmission and avoid data loss. Record the uploaded data format, including timestamp, sensor type, and corresponding monitoring parameters, for subsequent optimization and analysis. In the cloud, identify abnormal errors in uploaded water quality monitoring parameters, using statistical methods (such as the Z-score method) to identify outliers. For example, if the pH value during a certain period is abnormally above the standard range, it is marked as abnormal data. Identified abnormal data is removed to ensure that subsequent data analysis is based on accurate monitoring parameters. The details of the removed data are recorded for subsequent analysis and verification. Perform spatiotemporal missing data detection to identify missing data in certain time periods or locations. Use interpolation to estimate the location of missing values ​​to ensure data integrity. For example, if turbidity data is not recorded for a certain period, the missing data is recorded and marked as requiring interpolation. Calculate the average value of the removed monitoring parameters to facilitate subsequent interpolation and optimization. For example, if the processed turbidity data is 4 NTU, 5 NTU, and 6 NTU, calculate the average value to be 5 NTU. Record the calculated average value in the database for subsequent interpolation. For example, record the average turbidity value of a certain period as 5NTU as the basis for subsequent interpolation and filling. Select an appropriate interpolation method (such as linear interpolation or spline interpolation) and fill the missing positions according to the calculated average value. Record the selected method for subsequent data verification. Interpolate the identified missing data positions and fill the missing values ​​to ensure the integrity and continuity of the data. For example, if the turbidity is missing in a certain period, use the previous and next data for interpolation and fill the missing value with 5NTU. Integrate the data that has been eliminated, filled and optimized to generate the final optimized regional water quality monitoring parameters to ensure their accuracy and reliability. Record the optimized parameters and form a data report for subsequent analysis and application.

[0078] In this embodiment, refer to Figure 3 , is a flowchart of the detailed implementation steps of step S2. In this embodiment, the detailed implementation steps of step S2 include:

[0079] Obtain a regional satellite remote sensing map; perform global histogram equalization optimization on the regional satellite remote sensing map to obtain a brightness optimized remote sensing map;

[0080] Water flow direction identification is performed based on brightness optimized remote sensing maps to obtain regional water flow direction;

[0081] identifying the runoff distribution of the brightness optimized remote sensing map and extracting multiple water flow paths;

[0082] Based on the regional water flow direction, the water system trend characteristics of multiple water flow paths are analyzed one by one to generate the distribution characteristics of water flow path direction;

[0083] Calculate real-time water flow velocity based on regional water quality monitoring parameters;

[0084] The water flow distribution dynamics evolution is carried out according to the real-time water flow velocity and the distribution characteristics of the water flow path, and the water flow path distribution network is constructed.

[0085] In this embodiment, satellite remote sensing technology is used to obtain a remote sensing map of the target area. High-resolution satellite images can be downloaded through open data sources such as NASA, ESA, etc., or using commercial remote sensing services (such as Google Earth Engine). Ensure that the acquired image covers the target area and has sufficient spatial resolution (such as 10 meters or higher) and temporal resolution. When acquiring the image, metadata such as the image acquisition time, resolution, and sensor type are recorded to facilitate subsequent analysis. For example, the acquired image is from the Sentinel-2 satellite with a resolution of 10 meters and an acquisition time of March 1, 2023. The acquired satellite remote sensing image is preprocessed, including geometric correction, radiation correction, and atmospheric correction, to eliminate systematic errors and environmental effects in the image. Ensure that the geometric accuracy and radiation characteristics of the image meet the analysis requirements. For example, an atmospheric correction algorithm (such as the 6S model) is used to eliminate atmospheric effects and ensure that the spectral characteristics of the image accurately reflect the surface characteristics. The grayscale histogram of the regional satellite remote sensing map is analyzed to calculate the brightness distribution of the image. By analyzing the histogram, you can identify uneven brightness distribution within an image and determine why histogram equalization is necessary. For example, if the histogram shows that most pixels are concentrated in the low brightness range (e.g., 0-100), the image is generally dark and requires equalization. Applying a global histogram equalization algorithm to the satellite remote sensing map redistributes the image's grayscale values ​​to enhance contrast and brightness. This process is accomplished by calculating the cumulative distribution function (CDF), which maps pixel brightness values ​​to a new range. For example, in the processed image, the brightness range from 0-255 is evenly distributed, enhancing image visibility and making features such as water bodies, vegetation, and soil more distinct. Select an appropriate method for identifying water flow direction. Common algorithms include edge detection-based methods (such as Canny edge detection) and motion analysis based on optical flow. Select an appropriate algorithm to extract water flow direction. Parameters, such as high and low thresholds in Canny edge detection, are set to optimize edge detection. Apply the water flow direction identification algorithm to the brightness-optimized remote sensing map to extract the flow characteristics of the water body. By analyzing the edges and directions in the image, the main direction of the water flow is identified. For example, the edge detection method is used to identify the edges of multiple water bodies in the image, and by calculating the edge direction, the flow direction of the water flow is determined to be southeast. The identified water flow direction is recorded and saved to form a water flow direction dataset. The specific degree of the water flow direction (such as 135 degrees corresponds to the southeast direction) and possible changes in flow rate are recorded. For example, the main water flow direction in the recorded area is 135 degrees, and the flow rate range is 1-3m / s for subsequent analysis. Select a suitable runoff distribution analysis method, usually using an algorithm based on watershed analysis (such as DEM analysis), and use a digital elevation model (DEM) to identify the runoff characteristics of the watershed. Prepare elevation data to ensure that the elevation data is aligned with the remote sensing image in geographic space.Use the watershed analysis tool to identify the runoff distribution in the area and extract multiple flow paths. By analyzing the elevation changes and flow direction, determine the path where the water flows. For example, identify three main flow paths in the area: Path 1 (northeast), Path 2 (southeast), and Path 3 (southwest). Record the extracted flow paths to form a flow path dataset. Record the starting point, end point, and characteristic attributes of each path (such as flow velocity, flow rate, etc.). For example, the starting coordinates of Path 1 are (x1, y1), the end point is (x2, y2), the flow velocity is 2m / s, and the flow rate is 10m. 3 / s. Select an appropriate method for analyzing the direction characteristics of a water system, typically using geometric or statistical analysis, to analyze the direction characteristics of water flow paths. Determine analysis parameters, such as path length, curvature, and flow direction distribution. Perform a direction characteristic analysis on each extracted water flow path, calculate the path's geometric characteristics, and record the direction distribution characteristics. For example, if analyzed path 1 is 500 meters long and has a curvature of 0.2, its direction characteristic is recorded as "relatively straight." Record the results of the water system direction characteristic analysis to form a report on the direction distribution characteristics of water flow paths. Summarize the characteristics of each path to facilitate subsequent hydrodynamic analysis. For example, record path 1 as "straight," path 2 as "curved," and path 3 as "multi-branched." Select an appropriate method for calculating water flow velocity, typically using flow sensor data or a calculation method based on water flow paths and flow rates. Determine calculation parameters, such as flow rate and watershed area, to calculate water flow velocity. Calculate real-time water flow velocity based on the monitored flow rate and watershed area. Use the formula: water flow velocity = flow rate / cross-sectional area. For example, if the flow rate of a water flow path is 10m 3 / s, cross-sectional area is 5m 2, the calculated water velocity is 2 m / s. Based on the water velocity and path characteristics, select an appropriate dynamic model. A hydrodynamic model or a fluid dynamics-based model can be used to analyze the water flow evolution process. Determine the model's input parameters, including real-time water velocity, path direction, and characteristics. Use the dynamic model to simulate and evolve the water flow distribution, analyzing the changes and impacts of water flow under different conditions. Record changes in key parameters during the evolution process. For example, if the simulation results show that the water velocity in path 1 will increase to 3 m / s under specific rainfall conditions, record this change for further analysis. Record the results of the dynamic evolution of the water flow distribution to form a water flow dynamic evolution report. Summarize the changes in water flow velocity and path, and their relationship with environmental factors. For example, record that the water velocity in path 1 increases after rainfall, path 2 remains stable, and path 3 is obstructed, forming a complete dynamic evolution analysis report. Construct a water flow path distribution network based on the extracted water flow paths and flow velocities. Using graph theory, treat the water flow paths as nodes and edges in the network and establish the connections between the paths. Determine the network's connectivity rules, such as the flow relationships and flow directions between paths. Build a water flow path distribution network model based on the flow paths and flow velocities. Record the flow velocity, flow rate, and connectivity of each path. For example, path 1 is connected to path 2, while path 3 is independent, forming a complete water flow path distribution network. Record the constructed water flow path distribution network and generate corresponding visualizations to visually display the water flow path distribution. For example, generate a network diagram to display the connectivity of water flow paths, flow velocity changes, and their relationship to environmental factors to facilitate subsequent decision support.

[0086] In this embodiment, refer to Figure 4 , is a flowchart of the detailed implementation steps of step S3. In this embodiment, the detailed implementation steps of step S3 include:

[0087] Calculate pollutant concentration gradients based on regional pollution concentration distribution maps;

[0088] Calculating the concentration variation amplitude of the pollutant concentration gradient to generate a concentration variation amplitude value;

[0089] Conduct in-depth mining of concentration fluctuation trends based on concentration change amplitude values ​​to generate regional concentration fluctuation trend characteristics;

[0090] Conduct pollutant migration logic evolution on the water flow path distribution network to generate pollutant migration laws;

[0091] Based on the migration law of pollutants, multi-region gradient diffusion prediction is carried out on the regional concentration fluctuation trend characteristics to construct a water pollution diffusion prediction situation map.

[0092] In this embodiment, relevant pollutant concentration data is extracted from the regional pollution concentration distribution map to ensure that the data covers the entire study area. The data is organized in a grid format, with each grid representing the pollutant concentration value at a specific location. For example, assuming the area is divided into a 10 m x 10 m grid, the pollutant concentration of each grid is recorded (e.g., in mg / L), and the integrity of the data is ensured. An appropriate concentration gradient calculation method is selected, typically using a numerical differentiation method or a gradient calculation algorithm (such as the Sobel operator), to facilitate calculation of concentration changes between each grid. The calculation direction is determined, for example, calculating the concentration gradient in the horizontal and vertical directions to comprehensively analyze the concentration changes. The selected algorithm is used to calculate the pollutant concentration gradient for each grid in the area. The concentration gradient value for each grid is recorded, typically expressed in mg / L / m. For example, if the pollutant concentration in a grid is 50 mg / L and the concentration in the adjacent grid is 30 mg / L, the calculated concentration gradient is (50-30) / 10m = 2 mg / L / m, and this result is recorded. The concentration change amplitude is defined as the concentration difference between adjacent grids to reflect the change in pollutant concentration within the area. Ensure clear definitions to facilitate subsequent calculations. For example, set the amplitude of change to |C1-C2|, where C1 and C2 are the concentration values ​​of adjacent grids. Calculate the concentration difference for each pair of adjacent grids to generate a concentration amplitude of change value and record the amplitude of change for each grid. For example, if the concentration in grid A is 40 mg / L and the concentration in grid B is 50 mg / L, the amplitude is |40-50| = 10 mg / L, and this amplitude value is recorded. Select an appropriate fluctuation trend analysis method, typically using time series analysis or a sliding window method, to analyze the time series characteristics of the concentration amplitude of change. Determine the analysis window size, for example, set it to five time points, and observe the trend of the concentration amplitude of change. Analyze the concentration amplitude of change data using the sliding window method, calculating statistical features such as the mean and standard deviation within each window to identify the trend of concentration fluctuation. For example, if the concentration amplitudes of change within five time points are 10, 15, 12, 8, and 20 mg / L, respectively, calculate the mean within the window as 13 mg / L and record this trend characteristic. Select a suitable logical evolution model for pollutant migration. Usually, the diffusion equation or fluid dynamics model can be used to analyze the migration pattern of pollutants in the water flow path. Determine the input parameters of the model, including water flow velocity, concentration gradient and flow direction. Use the selected model to simulate the migration of pollutants in the water flow path, and record the changes in pollutant concentration and its distribution along the water flow path. For example, if the pollutants migrate along the water flow path at a speed of 2m / s in the simulation, record the changes in their concentration at different locations. According to the migration pattern of pollutants, construct a multi-region gradient diffusion prediction model. Mathematical models (such as diffusion equations) or machine learning models can be used to predict the concentration changes of pollutants in multiple regions. Determine the input parameters of the model, including initial concentration, flow velocity and diffusion coefficient.The model predicts the spread of pollutants within a region and records concentration changes in each region at a specific point in the future. For example, if the model predicts that the pollutant concentration in a certain area will spread from 10 mg / L to 5 mg / L within 48 hours, this prediction is recorded. All analyzed pollutant concentration data, migration patterns, and diffusion predictions are integrated to generate a water pollution diffusion prediction map. Ensure that the data format is uniform to facilitate subsequent visualization. Use GIS software or data visualization tools to construct the water pollution diffusion prediction map. Associate pollutant concentrations with geographic location to generate heat maps or distribution maps. For example, the generated prediction map displays pollution concentrations in different regions, with light and dark colors representing higher and lower concentrations, making it easy to quickly identify areas of severe pollution. Analyze the generated water pollution diffusion prediction map to identify concentrated areas of pollution and generate a corresponding report detailing the pollution situation and its potential impacts. For example, if the pollution concentration in a certain area is significantly higher than in other areas, corresponding remediation recommendations can be made to provide a basis for subsequent water quality management.

[0093] In this embodiment, step S4 includes the following steps:

[0094] According to the water pollution diffusion prediction situation map, the highest diffusion progressive gradient is identified and the highest diffusion progressive gradient is extracted;

[0095] Analyze the water flow direction of the highest diffusion progressive gradient to generate the water flow direction of the highest pollution gradient;

[0096] Based on the water flow direction with the highest pollution gradient, the direction of potential pollution sources in the water flow path distribution network is located to obtain the orientations of multiple potential pollution sources;

[0097] Identify the current spatial position of the unmanned vessel and calculate the nearest potential pollution source based on the positions of multiple potential pollution sources;

[0098] Calculating the pollution source distance difference of the plurality of potential pollution source positions;

[0099] An optimal navigation monitoring sequence is analyzed based on the nearest potential pollution source and the distance difference between the pollution sources to construct an optimal navigation monitoring sequence.

[0100] In this embodiment, pollutant concentration data is extracted from the water pollution diffusion prediction situation map. The data is organized into a grid to ensure that the pollution concentration value of each grid is clear and readable, which is convenient for subsequent analysis. For example, the area is divided into a grid of 10 meters by 10 meters, and the pollutant concentration (such as mg / L) of each grid is recorded. Ensure data integrity to facilitate subsequent gradient calculation. Select a suitable diffusion progressive gradient calculation method, usually using the concentration gradient calculation formula to calculate the concentration change between adjacent grids. The numerical differentiation method can be used to identify the location with the largest change. Define the progressive gradient as the concentration difference between adjacent grids, and set the calculation formula as: gradient = |C1-C2| / d, where C1 and C2 are the concentration values ​​of adjacent grids, and d is the grid spacing. Calculate the diffusion progressive gradient for each pair of adjacent grids and identify the highest gradient value. This process will help determine the location where the pollutant diffusion is most significant. For example, if the concentration of grid A is 40mg / L and the concentration of grid B is 70mg / L, the calculated progressive gradient is (70-40) / 10m=3mg / L / m. Record the gradient values ​​for all grid cells and identify the highest progressive gradient. Leverage the previous flow direction identification results to prepare flow direction data. Ensure that the flow direction data matches the concentration data for analysis. Record the flow direction for each grid cell, ensuring it is in degrees (0° represents north, clockwise). Select an appropriate flow direction analysis method, typically using a flow diagram-based analysis method, combined with the concentration gradient identification results, to analyze the flow direction at the highest pollution gradient. Define the flow direction characteristic as "flow from high concentration to low concentration." Based on the highest identified diffusion progressive gradient, analyze the flow direction for the grid cell corresponding to that gradient. Record this direction for subsequent potential pollution source location. For example, if the location with the highest diffusion progressive gradient has a flow direction of 135° (southeast), record this flow direction characteristic. Prepare potential pollution source data based on the flow path distribution network. Ensure that the coordinates of each potential pollution source and its corresponding concentration value are known. Record the geographic location of the potential pollution source and its corresponding pollutant concentration for subsequent analysis. Select an appropriate direction location method, typically using vector analysis, to determine the location of the pollution source by combining the flow direction and the location of the potential pollution source. The pollution source orientation is defined as the direction from the current unmanned boat position to the potential pollution source. According to the water flow direction with the highest pollution gradient, each potential pollution source is positioned and analyzed, and its orientation relative to the current spatial position of the unmanned boat is calculated. For example, if the position of the unmanned boat is (x0, y0) and the position of the potential pollution source is (x1, y1), the azimuth is calculated as atan2(y1-y0, x1-x0), and the orientation of all potential pollution sources is recorded. Use the global positioning system (GPS) to obtain the current spatial position of the unmanned boat to ensure that the acquired position information is accurate and reliable. Record the current longitude and latitude of the unmanned boat (such as longitude X, latitude Y), and ensure that its format is clear for subsequent calculations.Select an appropriate distance calculation method, typically the Euclidean distance method, to calculate the distance between the unmanned vessel and each potential pollution source. Define the distance calculation formula as: distance = √((x1 - x0). 2 +(y1-y0) 2 ), where (x0, y0) is the position of the unmanned vessel and (x1, y1) is the position of the potential pollution source. Calculate the distance between all potential pollution sources and record the distance between the unmanned vessel and each potential pollution source. For example, if the position of the unmanned vessel is (5, 5) and the position of the potential pollution source is (10, 10), the calculated distance is √((10-5)2+(10-5) 2 )=7.07, record the distance. According to the calculated distance value, identify the nearest potential pollution source, and record its location information and distance value. For example, if the distance of potential pollution source A is 6.5, the distance of potential pollution source B is 7.0, and the nearest pollution source is A. The pollution source distance difference is defined as the distance difference between the nearest potential pollution source and other potential pollution sources, reflecting the relative position relationship of the pollution sources. For example, if the distance of the nearest pollution source A is 6.5 and the distance of another pollution source B is 8.0, then the distance difference is 8.0-6.5=1.5. Calculate the distance difference for all potential pollution sources, and record the distance difference between each potential pollution source and the nearest pollution source. For example, if the distance of potential pollution source C is 9.0, then the calculated distance difference between C and A is 9.0-6.5=2.5. Record the calculated pollution source distance difference in the data set to form a pollution source information table containing the distance difference. For example, record "distance to pollution source A: 6.5, distance to pollution source B: 8.0, distance to pollution source C: 9.0" and calculate the corresponding distance difference. Select a suitable navigation sequence analysis method, usually using a greedy algorithm or a shortest path algorithm, to calculate the optimal navigation path of the unmanned ship between potential pollution sources to determine the analysis goal, such as minimizing the navigation distance or time. Based on the distance and direction of the potential pollution source, calculate the optimal navigation sequence of the unmanned ship between different potential pollution sources. For example, give priority to visiting the nearest pollution source, and then the pollution source with the second closest distance. Record the optimal navigation sequence to form a navigation path data set. Record the optimal navigation monitoring sequence and generate corresponding visualization charts to intuitively display the navigation path of the unmanned ship. For example, generate a navigation path diagram to show the optimized path of the unmanned ship from the current position to each potential pollution source, which is convenient for subsequent navigation control.

[0101] In this embodiment, step S5 includes the following steps:

[0102] Based on the water flow path distribution network, the unmanned boat navigation upstream and downstream direction is determined, and the upstream and downstream directions of each path are obtained;

[0103] The navigation speed of each path is calculated based on the real-time water speed and the upstream and downstream directions of each path to obtain the navigation speed of each path;

[0104] According to the navigation rate of each path, the optimal navigation monitoring sequence is used to plan the pollution source coverage cruise path and construct an intelligent coverage cruise path;

[0105] Dynamic navigation cruise monitoring is carried out on the water quality monitoring unmanned vessel according to the intelligent coverage cruise path, and full-process cruise monitoring data is collected.

[0106] In this embodiment, water flow direction data is extracted from the water flow path distribution network. Ensure that the water flow direction of each path is expressed in degrees and matches the navigation system of the unmanned boat. Record the directional characteristics of each water flow path, for example, the water flow direction of one path is 135° (southeast direction) and the water flow direction of another path is 315° (northwest direction). Select a suitable method for judging upstream and downstream, usually based on the comparison between the water flow direction and the navigation direction of the unmanned boat. If the water flow direction is consistent with the navigation direction, it is downstream; if it is opposite, it is upstream. Set the target direction for the unmanned boat to sail, for example, the navigation direction is 180° (south). Compare the direction of each water flow path with the navigation direction of the unmanned boat to determine whether it is downstream or upstream. For example, if the water flow direction is 135° and the navigation direction is 180°, calculate the angle between the two and judge it as "countercurrent". Record the upstream and downstream status of each path to form a data table for subsequent analysis. For example, path A is "downstream" and path B is "countercurrent". Ensure that real-time water velocity data is available and compatible with the water path distribution network. Water velocity should be recorded in meters per second (m / s). For example, record a water velocity of 2 m / s in a certain area and ensure that this data applies to all paths. Select an appropriate method for calculating navigation speed, typically a combination of water velocity and navigation direction. If traveling downstream, the navigation speed is calculated as the water velocity plus the UAV's own speed; if traveling upstream, the navigation speed is calculated as the water velocity minus the UAV's own speed. Set the UAV's own navigation speed, for example, to 1 m / s. For each path, calculate the navigation speed based on its downstream and upstream status. If traveling downstream, the speed is calculated as the water velocity + the boat's speed; if traveling upstream, the speed is calculated as the water velocity minus the boat's speed. For example, if path A is downstream, the water velocity is 2 m / s, and the UAV's speed is 1 m / s, the navigation speed is 2 + 1 = 3 m / s; if path B is upstream, the navigation speed is 2 - 1 = 1 m / s. Record the speed of each path and create a data table to facilitate subsequent cruise route planning. Select an appropriate path planning method, typically using a heuristic algorithm (such as the A* algorithm or genetic algorithm) to optimize the pollution source coverage path. The goal is to ensure that the unmanned vessel can cover all potential pollution sources. Determine the starting point, end point, and waypoints of the coverage path to ensure the effectiveness of the path planning. Calculate the optimal coverage cruise path based on the speed of each path and the location of potential pollution sources. For example, prioritize paths with faster speeds and coverage of multiple pollution sources. Record the planned paths, including the order of each path and its corresponding speed, to form the final coverage cruise path dataset. Configure the unmanned vessel's navigation system to ensure it can dynamically adjust according to the planned coverage cruise path. The system should be able to receive real-time water speed and direction information to adjust navigation strategies. Record the operating parameters of the navigation system, such as GPS positioning accuracy and navigation algorithm selection, to ensure the unmanned vessel's accurate navigation. Based on the intelligent coverage cruise path, control the unmanned vessel to dynamically navigate along the planned path.Monitor water quality parameters in real time, ensuring data such as pollutant concentration, temperature, and pH is recorded during the cruise. For example, the unmanned vessel collects water quality data every five minutes during navigation and records changes in relevant parameters. Select appropriate data analysis methods, typically using statistical analysis and visualization tools, to analyze the water quality monitoring data collected during the cruise. Identify key analysis indicators, such as pollutant concentration trends and regional water quality safety. Analyze the collected water quality monitoring data to identify trends in pollutant concentrations and assess regional water quality conditions. For example, through time series analysis, identify whether there is a clear upward or downward trend in pollutant concentrations and record the results.

[0107] In this embodiment, step S6 includes the following steps:

[0108] Conduct real-time cruise concentration distribution change analysis on the full-process cruise monitoring data and construct a real-time concentration distribution change curve;

[0109] Conduct concentration mutation detection based on the instant concentration distribution change curve and locate the concentration mutation point;

[0110] Based on the concentration mutation point, the secondary pollution source is traced and located, thereby obtaining the precise pollution source location coordinates;

[0111] Dynamically adjust the intelligent coverage cruise path based on the precise pollution source positioning coordinates to obtain the real-time pollution source positioning adjustment path;

[0112] Based on the real-time pollution source positioning adjustment path, deep iterative learning optimization is carried out to build an intelligent pollution source tracing and positioning model.

[0113] In this embodiment, water quality monitoring parameters are extracted from the full-process cruise monitoring data to ensure that the data format is unified, including timestamps, location coordinates and pollutant concentrations (such as mg / L). The data is sorted in time series for subsequent analysis. For example, the water quality monitoring data of the unmanned ship at different time points are recorded to form a data set, including: time (t1, t2, t3...), location coordinates (x, y) and corresponding pollutant concentrations (C1, C2, C3...). A suitable concentration distribution change analysis method is selected. Interpolation methods (such as Kriging interpolation) are usually used to process the monitoring data, generate a concentration distribution map, and draw a concentration change curve. Set interpolation parameters, such as selecting an appropriate neighborhood range to ensure the accuracy of the interpolation. The five nearest monitoring points are usually selected for interpolation calculations. Based on the sorted data and interpolation results, an instant concentration distribution change curve is constructed. The position coordinates and the corresponding concentration values ​​are visualized to draw a curve showing the concentration change over time. For example, if the concentration values ​​are 10 mg / L, 15 mg / L, and 20 mg / L, respectively, within a specific time period, the generated curve should show a gradually increasing concentration trend, and the key features of the curve should be recorded. The criteria for defining concentration mutations are typically based on statistical methods, with thresholds set. For example, a concentration change exceeding a set value (e.g., 20%) is considered a mutation, or the standard deviation is used to identify mutation points. The set mutation detection criteria are recorded to facilitate subsequent analysis and verification. The instantaneous concentration distribution curve is analyzed to detect concentration mutation points. By calculating the magnitude of change between adjacent concentration values, mutation locations exceeding the threshold are identified. For example, if at a certain time point, the concentration suddenly increases from 10 mg / L to 30 mg / L, a change of 200%, this location is recorded as a concentration mutation point, and its specific time and coordinates are marked. The detected concentration mutation locations are recorded to form a mutation point dataset, including the mutation time, location coordinates, and the magnitude of the concentration change. For example, the mutation point location can be recorded as (x1, y1), time as t1, and concentration change as 200%, for subsequent traceability analysis. Select a suitable pollution source tracing analysis method, usually using a fluid dynamics model or a pollutant migration model, and locate the pollution source in combination with the mutation point location. Determine the input parameters of the model, including water flow velocity, concentration characteristics, and the spatial distribution of mutations. Based on the concentration mutation location point, use the selected tracing analysis model to calculate the pollution source location. According to the concentration of the mutation point and its changing trend, infer the location of the potential pollution source. For example, if the mutation point is (x1, y1) and the direction of concentration change points to a specific area, it is inferred that the pollution source may be located in this area. Record the results of the tracing analysis to form precise pollution source location coordinate data. Make sure that the record content includes the spatial coordinates of the pollution source and its corresponding concentration characteristics. For example, the recorded pollution source location is (x2, y2) and the concentration is 35 mg / L, which serves as the basis for subsequent path adjustments. According to the precise pollution source location coordinates, set the dynamic adjustment standard of the intelligent coverage cruise path.For example, if a pollution source is within the unmanned vessel's navigation path, the navigation path needs to be adjusted to ensure coverage of the pollution source. The set adjustment criteria are recorded to facilitate subsequent dynamic adjustments. Based on the precise pollution source location coordinates, the intelligent coverage cruise path is dynamically adjusted. A path planning algorithm is used to recalculate the navigation path to ensure the unmanned vessel effectively covers the newly located pollution source. For example, if the original route is from A to B, the adjusted route is from A to (x², y²) and then to B, ensuring that the pollution source is passed along the way. The adjusted intelligent coverage cruise path is recorded and a corresponding visualization is generated to visually demonstrate the route changes. For example, a map showing the pollution source and the adjusted path can be generated to help the unmanned vessel clearly understand the adjusted target during the cruise. An appropriate deep learning model, typically a neural network or reinforcement learning model, is selected to build an intelligent pollution source tracing and localization model. This model will be trained using historical data to improve localization accuracy. The model's input features are determined, including historical monitoring data, pollution source locations, and concentration fluctuation characteristics. The selected deep learning model is trained using collected cruise monitoring data to optimize parameters and enhance the model's predictive capabilities. Ensure the sufficiency and diversity of the training data. For example, models are trained using past monitoring data, and performance metrics (such as accuracy and loss) are recorded to ensure the model is validated. Trained intelligent pollution source location models are applied in real time during the cruise, monitoring new data and making real-time predictions to dynamically adjust the route. The model's predictions are recorded and compared with actual observations, and the model's performance is analyzed and iteratively optimized to improve future prediction accuracy.

[0114] In this embodiment, a multi-mode communication-based autonomous water quality monitoring unmanned vessel navigation control system is provided, which is used to execute the multi-mode communication-based autonomous water quality monitoring unmanned vessel navigation control method as described above, including:

[0115] The spatial pollution distribution module is used to collect regional water quality monitoring parameters based on ship-borne water quality monitoring sensors, conduct spatial pollution distribution mining, and construct regional pollution concentration distribution maps;

[0116] The water flow distribution evolution module is used to obtain regional satellite remote sensing maps, conduct dynamic evolution of water flow distribution, and construct a water flow path distribution network;

[0117] The diffusion prediction module is used to perform pollutant migration logic evolution and multi-region gradient diffusion prediction on the water flow path distribution network based on the regional pollution concentration distribution map, and to construct a water pollution diffusion prediction situation map;

[0118] The navigation sequence module is used to identify the highest diffusion gradient based on the water pollution diffusion prediction situation map, analyze the optimal navigation monitoring sequence, and construct the optimal navigation monitoring sequence;

[0119] The path planning module is used to plan the pollution source coverage cruise path according to the optimal navigation monitoring sequence, conduct dynamic navigation cruise monitoring, and collect full-process cruise monitoring data;

[0120] The path adjustment module is used to conduct real-time cruise concentration distribution change analysis and dynamic path adjustment based on the full-process cruise monitoring data, and to build an intelligent pollution source tracing and positioning model.

[0121] This invention uses onboard sensors to collect various water quality data in real time, enabling rapid location of pollution hotspots and ensuring timely detection of pollution issues within water bodies. The construction of spatial pollution distribution maps clearly displays pollution concentrations in different regions, providing crucial data support for subsequent water flow and pollution diffusion analysis. Data mining techniques can effectively extract pollution information from large amounts of data, enabling efficient pollution monitoring and control. Using satellite remote sensing maps and water flow evolution models, unmanned vessels can obtain dynamic water flow evolution information, including flow velocity and direction, providing a foundation for path planning and pollution diffusion prediction. The establishment of a water flow path distribution network helps understand the propagation path of water within a water body, making subsequent path planning more accurate and avoiding monitoring errors caused by changes in water flow direction. Predicting the migration and evolution of pollutants enables the path and speed of pollution diffusion to be identified in advance, facilitating the timely development of countermeasures. Multi-region gradient diffusion prediction can assess pollution diffusion in different regions, helping to determine the potential impact range of pollution and providing an accurate basis for subsequent monitoring and control. Based on diffusion prediction situation maps, early warning can be achieved, preventing the spread of pollution and reducing the difficulty and cost of pollution control. By analyzing the optimal navigation and monitoring sequence, unmanned vessels prioritize monitoring in areas with the most severe pollution spread, improving the overall efficiency of water quality monitoring. Optimizing the navigation sequence avoids duplicate monitoring or missed detection of polluted areas, thereby increasing the coverage and accuracy of water quality monitoring. Multiple unmanned vessels can work together according to the optimized navigation and monitoring sequence to avoid conflicts and enhance the efficiency of the entire monitoring system. The path planning module enables unmanned vessels to accurately cover pollution sources, ensuring comprehensive monitoring and data collection. Path planning allows unmanned vessels to avoid unnecessary route duplication and time waste, thereby improving monitoring efficiency and saving energy. Dynamic navigation allows unmanned vessels to flexibly adjust their navigation paths based on real-time conditions (such as water flow changes and sudden pollution incidents), ensuring efficient completion of monitoring tasks. By analyzing changes in cruising concentrations in real time, the system can quickly respond to sudden changes in water quality and adjust its path in a timely manner, ensuring the effective tracking and location of pollution sources. Dynamic path adjustment optimizes the unmanned vessel's monitoring path in real time based on changes in pollution concentration, enabling accurate tracing and location of pollution sources. Path adjustment allows unmanned vessels to adjust their cruising paths based on environmental and pollutant changes, achieving continuous and efficient monitoring and avoiding limitations in path design.

[0122] The present invention is therefore intended to be illustrative and non-restrictive in all respects, with the scope of the invention being defined by the appended claims rather than the foregoing description, and all changes that come within the meaning and range of equivalents of the application documents are intended to be embraced therein.

[0123] The foregoing description is intended only to provide specific embodiments of the present invention, which will enable those skilled in the art to understand and implement the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown herein, but is to be construed in the widest possible manner consistent with the principles and novel features disclosed herein.

Claims

1. A navigation control method for an autonomous water quality monitoring unmanned vessel based on multi-mode communication, characterized in that: The unmanned boat device has a ship-borne water quality monitoring sensor and a multimodal communication module; and includes the following steps: Step S1: Collect regional water quality monitoring parameters based on shipborne water quality monitoring sensors, conduct spatial pollution distribution mining, and construct a regional pollution concentration distribution map; Step S2: Obtain regional satellite remote sensing maps, perform dynamic evolution of water flow distribution, and construct a water flow path distribution network; Step S3: Based on the regional pollution concentration distribution map, the pollutant migration logic evolution and multi-region gradient diffusion prediction of the water flow path distribution network are carried out to construct a water pollution diffusion prediction situation map; Step S4: Identify the highest diffusion gradient according to the water pollution diffusion prediction situation map, analyze the optimal navigation monitoring sequence, and construct the optimal navigation monitoring sequence; Step S5: planning a pollution source coverage cruise path according to the optimal navigation monitoring sequence, performing dynamic navigation cruise monitoring, and collecting full-process cruise monitoring data; Step S6: Based on the full-process cruise monitoring data, conduct real-time cruise concentration distribution change analysis and dynamic path adjustment to build an intelligent pollution source tracing and positioning model.

2. The method for autonomous water quality monitoring unmanned vessel navigation control based on multi-mode communication according to claim 1 is characterized in that: The specific steps of step S1 are: Based on the ship-borne water quality monitoring sensors, regional water quality monitoring parameters are collected and uploaded to the cloud for data optimization to obtain optimized regional water quality monitoring parameters; Identify water pollution by optimizing regional water quality monitoring parameters and generate regional water pollution characteristics; Infer the source of water pollution based on the regional water pollution characteristics and obtain the regional water pollution source; Calculate the pollution concentration of the optimized regional water quality monitoring parameters to generate regional pollution concentration values; Based on the regional water pollution sources, the spatial pollution distribution of regional pollution concentration values ​​is mined to construct a regional pollution concentration distribution map.

3. The method for autonomous water quality monitoring unmanned vessel navigation control based on multi-mode communication according to claim 2 is characterized in that: The specific steps of collecting regional water quality monitoring parameters based on the ship-borne water quality monitoring sensor and uploading them to the cloud for data optimization to obtain optimized regional water quality monitoring parameters are as follows: identifying a plurality of available networks in an area according to the multimodal communication module; Calculating the communication distance, bandwidth, and anti-interference capability of the multiple available networks and performing a comprehensive network status evaluation to obtain the real-time signal status of each available network; Perform real-time optimal network evaluation based on the real-time signal status of each available network and mark the real-time optimal available network; Determining the dynamic change characteristics of the real-time signal status of each available network; Dynamically switching the best available network in real time according to the dynamic change characteristics to build a multi-modal intelligent switching strategy; Collect regional water quality monitoring parameters based on ship-borne water quality monitoring sensors; Uploading the regional water quality monitoring parameters to the cloud for cloud data optimization based on a multimodal intelligent switching strategy to obtain optimized regional water quality monitoring parameters; The cloud data optimization is specifically as follows: Identify sensor anomalies and errors for regional water quality monitoring parameters and extract sensor error parameters; Performing data elimination processing on the sensor error parameters to obtain error optimization monitoring parameters; Perform spatiotemporal loss detection on error optimization monitoring parameters and identify spatiotemporal loss locations; Calculate the average value of the prime error optimization monitoring parameter; The interpolation filling optimization is performed on the missing positions in time and space based on the average value to construct the optimized regional water quality monitoring parameters.

4. The method for autonomous water quality monitoring unmanned vessel navigation control based on multi-mode communication according to claim 1, characterized in that: The specific steps of step S2 are: Obtain a regional satellite remote sensing map; perform global histogram equalization optimization on the regional satellite remote sensing map to obtain a brightness optimized remote sensing map; Water flow direction identification is performed based on brightness optimized remote sensing maps to obtain regional water flow direction; identifying the runoff distribution of the brightness optimized remote sensing map and extracting multiple water flow paths; Based on the regional water flow direction, the water system trend characteristics of multiple water flow paths are analyzed one by one to generate the distribution characteristics of water flow path direction; Calculate real-time water flow velocity based on regional water quality monitoring parameters; The water flow distribution dynamics evolution is carried out according to the real-time water flow velocity and the distribution characteristics of the water flow path, and the water flow path distribution network is constructed.

5. The method for autonomous water quality monitoring unmanned vessel navigation control based on multi-mode communication according to claim 1, characterized in that: The specific steps of step S3 are: Calculate pollutant concentration gradients based on regional pollution concentration distribution maps; Calculating the concentration variation amplitude of the pollutant concentration gradient to generate a concentration variation amplitude value; Conduct in-depth mining of concentration fluctuation trends based on concentration change amplitude values ​​to generate regional concentration fluctuation trend characteristics; Conduct pollutant migration logic evolution on the water flow path distribution network to generate pollutant migration laws; Based on the migration law of pollutants, multi-region gradient diffusion prediction is carried out on the regional concentration fluctuation trend characteristics to construct a water pollution diffusion prediction situation map.

6. The method for autonomous water quality monitoring unmanned vessel navigation control based on multi-mode communication according to claim 1, characterized in that: The specific steps of step S4 are: According to the water pollution diffusion prediction situation map, the highest diffusion progressive gradient is identified and the highest diffusion progressive gradient is extracted; Analyze the water flow direction of the highest diffusion progressive gradient to generate the water flow direction of the highest pollution gradient; Based on the water flow direction with the highest pollution gradient, the direction of potential pollution sources in the water flow path distribution network is located to obtain the orientations of multiple potential pollution sources; Identify the current spatial position of the unmanned vessel and calculate the nearest potential pollution source based on the positions of multiple potential pollution sources; Calculating the pollution source distance difference of the plurality of potential pollution source positions; An optimal navigation monitoring sequence is analyzed based on the nearest potential pollution source and the distance difference between the pollution sources to construct an optimal navigation monitoring sequence.

7. The method for autonomous water quality monitoring unmanned vessel navigation control based on multi-mode communication according to claim 1, characterized in that: The specific steps of step S5 are: Based on the water flow path distribution network, the unmanned boat navigation upstream and downstream direction is determined, and the upstream and downstream directions of each path are obtained; The navigation speed of each path is calculated based on the real-time water speed and the upstream and downstream directions of each path to obtain the navigation speed of each path; According to the navigation rate of each path, the optimal navigation monitoring sequence is used to plan the pollution source coverage cruise path and construct an intelligent coverage cruise path; Dynamic navigation cruise monitoring is carried out on the water quality monitoring unmanned vessel according to the intelligent coverage cruise path, and full-process cruise monitoring data is collected.

8. The method for autonomous water quality monitoring unmanned vessel navigation control based on multi-mode communication according to claim 1, characterized in that: The specific steps of step S6 are: Conduct real-time cruise concentration distribution change analysis on the full-process cruise monitoring data and construct a real-time concentration distribution change curve; Conduct concentration mutation detection based on the instant concentration distribution change curve and locate the concentration mutation point; Based on the concentration mutation point, the secondary pollution source is traced and located, thereby obtaining the precise pollution source location coordinates; Dynamically adjust the intelligent coverage cruise path based on the precise pollution source positioning coordinates to obtain the real-time pollution source positioning adjustment path; Based on the real-time pollution source positioning adjustment path, deep iterative learning optimization is carried out to build an intelligent pollution source tracing and positioning model.

9. An autonomous water quality monitoring unmanned vessel navigation and control system based on multi-mode communication, characterized in that: The method for executing the multi-mode communication-based autonomous water quality monitoring unmanned vessel navigation control method according to claim 1 comprises: The spatial pollution distribution module is used to collect regional water quality monitoring parameters based on ship-borne water quality monitoring sensors, conduct spatial pollution distribution mining, and construct regional pollution concentration distribution maps; The water flow distribution evolution module is used to obtain regional satellite remote sensing maps, conduct dynamic evolution of water flow distribution, and construct a water flow path distribution network; The diffusion prediction module is used to perform pollutant migration logic evolution and multi-region gradient diffusion prediction on the water flow path distribution network based on the regional pollution concentration distribution map, and to construct a water pollution diffusion prediction situation map; The navigation sequence module is used to identify the highest diffusion gradient based on the water pollution diffusion prediction situation map, analyze the optimal navigation monitoring sequence, and construct the optimal navigation monitoring sequence; The path planning module is used to plan the pollution source coverage cruise path according to the optimal navigation monitoring sequence, conduct dynamic navigation cruise monitoring, and collect full-process cruise monitoring data; The path adjustment module is used to conduct real-time cruise concentration distribution change analysis and dynamic path adjustment based on the full-process cruise monitoring data, and to build an intelligent pollution source tracing and positioning model.

Images