Water quality pollution traceability analysis method and system based on intelligent unmanned ship

Abstract

The invention relates to the field of water quality pollution traceability, in particular to a water quality pollution traceability analysis method and system based on an intelligent unmanned ship. The method comprises the following steps: acquiring a multi-mode network monitoring parameter of a real-time position based on a multi-mode communication module, performing a dynamic multi-mode network intelligent switching decision, and constructing an intelligent multi-mode network switching strategy; real-time water area multi-dimensional water quality monitoring parameters of the intelligent unmanned ship are obtained according to the multi-dimensional water quality sensor, abnormal pollution parameter change detection is carried out, and abnormal change pollution parameters are marked; performing reverse water quality spatial change analysis and gradient descent iterative traceability calculation on the abnormal change pollution parameters to generate a potential pollution diffusion path; and performing intelligent traceability cruise according to the potential pollution diffusion path, and tracking and positioning the polluted water source to obtain a polluted water source point. According to the invention, efficient and accurate water quality pollution traceability is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of water pollution source tracing, and particularly to a water pollution source tracing analysis method and system based on an intelligent unmanned ship. Background Art

[0002] With the advancement of industrialization and the continuous improvement of urbanization level, the problem of water pollution has become increasingly severe and has become an important issue affecting the ecological environment and human health. Especially in areas with water resource shortages, the prevention and control of water pollution are particularly urgent. Traditional water pollution source tracing analysis methods mainly rely on manual inspections and detections at fixed monitoring stations, suffering from problems such as lagging responses, limited distribution of monitoring points, and incomplete monitoring data. These traditional methods not only have limitations in terms of spatial scope and timeliness but also have large blind spots in the process of pollution source location and tracing analysis, resulting in the inability to timely warn and effectively handle pollution incidents.

[0003] In recent years, with the rapid development of intelligent technologies and unmanned systems, intelligent unmanned ships, as a new type of water quality monitoring tool, have gradually attracted wide attention. Intelligent unmanned ships have the advantages of high efficiency, flexibility, and real-time monitoring, and can conduct long-term continuous automated monitoring over a wide range of water areas and collect water quality-related data. Compared with traditional manual inspections and fixed monitoring stations, unmanned ships can achieve dynamic monitoring and automated operations, effectively improving the detection efficiency and tracing accuracy of water pollution. By carrying a variety of sensors (such as water quality sensors, GPS positioning devices, etc.), unmanned ships can collect water quality data in the water area in real time and obtain accurate position coordinates, thus providing basic data for the location and tracking of pollution sources.

[0004] However, although intelligent unmanned ships have shown great potential in water quality monitoring, in the process of water pollution source tracing, they still face difficulties such as accurately judging the location of pollution sources, determining the pollution diffusion path, and analyzing pollution components. Traditional pollution source tracing methods often rely on empirical judgments and cannot timely and accurately analyze the spatial distribution and diffusion trend of pollution sources. Therefore, how to use the real-time monitoring data of intelligent unmanned ships and combine advanced data analysis methods for pollution source tracing has become an important technical problem in water pollution prevention and control. Summary of the Invention

[0005] To solve the above technical problems, the present invention proposes a water pollution source tracing analysis method and system based on an intelligent unmanned ship to solve at least one of the above technical problems.

[0006] To achieve the above object, the present invention provides a water pollution source tracing analysis method based on an intelligent unmanned ship. The intelligent unmanned ship is equipped with multi-dimensional water quality sensors, a multi-mode communication module, and an infrared camera, and includes the following steps:

[0007] Step S1: Obtain multi-modal network monitoring parameters of the real-time position based on the multi-mode communication module, make a dynamic multi-mode network intelligent switching decision, and construct an intelligent multi-mode network switching strategy;

[0008] Step S2: Obtain the real-time multi-dimensional water quality monitoring parameters of the intelligent unmanned ship according to the multi-dimensional water quality sensor, detect the abnormal change of pollution parameters, and mark the abnormal change pollution parameters;

[0009] Step S3: Conduct reverse water quality spatial change analysis and gradient descent iterative traceability calculation on the abnormal change pollution parameters to generate a potential pollution diffusion path;

[0010] Step S4: Conduct intelligent traceability cruising according to the potential pollution diffusion path, track and locate the polluted water source, and obtain the polluted water source point;

[0011] Step S5: Identify the hidden sewage outlet according to the polluted water source point, and conduct quantitative analysis of the pollution source components to obtain the water quality pollution component information;

[0012] Step S6: Conduct pollution source diffusion evolution based on the water quality pollution component information, and make an intelligent early warning decision based on the intelligent multi-mode network switching strategy to construct a water quality pollution traceability early warning strategy.

[0013] The present invention combines multi-mode communication technologies (such as 5G, WiFi, Beidou, etc.) to ensure that even in complex environments or areas far from network signals, the unmanned ship can maintain a stable connection. By monitoring the network status in real time (such as bandwidth, latency, packet loss rate, etc.), it can dynamically select the best communication link according to different environmental conditions, thereby maximizing the data transmission speed and reliability, and ensuring the accurate and real-time transmission of water quality monitoring data. Traditional communication technologies (such as a single network) may suffer from signal interruption or instability in certain environments. This intelligent switching strategy optimizes the network switching mechanism to ensure the continuity of the communication link, avoiding data loss or monitoring interruption caused by network failures, which is particularly important in areas with complex water conditions and weak signals. Multiple water quality sensors (such as pH, dissolved oxygen, turbidity, conductivity, etc.) are used to obtain high-precision real-time water quality data, providing rich monitoring data support for subsequent pollution source tracing. Through the comprehensive collection of multi-dimensional water quality data, the water quality of the water area can be evaluated more comprehensively, reducing potential pollution sources that may be overlooked. The detection of abnormal changes in pollution parameters can quickly identify sudden changes in water quality and promptly mark the polluted areas. This function can effectively improve the response speed and accuracy of water quality monitoring, promptly identify pollution sources, and reduce pollution spread. Through reverse water quality spatial change analysis and gradient descent iterative source tracing calculation, based on the marked abnormal changes in pollution parameters, the potential location of the pollution source and the pollution diffusion path can be inversely calculated. This process can quickly identify the pollution source, avoiding misjudgment or omission of the pollution source. The gradient descent algorithm optimizes the source tracing path, making the source tracing process more efficient. This step not only improves the accuracy of pollution source tracing but also reduces errors caused by factors such as complex environments and sensor errors, enhancing the intelligence and reliability of the entire system. Based on the potential pollution diffusion path, the intelligent unmanned ship can dynamically adjust its cruising path according to the environment and accurately track along the pollution path. Combining intelligent obstacle avoidance and path planning technologies, the system can avoid colliding with obstacles, adapt to water area changes, and optimize the navigation route, thereby efficiently and accurately locating the pollution source. The unmanned ship eliminates the inefficiencies and errors of manual operation through autonomous cruising and intelligent path planning, ensuring continuous and efficient monitoring of the water area. This automated process significantly improves the efficiency and accuracy of water pollution monitoring. By using devices such as infrared imaging to identify hidden sewage outlets and combining the sampling and monitoring data of pollution sources for quantitative analysis of pollutant types and concentrations, more in-depth information can be provided for pollution source identification. This analysis can provide a scientific basis for pollution source control and law enforcement. The detailed analysis of the water quality of the sewage outlet and its surrounding areas can accurately determine the composition (such as heavy metals, chemical substances, etc.) and concentration distribution of the pollution source, providing key data support for water quality control and environmental protection. Based on the information on the composition of the pollution source, the diffusion and evolution process of the pollution source can be simulated, predicting the possible impact of pollution events on the surrounding water area. This analysis can provide forward-looking decision-making support for pollution prevention and control, helping to quickly take emergency measures to reduce pollution spread.Combined with the dynamic switching strategy of the multi-mode communication module, the system can quickly send warning signals to relevant departments or personnel in case of pollution events. Through intelligent warning decision-making, the system can automatically evaluate the pollution risk and generate appropriate emergency response strategies. This not only improves the response speed of the system but also provides timely guidance for pollution control.

[0014] In this specification, a water quality pollution source tracing and analysis system based on an intelligent unmanned ship is provided, which is used to execute the water quality pollution source tracing and analysis method based on an intelligent unmanned ship as described above, including:

[0015] A multi-modal network switching module, which is used to obtain multi-modal network monitoring parameters of the real-time position based on the multi-mode communication module, and make dynamic multi-mode network intelligent switching decisions to construct an intelligent multi-mode network switching strategy;

[0016] A pollution change detection module, which is used to obtain real-time water area multi-dimensional water quality monitoring parameters of the intelligent unmanned ship according to multi-dimensional water quality sensors, and conduct abnormal pollution parameter change detection to mark abnormal change pollution parameters;

[0017] A reverse water quality tracing module, which is used to conduct reverse water quality spatial change analysis and gradient descent iterative tracing calculation on abnormal change pollution parameters to generate potential pollution diffusion paths;

[0018] A tracing cruise module, which is used to conduct intelligent tracing cruises according to potential pollution diffusion paths, and conduct pollution source tracking and positioning to obtain pollution source points;

[0019] A quantitative analysis module, which is used to identify hidden sewage outlets according to pollution source points and conduct quantitative analysis of pollution source components to obtain water quality pollution component information;

[0020] An intelligent warning module, which is used to conduct pollution source diffusion evolution based on water quality pollution component information, and conduct intelligent warning decisions based on the intelligent multi-mode network switching strategy to construct a water quality pollution source tracing warning strategy.

[0021] The present invention obtains the position of the unmanned ship in real time through multi-mode communication technology, and dynamically optimizes the network switching decision according to the real-time monitoring parameters of the multi-mode network. This enables the unmanned ship to continuously transmit data through the best network connection in a complex environment, ensuring the stability and smoothness of data communication. By dynamically selecting the best communication method, the unmanned ship can avoid the loss of monitoring data caused by unstable communication, improving the reliability of task execution. Especially in a complex water area environment, it ensures the real-time and accuracy of data. The multi-dimensional water quality sensors collect water quality data in real time (such as temperature, pH value, dissolved oxygen, turbidity, etc.), and the module can effectively track the dynamic changes of water quality in the water area. The module can promptly detect abnormal changes in water quality, mark the pollution change parameters, and provide data support for subsequent pollution source tracing and treatment, so as to quickly discover potential pollution risks and avoid pollution spread. Through the reverse tracing analysis of abnormal pollution parameters, the spatial position and possible diffusion path of the pollution source can be inferred, which provides a basis for accurately locating the pollution source and helps to accurately find the root cause of water quality abnormality. Using the gradient descent algorithm for calculation and optimization can efficiently and accurately identify potential pollution sources. Through the iterative calculation of the model, the tracing accuracy and accuracy of the pollution source will be improved. According to the potential pollution diffusion path obtained from the reverse analysis, the unmanned ship is guided to conduct intelligent cruising to track the pollution source in real time. Through real-time cruising, the unmanned ship can effectively track the position of the pollution source and provide data support for subsequent pollution treatment. The intelligent tracing cruise can not only ensure efficient tracking but also avoid resource waste, making the cruising process more accurate and energy-saving. According to the information of the polluted water source point, the possible hidden sewage outlets can be identified. Through the quantitative analysis of the components of the pollution source, the types and components of the pollution source (such as organic matter, heavy metals, pesticides, etc.) can be accurately identified, providing accurate data support for treatment measures. Through the analysis of the pollution source, the specific types of pollutants can be identified, providing a decision-making basis for water quality treatment and pollution source control. Accurate pollution component information will help to formulate more effective treatment measures. According to the prediction of the diffusion and evolution of the pollution source, combined with the intelligent multi-mode network switching strategy, an early warning signal for water quality pollution can be issued in advance. By predicting the diffusion trend of pollutants in advance, a time window is provided for emergency response and treatment measures. The intelligent early warning module combined with the intelligent multi-mode network switching strategy can make a rapid early warning decision based on real-time data, network conditions, and pollution source information, helping relevant departments to take timely actions to deal with pollution spread. Description of the Drawings

[0022] Figure 1 It is a schematic flowchart of the steps of a method for tracing and analyzing water quality pollution based on an intelligent unmanned ship according to the present invention;

[0023] Figure 2 It is a detailed implementation step flowchart of step S1;

[0024] Figure 3It is a schematic diagram of the detailed implementation steps of step S2;

[0025] Figure 4 It is a schematic diagram of the detailed implementation steps of step S3. Specific implementation manners

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

[0027] The embodiments of the present application provide a water quality pollution source tracing and analysis method and system based on an intelligent unmanned ship. The execution subjects of the water quality pollution source tracing and analysis method and system based on the intelligent unmanned ship include, but are not limited to, the following general computing nodes that carry this system: mechanical equipment, data processing platforms, cloud server nodes, network upload devices, etc. 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] Please refer to Figures 1 to 4 , the present invention provides a water quality pollution source tracing and analysis method based on an intelligent unmanned ship. The water quality pollution source tracing and analysis method based on the intelligent unmanned ship, the intelligent unmanned ship is equipped with multi-dimensional water quality sensors, multi-mode communication modules, and infrared cameras, and includes the following steps:

[0029] Step S1: Obtain multi-modal network monitoring parameters of the real-time position based on the multi-mode communication module, and make a dynamic multi-mode network intelligent switching decision to construct an intelligent multi-mode network switching strategy;

[0030] Step S2: Obtain the real-time water area multi-dimensional water quality monitoring parameters of the intelligent unmanned ship according to the multi-dimensional water quality sensors, and perform abnormal pollution parameter change detection to mark the abnormal change pollution parameters;

[0031] Step S3: Perform reverse water quality spatial change analysis and gradient descent iterative source tracing calculation on the abnormal change pollution parameters to generate a potential pollution diffusion path;

[0032] Step S4: Perform intelligent source tracing cruise according to the potential pollution diffusion path, and perform pollution source tracking and positioning to obtain the pollution source point;

[0033] Step S5: Identify the hidden sewage outlet according to the pollution source point, and perform quantitative analysis of the pollution source components to obtain the water quality pollution component information;

[0034] Step S6: Perform pollution source diffusion evolution based on the water quality pollution component information, and perform intelligent early warning decision-making based on the intelligent multi-mode network switching strategy to construct a water quality pollution source tracing early warning strategy.

[0035] The present invention combines multi-mode communication technologies (such as 5G, WiFi, Beidou, etc.) to ensure that even in complex environments or areas far from network signals, the unmanned ship can be stably connected. By real-time monitoring of network status (such as bandwidth, latency, packet loss rate, etc.), it is able to dynamically select the best communication link according to different environmental conditions, thereby maximizing data transmission speed and reliability, and ensuring the accurate and real-time transmission of water quality monitoring data. Traditional communication technologies (such as single network) may have signal interruption or instability in some environments. This intelligent switching strategy optimizes the network switching mechanism to ensure the continuity of the communication link, avoiding data loss or monitoring interruption caused by network failures, which is particularly important in areas with complex waters and weak signals. Multiple water quality sensors (such as pH, dissolved oxygen, turbidity, conductivity, etc.) are used to obtain high-precision real-time water quality data, providing rich monitoring data support for subsequent pollution source tracing. Through the comprehensive collection of multi-dimensional water quality data, the water quality of the water area can be more comprehensively evaluated, reducing potential pollution sources that may be missed. The abnormal pollution parameter change detection can quickly identify sudden changes in water quality and promptly mark the polluted areas. This function can effectively improve the response speed and accuracy of water quality monitoring, promptly identify pollution sources, and reduce pollution spread. Through reverse water quality spatial change analysis and gradient descent iterative source tracing calculation, it is able to reverse calculate the potential location of the pollution source and the pollution diffusion path based on the marked abnormal pollution parameter changes. This process can quickly find the pollution source, avoiding misjudgment or omission of the pollution source. The gradient descent algorithm optimizes the source tracing path, making the source tracing process more efficient. This step not only improves the accuracy of pollution source tracing but also reduces errors caused by factors such as complex environment and sensor errors, enhancing the intelligence and reliability of the entire system. Based on the potential pollution diffusion path, the intelligent unmanned ship can dynamically adjust its cruising path according to the environment and precisely track along the pollution path. Combining intelligent obstacle avoidance and path planning technologies, the system can avoid colliding with obstacles, adapt to water area changes, and optimize the navigation route, thereby efficiently and accurately locating the pollution source. The unmanned ship eliminates the inefficiency and errors of manual operation through autonomous cruising and intelligent path planning, ensuring continuous and efficient monitoring of the water area. This automated process significantly improves the efficiency and accuracy of water pollution monitoring. By using devices such as infrared imaging to identify hidden sewage outlets and combining the sampling and monitoring data of pollution sources for quantitative analysis of pollutant types and concentrations, it can provide more in-depth information for pollution source identification. This analysis can provide a scientific basis for pollution source control and law enforcement. The detailed analysis of the water quality of the sewage outlet and its surrounding areas can accurately determine the composition (such as heavy metals, chemical substances, etc.) and concentration distribution of the pollution source, providing key data support for water quality control and environmental protection. Based on the pollution source composition information, it is able to simulate the diffusion and evolution process of the pollution source and predict the possible impact on the surrounding water area of the pollution event. This analysis can provide forward-looking decision-making support for pollution prevention and control, helping to quickly take emergency measures to reduce pollution spread.Combined with the dynamic switching strategy of the multimode communication module, the system can quickly send early warning signals to relevant departments or personnel in case of pollution events. Through intelligent early warning decision-making, the system can automatically evaluate the pollution risk and generate appropriate emergency response strategies. This not only improves the response speed of the system but also provides timely guidance for pollution control.

[0036] In the embodiment of the present invention, refer to Figure 1 , which is a schematic diagram of the step flow of a water pollution source tracing and analysis method based on an intelligent unmanned ship of the present invention. In this example, the steps of the water pollution source tracing and analysis method based on the intelligent unmanned ship include:

[0037] Step S1: Obtain multimodal network monitoring parameters of the real-time position based on the multimode communication module, and make a dynamic multimode network intelligent switching decision to construct an intelligent multimode network switching strategy;

[0038] In this embodiment, a suitable multi-mode communication module is selected, which usually includes multiple communication methods such as 4G, 5G, Wi-Fi, and Bluetooth. Ensure that the module supports fast switching and data transmission flexibility. Integrate the multi-mode communication module into the control system of the intelligent unmanned boat, configure the communication interface, and ensure seamless docking with other system modules (such as GPS positioning module, sensor module, etc.). Start the multi-mode communication module and perform self-check to ensure that all communication functions are normal. The self-check includes checking signal strength, network availability, connection stability, etc. Record the initial state of the device, including available network types, signal strength, and current GPS coordinates for subsequent data analysis and decision-making. Start the GPS positioning system on the unmanned boat to obtain the geographical location information of the unmanned boat in real time. Ensure that the accuracy of the GPS module is within meters to obtain accurate position information. Set the data collection frequency, for example, obtain position data once per second, and record the timestamp, longitude and latitude, speed, and heading of each data point. Transmit the obtained real-time position information through the multi-mode communication module to ensure data real-time. Select the communication method with the strongest current signal for data transmission to reduce latency. At the same time, store the position data in the local database of the unmanned boat for subsequent analysis and traceability. Each record should include information such as time, position, signal strength, and network type. Monitor the parameters of multiple network environments in real time, including signal strength, latency, bandwidth, and network availability. These parameters are crucial for determining the optimal communication method. Set the monitoring frequency (for example, once every 5 seconds) and record the performance metrics under different network conditions for subsequent analysis. Through the multi-mode communication module, collect the performance data of each network type in real time. Ensure the accuracy and integrity of the data, including the signal strength (in dBm) of each network, latency (in milliseconds), and bandwidth (in Mbps). Conduct a preliminary analysis of the collected data to identify the change trends in the current network environment, such as signal fluctuations and network switching frequencies. Based on the real-time obtained network monitoring parameters, design a dynamic switching decision algorithm. This algorithm should be able to automatically select the optimal communication method according to the network performance metrics. Adopt a weighted decision model and set weights according to parameters such as signal strength, latency, and bandwidth. For example, signal strength accounts for 60%, latency accounts for 30%, and bandwidth accounts for 10% to ensure that the selected network has the best overall performance. During the operation of the algorithm, evaluate the performance metrics of the current network in real time and compare them with the preset thresholds. When the performance of a certain network is lower than the set threshold, trigger the switching decision. According to the decision result, automatically switch to a network with stronger signal and better performance. For example, if the Wi-Fi signal strength is lower than -70 dBm, automatically switch to the 4G network. Record the decision-making process and results of each switch, including the network performance metrics before and after the switch, switch time, and switch frequency. These data will be used for subsequent optimization and adjustment of the algorithm.Regularly evaluate the handover strategy, and optimize the decision-making algorithm and weight settings in combination with the feedback in actual applications to improve the intelligence level of handover.

[0039] Step S2: Obtain the real-time multi-dimensional water quality monitoring parameters of the intelligent unmanned ship according to the multi-dimensional water quality sensors, and perform abnormal pollution parameter change detection to mark the abnormal change pollution parameters;

[0040] In this embodiment, suitable multi-dimensional water quality sensors are selected, usually including pH sensors, turbidity sensors, dissolved oxygen sensors, ammonia nitrogen sensors, total phosphorus sensors, etc. These sensors should have high sensitivity and fast response capabilities to ensure the accuracy of real-time monitoring. Integrate the water quality sensors into the control system of the intelligent unmanned boat to ensure seamless docking with the data acquisition module and perform necessary calibration to improve the measurement accuracy. Start the water quality sensors and conduct self-checks to confirm that all sensor functions are normal. The self-check process should include inspections of the sensor's response speed, sensitivity, and calibration status. Record the initial calibration data and sensor status, including the measurement range and sensitivity of each sensor, for subsequent analysis and adjustment. Set the real-time data acquisition frequency of the water quality sensors, for example, obtain water quality parameters once per second. Ensure that the system can stably collect key water quality indicators such as pH value, turbidity, dissolved oxygen, ammonia nitrogen, and total phosphorus. Use the data recording module to store the water quality parameters collected each time in the database of the unmanned boat in real-time to ensure the integrity and traceability of the data. During the monitoring process, continuously record the changes in each water quality parameter, including the timestamp, sensor readings, and environmental conditions (such as water temperature, flow rate, etc.). Regularly check the working status of the sensors to ensure their normal operation, and promptly detect and handle possible faults or abnormal conditions. Based on the historical data and standards of water quality monitoring, establish detection criteria for abnormal changes. Usually, these criteria include the normal range and warning values of each water quality parameter. For example, the normal range of pH value is 6.5 - 8.5, and the excessive turbidity value is 5 NTU. Set dynamic thresholds. When the change of a certain water quality parameter exceeds the set standard (such as exceeding 10% of the normal range), it is determined as an abnormal change. Use data analysis algorithms (such as the standard deviation method or Z-score method) to analyze the changes in water quality parameters in real-time. For each monitoring period, calculate the deviation between the current parameter and the historical average value and determine whether it exceeds the set threshold. When an abnormal change is detected, the system automatically marks the parameter and records relevant information, including the abnormal value, timestamp, and sensor location, etc. Store the marked abnormal pollution parameters in the database and generate a detailed record of abnormal changes. The record should include the specific value of the abnormal parameter, the change range, and its possible impacts. Regularly generate reports on abnormal changes to summarize the abnormal situations during the monitoring period and provide a basis for subsequent environmental governance and decision-making. Once an abnormal change in pollution parameters is detected, the system will automatically trigger an alarm mechanism to notify relevant personnel for further analysis and processing. The alarm information should include key information such as the abnormal parameter, location, and time. Ensure that the alarm information can be quickly sent to the monitoring center through the multi-mode communication module for timely response measures. After detecting an abnormality, increase the monitoring frequency (such as once every 5 seconds) to more closely track the water quality changes and ensure a quick response to potential pollution sources. Combine the abnormal data and environmental conditions for comprehensive analysis to evaluate the possible influence range and consequences of the pollution source and provide a scientific basis for formulating subsequent treatment plans.

[0041] Step S3: Conduct reverse water quality spatial variation analysis and gradient descent iterative traceability calculation on the abnormal change pollution parameters to generate potential pollution diffusion paths;

[0042] In this embodiment, data on abnormal change pollution parameters previously monitored are collected and sorted out, including outliers, timestamps, geographical locations, and the change trends of water quality parameters, etc. These data will serve as the basis for reverse analysis. The historical data of abnormal parameters are recorded for subsequent analysis, ensuring that the data cover a sufficient time span and spatial distribution. For example, the water quality parameter readings per hour within the past 24 hours. The collected data are cleaned to remove possible noise and incorrect data to ensure the accuracy of subsequent analysis. Missing values and outliers are checked and processed using interpolation methods or other data filling methods. The data are standardized to eliminate the influence of different parameter units and magnitudes, making it suitable for subsequent spatial change analysis. Spatial interpolation techniques (such as Kriging interpolation, inverse distance weighting method, etc.) are used to conduct spatial change analysis on abnormal change pollution parameters. An appropriate interpolation method is selected to estimate the spatial distribution of pollutants in the water area based on the known outlier data. The parameters of interpolation are set, such as the search radius and weights, to ensure that the generated spatial change model can truly reflect the distribution characteristics of pollutants. Based on the spatial model, reverse analysis is carried out to identify possible source points of pollutants. By tracing the change trajectory of pollutants in time and space, the potential location of the pollution source is determined. Combining the flow characteristics of the water area (such as water flow velocity and direction), the diffusion path and diffusion speed of pollutants in the water area are analyzed. A hydrodynamic model is used to simulate the influence of water flow on pollutant diffusion. A pollutant spatial change map is generated to show the distribution of abnormal change pollution parameters and the possible source locations. In the form of a heat map or contour map, the data are visualized for easy analysis. The parameter settings and results of each analysis step are recorded for subsequent evaluation and verification. A gradient descent algorithm is designed to optimize the estimation of the pollutant diffusion path. The algorithm should consider the abnormal changes in water quality parameters, flow velocity, flow direction, and the influence of other environmental factors. A loss function is determined, such as the goodness of fit based on pollutant concentration and spatial change, as the optimization objective. The goal is to minimize the loss function to find the optimal diffusion path. Based on the initial path, the gradient descent method is used for iterative estimation. In each iteration, the path is adjusted according to the loss value of the current path, updating the direction and step size to find a better solution. In each iteration, the loss value of the current path is calculated, and according to the changes in the hydrodynamic model and water quality parameters, the direction and range of the path are dynamically adjusted to ensure the rationality of the estimated path. When the set number of iterations is reached or the loss value converges, the iteration is stopped, and the final pollution diffusion path is recorded. Ensure that the path can reflect the potential pollution source and its diffusion characteristics. Result verification is carried out by comparing with historical data and on-site monitoring results to evaluate the accuracy of the estimated path. If necessary, the model parameters and algorithm settings are further adjusted according to the evaluation results. The estimated potential pollution diffusion path and its analysis results are sorted out into a report. The report should include the visual illustration of the path, the analysis of key parameters, the possible location of the pollution source and its influence range.Describe the implementation process, parameter settings, and results of each step in detail in the report to make it operable and valuable for reference.

[0043] Step S4: Conduct intelligent traceability cruising according to the potential pollution diffusion path, and conduct tracking and positioning of the polluted water source to obtain the polluted water source point;

[0044] In this embodiment, based on the previously deduced pollution diffusion path, the cruising route of the intelligent unmanned ship is designed. The cruising route should cover potential pollution sources and affected areas to ensure real-time monitoring and positioning of pollution sources. The cruising route is divided into multiple monitoring points, and each monitoring point should include specific longitude and latitude information and a predetermined stay time for detailed water quality detection and data collection. Determine the cruising speed and data collection frequency. For example, set the unmanned ship to cruise at a speed of 5 kilometers per hour and stay at each monitoring point for 5 minutes for water quality detection. Combine environmental factors such as water flow speed and wind direction to optimize the cruising route to ensure that the unmanned ship can reach key monitoring areas in the shortest time. Start the water quality monitoring module on the unmanned ship, including multi-dimensional water quality sensors. Ensure that the sensors are calibrated and perform a self-check before the cruise starts to confirm their normal working status. During the cruise, real-time collect water quality parameters such as pH value, dissolved oxygen, turbidity, ammonia nitrogen, and total phosphorus to ensure the accuracy and reliability of the data. Set the data collection frequency. For example, record water quality parameters once per minute and transmit the collected data to the control system of the unmanned ship for storage in real time. Each data record should include a timestamp, location, monitoring parameters, and their corresponding environmental conditions for subsequent analysis and tracking. Based on the collected water quality parameter data, design a pollution source tracking and positioning algorithm. The algorithm should be able to identify abnormal changes in water quality parameters and analyze them in combination with the potential pollution diffusion path. Adopt multivariate analysis methods (such as principal component analysis or clustering analysis) to identify the change patterns of water quality parameters to judge the possible location of the pollution source. During the cruise, analyze the water quality data in real time. When a certain water quality parameter is monitored to exceed the set threshold, the system will automatically mark the location and perform further data collection and analysis. Combine historical monitoring data and real-time parameter changes to dynamically adjust the cruising route and give priority to going to possible pollution source locations for detailed detection. Use the GPS positioning system to record the precise location of each monitoring point and compare it with the changes in water quality parameters to verify the positioning accuracy of the pollution source. By comparing the water quality data of different monitoring points, confirm the actual location of the pollution source and record the characteristic parameters of the pollution source. Once the existence of the pollution source is confirmed at a certain monitoring point, immediately conduct more detailed sampling and analysis to verify the types and concentrations of pollutants. Record the sampling location, time, and water sample parameters. Mark the confirmed pollution source points and their characteristics to ensure the integrity and traceability of the data. Organize the confirmation results of the pollution source points into a report, which should include information such as the specific location of the pollution source, water quality parameters, types of potential pollutants, and their concentrations. Describe the implementation process of each step, data collection, and analysis methods in detail in the report to provide a scientific basis for subsequent treatment plans.

[0045] Step S5: Identify hidden sewage outlets based on the pollution source points and conduct quantitative analysis of the pollution source components to obtain water quality pollution component information;

[0046] In this embodiment, all data related to the polluted water source points are collected, including water quality monitoring results, historical pollution records, basin characteristics, and environmental conditions. These data will serve as the basis for identifying hidden sewage outlets. Through Geographic Information System (GIS) tools, the location information of the polluted water source points is integrated and analyzed with the hydrological data, land use conditions, and historical distribution of sewage outlets in the basin to identify potential sewage outlet locations. Statistical analysis methods (such as control charts or outlier detection algorithms) are used to process water quality data to identify the spatio-temporal distribution characteristics of abnormal pollutant concentrations. Focus on the pattern of pollutant diffusion in the water area to find clues to unknown pollution sources. Combining spatial analysis techniques, hotspot analysis (such as Getis-Ord Gi* statistic) is used to identify areas with abnormal pollutant concentrations, guiding the identification of hidden sewage outlets. Based on the results of data analysis, potential sewage outlet locations are selected for on-site investigations. Through on-site inspections, observe possible sewage outlet exits, sewage flow conditions, and surrounding environmental characteristics. Use multi-dimensional water quality sensors on intelligent unmanned vessels to take immediate samples at suspicious locations to verify whether the water quality parameters match the data of the polluted water source points. Further confirm the location of the hidden sewage outlet based on on-site data. Collect water samples near the confirmed hidden sewage outlet, ensuring that the sampling process follows the Standard Operating Procedure (SOP) to avoid sample contamination. Usually, water samples are collected at multiple points for comparative analysis. Record information such as the collection time, location, and environmental conditions (such as water temperature, flow rate) of each sample to ensure the integrity and traceability of the data. According to the characteristics of the water samples, select appropriate analysis methods for quantitative analysis of the components of the pollution source. Commonly used methods include Gas Chromatography-Mass Spectrometry (GC-MS), High Performance Liquid Chromatography (HPLC), and Atomic Absorption Spectrometry (AAS). Determine the analysis objectives and standard methods for each pollutant to ensure the accuracy and reliability of the data. For example, for heavy metal pollution, AAS can be used to analyze the concentrations of metal ions such as lead, cadmium, and mercury. Organize the analysis results of the water quality pollution components into a comprehensive report, which should include detailed information on the components of the pollution source, possible pollutant types, concentrations, and their potential sources. Combining the characteristics of the polluted water source points and the identification results of the hidden sewage outlets, analyze the causes and diffusion paths of the pollution to provide a scientific basis for the treatment plan. Based on the pollution component information, put forward corresponding treatment suggestions, including pollutant removal technologies, monitoring frequencies, and selection of treatment measures. Ensure that the suggestions are operable and targeted. It is recommended to monitor the pollution source regularly to evaluate the treatment effect and adjust the treatment measures according to the monitoring data to ensure the continuous improvement of water quality.

[0047] Step S6: Conduct the diffusion and evolution of the pollution source based on the water quality pollution component information, and make an intelligent early warning decision based on the intelligent multi-mode network switching strategy to construct a water quality pollution traceability and early warning strategy.

[0048] In this embodiment, the water quality pollution component information obtained from the previous analysis is collected, including the types of pollutants, concentrations, and their spatial distribution data, which will provide the basic input for the pollution source diffusion model.

[0049] Select a suitable diffusion model, such as the Gaussian diffusion model, Lagrangian particle tracking model, or hydrodynamic model, to describe the diffusion process of pollutants in the water body. When selecting the model, consider environmental factors such as water flow velocity, wind speed, and temperature. According to historical data and on-site monitoring results, set model parameters, such as water flow velocity (e.g., 0.5 m / s), diffusion coefficient (e.g., 0.1 m 2 / s), and calibrate the model to improve its accuracy. Conduct a preliminary simulation to verify the rationality and accuracy of the model. By comparing with the actual monitoring data, continuously adjust the model parameters to ensure that the model can truly reflect the diffusion characteristics of pollutants. Based on the determined parameters and model, conduct a simulation of the pollution source diffusion evolution. Through numerical simulation, predict the spatial distribution changes of pollutants at different time periods and generate a time series of pollutant concentrations. Record the pollutant concentration distribution maps at each time step to ensure the integrity and visualization of the simulation results, enabling relevant personnel to intuitively understand the diffusion dynamics of pollutants. While conducting the pollution source diffusion simulation, continuously monitor the performance of the multi-mode network environment, including signal strength, bandwidth, and delay, to ensure the real-time and stability of data transmission. Set a regular monitoring frequency (e.g., once every 5 minutes) and record the network performance data for subsequent intelligent handover decisions. Design an intelligent handover algorithm based on real-time network performance data. When it is detected that the network performance deteriorates (e.g., the signal strength is lower than -70 dBm), the system automatically switches to a network with stronger signal (e.g., from Wi-Fi to 4G or 5G). Introduce a priority setting in the algorithm. For example, during data transmission, preferentially select a network with a larger bandwidth to ensure the real-time transmission of pollution diffusion simulation data and warning information. According to the decision of the intelligent handover algorithm, transmit the pollution source diffusion simulation results and water quality monitoring data to the control center in real time. Ensure that the warning information can be quickly and accurately sent to relevant management personnel. During data transmission, the system automatically generates warning information, including pollutant concentration, diffusion range, and possible affected areas. Based on the water quality monitoring data and pollution source diffusion simulation results, formulate clear warning criteria. Usually, it includes warning thresholds for different pollutant concentrations. For example, when the ammonia nitrogen concentration exceeds 0.5 mg / L, a warning is triggered. Set a three-level warning mechanism, with level one warning for slight pollution, level two for moderate pollution, and level three for severe pollution, to ensure that the hierarchical response of the warning mechanism is timely and effective. During the monitoring process, the system compares the current water quality parameters with the warning criteria in real time. When it is detected that a certain parameter exceeds the set threshold, the corresponding warning level is automatically triggered. Transmit the warning information to the decision-making center quickly through the multi-mode network to ensure that relevant personnel can timely understand the pollution situation and take corresponding measures.

[0050] In this embodiment, refer to Figure 2 , which is a schematic diagram of the detailed implementation steps of step S1. In this embodiment, the detailed implementation steps of the said step S1 include:

[0051] Locate the real-time position of the intelligent unmanned ship and obtain the multi-modal network monitoring parameters of the real-time position based on the multi-mode communication module;

[0052] Calculate the delay, packet loss rate and bandwidth parameters of the multi-modal network monitoring parameters;

[0053] Conduct real-time multi-index parameter change analysis according to the delay, packet loss rate and bandwidth parameters, and generate the change characteristics of multi-monitoring indexes of each network;

[0054] Conduct real-time network status evaluation according to the change characteristics of multi-monitoring indexes of each network to generate the real-time network status evaluation value of each network;

[0055] Based on the real-time network status evaluation value of each network, make a dynamic multi-mode network intelligent switching decision and construct an intelligent multi-mode network switching strategy.

[0056] In this embodiment, a multi-mode communication module is installed on the unmanned ship, supporting multiple communication protocols (such as 4G, 5G, Wi-Fi, and satellite communication). Ensure that the module can switch under different network environments to obtain real-time position information. Configure a Global Navigation Satellite System (GNSS) receiver to obtain the geographical location data of the unmanned ship in real time and integrate it with the multi-mode communication module to ensure the accuracy and real-time nature of the positioning information. Regularly (for example, every second) collect the real-time position data of the unmanned ship through the multi-mode communication module, including information such as longitude, latitude, altitude, and speed, and at the same time collect network monitoring parameters. Transmit the collected position data and network monitoring parameters to the ground control center through the set communication protocol for subsequent analysis. During the data transmission process, record the timestamps of each sent and received data packet to calculate the network latency. The calculation method of latency is the reception time minus the transmission time, and record the latency situation of each data packet. Use statistical methods (such as mean, variance) to process the latency data, identify the change trends and outliers of the latency, and ensure the accuracy and reliability of the data. Calculate the packet loss rate by comparing the number of successfully received data packets with the total number of sent data packets. Packet loss rate = (number of lost data packets / total number of sent data packets) × 100%. Record the packet loss rates in different network modes and analyze their impact on the real-time positioning of the unmanned ship. For example, the packet loss rate may increase significantly in areas with weak signals. Regularly monitor the network bandwidth through a network bandwidth testing tool (such as iperf) and record the bandwidth changes in different time periods. Analyze the stability and change trends of the bandwidth, identify the periods of network congestion or instability for subsequent network status evaluation. Organize the data of latency, packet loss rate, and bandwidth parameters into a table and arrange them in chronological order for comprehensive analysis. Ensure that the timestamps of the data correspond to the position information of the unmanned ship so that the network performance and position data can be correlated during subsequent analysis. Use data mining and statistical analysis methods (such as time series analysis) to extract the change characteristics of multi-monitoring indicators for each network. Identify the correlations and change trends among latency, packet loss rate, and bandwidth. Generate charts (such as line charts, bar charts) to display the changes in monitoring indicators under different network conditions for intuitive analysis. Analyze the relationship between the change characteristics of network monitoring indicators and the operating state of the unmanned ship. For example, whether the increase in packet loss rate is related to the increase in latency in a specific area. Record the analysis results to provide a basis for subsequent network status evaluation. Set the index weights for network status evaluation according to latency, packet loss rate, and bandwidth, and formulate an evaluation formula. For example, the comprehensive score of latency, packet loss rate, and bandwidth can be used as the main basis for network status evaluation. Set the evaluation threshold to determine the evaluation levels of different network states (such as excellent, good, poor). According to the real-time collected monitoring parameters, apply the set formula to calculate the real-time status evaluation value for each network. Record the evaluation results of each network in different time periods. Generate an evaluation report, detailing the status evaluation values of each network and their changes, to provide a basis for subsequent decision-making.Design a dynamic switching decision algorithm based on the real-time network status evaluation value. This algorithm should be able to intelligently determine when to switch the network according to the changes in the evaluation value. Set switching conditions, for example, when the evaluation value of a certain network is lower than the set threshold, automatically switch to other networks to maintain the positioning accuracy and communication stability of the unmanned ship. Implement an intelligent multi-mode network switching strategy in the control system of the unmanned ship, monitor the network status in real time and perform dynamic switching. Ensure that the switching process is seamlessly connected to avoid affecting real-time positioning. Record each link of the switching operation, including the switching time, the network status before and after switching and its impacts, for subsequent analysis. Conduct system tests on the implemented switching strategy, monitor the positioning accuracy and stability of the unmanned ship under different network conditions. Optimize the strategy according to the test results to ensure that the switching decision can adapt to the changing network environment and improve the real-time positioning ability and communication quality of the unmanned ship.

[0057] In this embodiment, refer to Figure 3 , which is a schematic diagram of the detailed implementation steps of step S2. In this embodiment, the detailed implementation steps of the said step S2 include:

[0058] Obtain the real-time multi-dimensional water quality monitoring parameters of the intelligent unmanned ship according to the multi-dimensional water quality sensors;

[0059] Calculate the average values of pH value, dissolved oxygen, turbidity and conductivity according to the real-time multi-dimensional water quality monitoring parameters;

[0060] Conduct multi-sampling point water quality change analysis according to the average values of pH value, dissolved oxygen, turbidity and conductivity to generate water quality change characteristics of multiple sampling points;

[0061] Perform parameter change trend evolution on the water quality change characteristics of multiple sampling points to generate a multi-parameter change trend curve;

[0062] Conduct abnormal pollution parameter change detection on the multi-parameter change trend curve and mark the abnormal change pollution parameters.

[0063] In this embodiment, multi-dimensional water quality sensors are installed on the intelligent unmanned ship, including pH sensors, dissolved oxygen sensors, turbidity sensors, and conductivity sensors. These sensors should have the ability to collect real-time data to ensure accurate monitoring of water quality parameters in different water environments. During the installation process, ensure that the sensors are well-connected to the control system of the unmanned ship, can transmit monitoring data in real-time, and perform necessary calibration to improve the measurement accuracy. Configure a data acquisition system to obtain water quality monitoring parameters from the sensors regularly (such as every second or every minute). Record the data of each sensor, including pH value, dissolved oxygen concentration (mg / L), turbidity (NTU), and conductivity (μS / cm). Transmit the collected data to the ground control center or cloud platform in real-time through a wireless communication module for subsequent analysis and processing. Store the real-time monitoring data in a secure database to ensure the integrity and traceability of the data. Record the timestamp, sensor location, and environmental conditions (such as temperature, weather, etc.) of each data point to provide a basis for subsequent analysis. Organize the collected water quality monitoring data, remove outliers and noise to ensure the accuracy of the data. Statistical methods such as moving average or median filtering can be used to smooth the data. Classify the data according to sampling points and time to facilitate the subsequent analysis of water quality changes at different sampling points. For each sampling point, calculate the average values of pH, dissolved oxygen, turbidity, and conductivity. For example, if 60 data points are recorded at a certain sampling point within 10 minutes, calculate the arithmetic mean of these data points. Record the average value of each sampling point and store the results in the database for subsequent analysis. Extract change characteristics based on the average water quality parameters of different sampling points. By comparing the average values of each sampling point, identify the spatial distribution characteristics and change patterns of water quality. Use statistical analysis methods (such as analysis of variance) to compare the water quality parameters of different sampling points to determine which sampling points have significant differences. For the water quality changes at each sampling point, draw a water quality change characteristic diagram. For example, heat maps or line charts can be used to show the change trends of pH, dissolved oxygen, turbidity, and conductivity at each sampling point. Record the change trends and characteristics, analyze possible reasons, such as the influence of the surrounding environment, the existence of pollution sources, etc., to provide a basis for subsequent water quality monitoring. Use data visualization tools to plot the water quality parameters of each sampling point into multi-parameter change trend curves. Each curve should clearly mark the time axis and parameter values to facilitate the observation of change trends. During the plotting process, ensure that the curves of different parameters use different colors or styles for easy distinction. By observing the multi-parameter change trend curves, analyze the correlation between different water quality parameters. For example, whether the increase in turbidity is related to the decrease in dissolved oxygen, and explore the internal relationship of water quality changes. Record the results of trend analysis to provide a reference basis for abnormal pollution detection. Select suitable abnormal detection methods, such as statistical control charts, machine learning algorithms, or threshold-based detection methods. Set reasonable thresholds to identify abnormal changes.For each water quality parameter (pH, dissolved oxygen, turbidity, and conductivity), a normal range is set based on historical data, and any deviation beyond this range is considered abnormal. During real-time monitoring, continuous anomaly detection is performed on the water quality parameters at the sampling points. Whenever an abnormal change is detected, the parameter is immediately recorded and marked, along with a timestamp and sampling point information. An alarm system is generated to send a warning to the control center in a timely manner when a parameter becomes abnormal, ensuring a quick response. The results of anomaly detection are summarized to generate a report, which details the abnormal changes at each sampling point, including the abnormal parameter, occurrence time, and its possible impacts. Based on the results of anomaly detection, potential pollution sources and their impacts on water quality are analyzed to provide a scientific basis for subsequent water quality management.

[0064] In this embodiment, refer to Figure 4 , which is a schematic diagram of the detailed implementation steps of step S3. In this embodiment, the detailed implementation steps of step S3 include:

[0065] Perform a gradient analysis of water pollution changes for the abnormal change pollution parameters to generate a water quality pollution parameter change gradient;

[0066] Conduct a reverse water quality spatial change analysis based on the water quality pollution parameter change gradient to generate water quality pollution spatial distribution data;

[0067] Identify the direction of the fastest pollution concentration for the water quality pollution spatial distribution data and extract the direction of the fastest pollution concentration;

[0068] Perform gradient descent iterative traceability calculation based on the direction of the fastest pollution concentration to generate a water quality pollution traceability trajectory;

[0069] Predict the hydrodynamic evolution based on the water quality pollution traceability trajectory to generate a potential pollution diffusion path.

[0070] In this embodiment, the marked abnormal change pollution parameter data are collected, including water quality parameters (such as pH, dissolved oxygen, turbidity, and conductivity) at different sampling points and their timestamps. Ensure data integrity, remove outliers and noise, and ensure the accuracy of subsequent analysis. Normalize the data to facilitate comparison and analysis between different parameters and avoid analysis biases caused by different dimensions. Use spatial interpolation methods (such as Kriging interpolation) to perform spatial interpolation on the water quality parameters at each sampling point to generate a continuous distribution map of water quality parameters. Calculate the gradient of pollution change by comparing the pollution parameters at adjacent sampling points. Based on the pollution change gradient data, establish a spatial change model of water quality pollution. The model needs to consider the influence of environmental factors such as water flow direction, wind speed, and temperature on water quality changes. Adopt a hydrodynamic model to simulate the diffusion characteristics of pollutants in the water body, combine with the water flow velocity and direction, and analyze the movement trajectory of pollutants in the water area. Determine the source location of pollutants through reverse analysis. According to the gradient change, reverse calculate the diffusion path of pollutants from the high-concentration area to the low-concentration area, and calculate the pollution concentration at each sampling point. Record the concentration change at each point, generate the spatial distribution data of pollutants in the water area, and indicate the highest concentration and diffusion range of pollutants. Summarize the spatial distribution data of water quality pollution obtained by reverse analysis to generate a complete water area pollution distribution map. Ensure that the change trend of pollution concentration and the source location are marked on the map to provide a basis for subsequent pollution diffusion analysis. Use the generated spatial distribution data of water quality pollution to perform analysis in the concentration direction. By calculating the change rate of concentration in different directions, identify the fastest direction of pollution diffusion. Adopt the calculation method of directional derivative to identify the direction with the most significant concentration change. This process can be achieved through methods such as locally weighted regression to improve the accuracy of direction identification. Mark the fastest pollution concentration direction on the pollution distribution map, and use arrows or other symbols to represent the diffusion trend and speed. Ensure that the graph is intuitive for subsequent analysis and decision-making. Record the specific values of the fastest pollution concentration direction and the corresponding sampling point information to generate a detailed report describing the dynamic characteristics of pollution diffusion and its potential impacts. Based on the fastest pollution concentration direction, construct a gradient descent traceability calculation model. The model should be able to simulate the movement trajectory of pollutants in the water flow and perform reverse calculation. Set traceability parameters such as pollutant concentration, diffusion rate, and environmental conditions to ensure the accuracy and effectiveness of the model. Through iterative calculation, gradually advance towards the source. In each step, update the concentration distribution and diffusion direction of pollutants according to hydrodynamics and concentration changes. Record the results of each iteration to generate the traceability trajectory of pollutants, including the concentration change and time information at each point. Plot the generated water quality pollution traceability trajectory into a graph to show the calculated path of the pollution source. Through visualization, intuitively display the diffusion process of pollutants and their impact on the environment. Based on the traceability trajectory data, construct a hydrodynamic evolution prediction model. The model needs to consider the influence of the flow characteristics of the water body, temperature, wind speed, and other environmental factors on pollution diffusion.Model the hydrodynamic of water flow using numerical simulation methods (such as the finite element method or the finite difference method) to predict the future diffusion path of pollutants. Use the evolution prediction model to calculate the diffusion path and concentration change of pollutants in the future time. Generate a map of potential pollution diffusion paths indicating the areas that may be affected by the pollution. Record the prediction results, analyze the diffusion characteristics of pollutants under different environmental conditions, and provide a scientific basis for response measures.

[0071] In this embodiment, step S4 includes the following steps:

[0072] Conduct intelligent traceability cruising according to the potential pollution diffusion path and collect real-time cruising infrared imaging images;

[0073] Perform image brightness enhancement processing on the real-time cruising infrared imaging images to obtain brightness-optimized cruising infrared images;

[0074] Perform visual recognition of water area obstacles on the brightness-optimized cruising infrared images and mark the water area obstacle nodes;

[0075] Calculate the target water area points according to the potential pollution diffusion path;

[0076] Perform intelligent path planning based on the water area obstacle nodes and the target water area points to generate an intelligent traceability cruising path;

[0077] Track and locate the polluted water source based on the intelligent traceability cruising path to obtain the polluted water source point.

[0078] In this embodiment, a cruising plan for the intelligent unmanned ship is formulated according to the previously generated potential pollution diffusion paths. This plan should consider factors such as the flow characteristics of the water area, wind speed, weather conditions, and water depth to optimize the cruising efficiency and safety. During the planning process, ensure that the cruising path covers all potential pollution sources and their diffusion directions to comprehensively monitor the water quality changes in the water area. Configure the infrared imaging device on the unmanned ship to ensure that it can perform real-time imaging under various environmental conditions. The device should have high sensitivity and high resolution to capture small temperature changes and water area obstacles. Set the data acquisition frequency, usually performing infrared imaging once per second, to obtain continuous monitoring image data and ensure real-time assessment of the water area conditions. During the cruising process, real-time collect infrared imaging images and store them in the computing system of the unmanned ship. Each image should contain a timestamp and location coordinates for subsequent analysis and processing. Ensure that the format and resolution of the images are suitable for subsequent processing, usually using the TIFF or PNG format to retain the image quality. Use image processing algorithms to perform brightness enhancement processing on the collected infrared images. Common methods include histogram equalization and gamma correction, which can effectively improve the contrast and brightness of the images and make the water area features more obvious. During the processing, monitor the brightness change of each image to ensure that the enhanced image can clearly display the obstacles and other features of interest in the water area. Conduct a visual inspection of the processed images to ensure that the brightness enhancement effect meets the expectations. Several key images can be selected for quantitative analysis to evaluate the quality and stability of the enhancement effect. Based on the enhanced infrared images, apply image recognition algorithms (such as convolutional neural network CNN) for visual recognition of water area obstacles, which may include floating objects, shore plants, and other objects that may potentially affect the navigation of the unmanned ship. The dataset used for training the model should include infrared images of various water area obstacles to improve the accuracy and robustness of the recognition. During the recognition process, the algorithm should automatically mark the coordinate positions of the obstacles and generate corresponding node information, which should include the type, size, location of the obstacles, and their relative distance from the unmanned ship. Record the relevant information of each obstacle node and combine it with the real-time cruising data for subsequent path planning and decision support. According to the potential pollution diffusion paths, calculate the target water area points, which should be located in the core area of pollution diffusion, usually the place with the highest pollution concentration. Use the previous water quality monitoring data and combine with the water flow model to evaluate the pollution characteristics of the target water area points and determine the degree of their impact on water quality. Integrate the data of potential pollution paths, obstacle nodes, and target water area points, and analyze the relationships between different points. Ensure that the selection of target water area points can best reflect the dynamic changes of pollution diffusion. Based on the obstacle nodes and target water area points, use path planning algorithms (such as A* algorithm or Dijkstra algorithm) for intelligent path planning. The goal is to generate an optimal cruising path to avoid obstacles and quickly reach the target water area points.During the planning process, factors such as the flow characteristics of the water area, the relative positions of obstacles, the speed of the unmanned ship, and the safety distance are considered. The generated intelligent traceability cruise path is visualized and displayed on the control interface of the unmanned ship. Through graphical display, it is convenient for the operator to monitor and adjust the navigation route in real time. During the actual cruise process, the path is updated in real time to cope with unforeseen obstacles or environmental changes, ensuring the safety and efficiency of the unmanned ship. A high-precision positioning system is configured on the unmanned ship, which can obtain the position of the unmanned ship in real time and combine it with the path planning system to accurately track the polluted water source. Combining real-time water quality monitoring data, continuously evaluate the pollution level of the area passed by the unmanned ship to determine whether it is close to the pollution source. During the cruise, according to the changes in water quality monitoring data and its relationship with the intelligent traceability cruise path, gradually locate potential polluted water source points. Record the pollution characteristics of each point, including concentration, type, and its influence range. By comparing the water quality data at different time periods, confirm the existence and changes of the pollution source, and generate a detailed monitoring report. Feed back the results of tracking and positioning to the control center for environmental governance and subsequent monitoring. Ensure the accuracy of all data records and analysis results to support decision-making. According to the positioning results, formulate corresponding treatment plans and take timely measures to reduce or eliminate the impact of water pollution on the ecological environment.

[0079] In this embodiment, the specific steps of performing intelligent traceability cruise according to the potential pollution diffusion path and collecting real-time cruise infrared imaging images are as follows:

[0080] Start the hidden tracking mode of the intelligent unmanned ship, turn off the visible light, enable the infrared camera and lidar scanning, and perform sequential traceability cruise along the potential pollution diffusion path to collect real-time cruise infrared imaging images.

[0081] In this embodiment, select the "Stealth Tracking Mode" in the control system of the unmanned boat. This mode aims to reduce interference and detectability in the water environment. In this mode, turn off all visible light sources to ensure that the unmanned boat is not easily discovered at night or in complex environments. Check the system status of the unmanned boat to ensure that its battery power is sufficient and all sensors (including infrared cameras and lidar) are in normal working condition. Conduct a system self-check to ensure that the sensors can collect data normally and perform real-time processing. Configure the infrared camera to ensure that it can collect high-resolution images in low-light environments. Set a high sensitivity and an appropriate frame rate (e.g., 30 frames per second) to capture subtle temperature changes and underwater features. The lidar system should be calibrated to ensure that it can accurately measure distances and environmental features. Set the laser emission frequency and scanning angle to obtain comprehensive water environment data. Based on the previous pollution diffusion path data, formulate the cruising route of the unmanned boat. This route should cover all potential pollution sources and diffusion areas to ensure comprehensive monitoring and information collection. Ensure that the path planning takes into account the water flow direction, wind speed, obstacle positions, and the speed of the unmanned boat to optimize the cruising efficiency and ensure safety. Start the navigation system of the unmanned boat and cruise according to the set path. Utilize autonomous driving technology to ensure that the unmanned boat can autonomously avoid obstacles and adjust its heading in real time. During the cruise, continuously monitor the position and speed of the unmanned boat to ensure that it operates within the set path. Perform precise positioning through the GPS and Inertial Navigation System (INS) to provide real-time feedback. Start the infrared camera and begin to collect real-time infrared imaging images of the water area. Set an appropriate exposure time and gain to improve the clarity and contrast of the images. Ensure that the camera is highly sensitive to temperature changes on the water surface and underwater. Dynamically adjust the parameters of the infrared camera according to environmental conditions (such as water temperature, air temperature, weather changes) to adapt to different monitoring requirements. Store the collected infrared images in the computing system of the unmanned boat in real time, ensuring that the image format (such as TIFF or PNG) is suitable for subsequent processing. At the same time, record the timestamp and position coordinates of each image for subsequent analysis and traceability. Set a reasonable storage strategy in the data storage to ensure that during a long-term cruise, the system can effectively manage the storage space and avoid data loss. Start the lidar system for environmental scanning. Set the scanning frequency and range of the lidar to obtain comprehensive water area terrain and obstacle information. Usually set the scanning range of the lidar within 30 meters to ensure high-precision measurement. During the cruise, the lidar should collect distance data in real time and generate environmental point cloud data to construct a three-dimensional model of the water area. Integrate the infrared images with the lidar data to generate a comprehensive environmental information map. Integrate the data of the two sensors through a data fusion algorithm (such as Kalman filtering) to improve the accuracy of environmental recognition. Further identify obstacles and potential pollution sources in the water area by analyzing the thermal features in the infrared images and the point cloud data generated by the lidar to ensure the safe travel of the unmanned boat during the cruise.In the control center of the unmanned ship, a real-time monitoring interface is set up to display the current cruising status, infrared images, lidar data, and the position of the unmanned ship. Ensure that the operator can always grasp the environmental changes and potential risks during the cruise. The monitoring system should have an alarm function. When abnormal situations (such as suddenly appearing obstacles or abnormal temperatures) are detected, an alarm is automatically issued so that the operator can take timely measures.

[0082] In this embodiment, the specific steps of step S5 are as follows:

[0083] When the intelligent unmanned ship reaches the polluted water source point, start the infrared camera to conduct a panoramic scan of the target water area to obtain a panoramic infrared image of the target water area;

[0084] Identify the hidden sewage outlets from the panoramic infrared image of the target water area and mark the hidden sewage outlets;

[0085] Collect water samples from the surrounding water quality of the hidden sewage outlets and extract the water quality sampling parameters of the hidden sewage outlets;

[0086] Classify the water quality pollution of the water quality sampling parameters of the hidden sewage outlets to generate the water quality pollution type;

[0087] Calculate the pollutant concentration based on the water quality sampling parameters of the hidden sewage outlets to generate the pollutant concentration value;

[0088] Conduct quantitative analysis of the pollution source components based on the water quality pollution type and the pollutant concentration value to obtain the water quality pollution component information.

[0089] In this embodiment, after the unmanned boat reaches the polluted water source point, the infrared camera is activated for panoramic scanning. Ensure that the camera has been adjusted to the optimal working state, including appropriate exposure time and gain settings, so as to capture clear images under different lighting conditions. Set the infrared camera to the wide-angle mode to cover a larger area of water, ensuring that comprehensive information on the hidden sewage outlet and the surrounding environment can be obtained. Activate the infrared camera for omnidirectional scanning. Set the scanning period, for example, scan once per second, and generate a complete infrared imaging data set, which will be used for subsequent analysis. The data collected should include the timestamp of each frame of the image, the position of the unmanned boat, and the environmental conditions of the water area (such as water temperature, air temperature, etc.) for subsequent processing and analysis. Store the collected panoramic infrared imaging images in real time in the computing system of the unmanned boat, ensuring that the image format is suitable for subsequent processing (such as TIFF or PNG) to retain the image quality. Record the relevant information of each image and ensure the secure storage of the data for subsequent analysis and traceability. Process the panoramic infrared imaging images to identify hidden sewage outlets. Use image processing techniques (such as edge detection, region growing algorithms, etc.) to analyze the temperature anomaly regions in the images, which are usually related to the sewage outlets. Apply a machine learning model to train the features for identifying hidden sewage outlets, ensuring that the model can accurately identify the position and shape of the sewage outlets. The data set should include images of different types of sewage outlets to improve the robustness of the model. Once a hidden sewage outlet is identified, immediately mark its coordinate position and relevant information (such as temperature value, relative position) on the infrared imaging image. Markings and annotations can be added to the image in a graphical way. Record the detailed information of each mark, including the position, identification basis, and environmental conditions for subsequent water quality sampling and analysis. According to the position of the marked hidden sewage outlet, formulate a surrounding water quality sampling plan. Ensure that the selection of sampling points can reflect the impact of the sewage outlet on water quality. Usually, multiple sampling points near the sewage outlet should be selected. Determine the sampling depth and position, considering factors such as water flow direction, wind speed, and water temperature to avoid interference during the sampling process. Use a high-precision water quality sampler to collect water samples at the predetermined positions. Multiple water samples should be collected at each sampling point to ensure the reliability and accuracy of the data. Record the specific position, sampling time, and sampling depth of each sampling point for subsequent data analysis. Record the information of the collected water samples in the database, including the water sample number, sampling position, time, and relevant environmental data. Ensure the integrity and traceability of all data. Analyze the water quality sampling parameters around the hidden sewage outlet, usually including pH value, dissolved oxygen, turbidity, and conductivity, etc. Use high-precision water quality sensors to measure these parameters in real time and record the data. Statistical methods are used for data analysis to calculate the average value, standard deviation, etc. of each parameter to evaluate the overall water quality status. According to the collected water quality parameters, classification algorithms (such as support vector machine SVM or decision tree) are used for water quality pollution classification, and these algorithms should be trained to identify different types of water pollution sources.By comparing the sample data with known pollution types, the pollution type of the sample is determined and the pollution classification results are generated. The pollution classification results of each sampling point are recorded and a detailed water quality pollution classification report is generated. The report should include information such as pollution type, possible pollution sources and their impacts to provide a basis for subsequent analysis. According to the water quality sampling parameters, the pollutant concentration value is calculated. Usually, a known formula or model is used for calculation, such as inference based on the chemical composition and concentration in the water sample. A variety of methods are used for verification, such as comparison with standard solutions, to ensure the accuracy of the calculation results. The calculated pollutant concentration values ​​are recorded in the database and associated with the sampling point information for subsequent analysis. Ensure the integrity and traceability of the data. Generate a detailed pollutant concentration value report, which should include the concentration value of each sampling point and its corresponding pollution type, to provide basic data for subsequent pollution source analysis. Based on the water quality pollution type and pollutant concentration value, select an appropriate component analysis method, such as gas chromatography (GC) or liquid chromatography (HPLC), to quantitatively analyze the pollutant components in the water sample. Determine the experimental conditions required for the analysis, including sample processing, instrument calibration and analysis parameter setting. Conduct pollutant composition analysis in the laboratory and analyze water samples using selected instruments. Based on the analysis results, quantify the concentration of each pollutant and its relative proportion. During the analysis, record the conditions and results of each step to ensure the accuracy and repeatability of the analysis. Summarize the results of the pollution source component analysis and generate a detailed water quality pollution component information report. The report should include the concentration, component ratio and potential impact of each pollutant. Based on the pollution component information, provide a scientific basis for subsequent treatment measures to ensure the restoration and protection of the water environment.

[0090] In this embodiment, the specific steps of step S6 are:

[0091] Conduct sewage flow distribution analysis on hidden sewage outlets to obtain sewage outlet water flow distribution data;

[0092] Based on the water flow distribution data of the sewage outlet and the information of water pollution components, the pollution source diffusion evolution is carried out to generate the water pollution diffusion evolution characteristics;

[0093] Evaluate the pollution risk level of water pollution diffusion evolution characteristics and obtain the water pollution diffusion risk assessment results;

[0094] Based on the water pollution spread risk assessment results and the intelligent multi-mode network switching strategy, intelligent early warning decisions are made to build a water pollution source tracing early warning strategy.

[0095] In this embodiment, a flow sensor is set near the hidden sewage outlet to monitor the water flow rate and flow of the sewage outlet in real time. The sensor should have high precision and reliability to ensure the accuracy of the data. According to the water flow characteristics, select a suitable flow measurement device (such as an electromagnetic flowmeter or an ultrasonic flowmeter). Conduct multi-point sampling and record the flow data of the sewage outlet at different time periods to capture the changing trend of the water flow. Usually, the sampling period is once per minute, and the data record should include the timestamp, flow value, and environmental conditions (such as water level, air temperature, etc.). According to the collected flow data, use a hydrodynamic model (such as a two-dimensional water flow model) to model the water flow distribution of the sewage outlet. The model should consider the direction and velocity of the water flow and the geometry of the sewage outlet to generate a distribution map of the sewage flow. Use numerical simulation methods (such as the finite element method or the finite difference method) to simulate the water flow and identify the areas where the flow velocity changes, especially the water flow dynamics around the sewage outlet. According to the water flow distribution data of the sewage outlet, establish a mathematical model for pollutant diffusion. Use a diffusion equation (such as the convection-diffusion equation) to describe the movement and diffusion process of pollutants in the water body. The model should integrate the water flow rate, pollutant concentration, and their physical and chemical properties (such as solubility, sedimentation rate, etc.) to achieve accurate diffusion simulation. Use numerical simulation techniques (such as Monte Carlo simulation or Lagrangian method) to simulate the diffusion process of pollutants. Set the initial conditions (such as the pollutant concentration at the sewage outlet) and boundary conditions to simulate the dynamic changes of pollutants in the water area. Record the pollutant concentration distribution at different time points, analyze its spatial variation characteristics, and determine the speed and range of pollutant diffusion. Generate a characteristic map of the source pollution diffusion evolution to show the concentration changes and diffusion paths of pollutants in the water area. Through the analysis results, identify the main direction of pollutant diffusion and the potential impact areas. Record the key parameters (such as the maximum concentration value, diffusion range) to provide a basis for subsequent risk assessment and early warning decision-making. According to the characteristics and diffusion characteristics of water pollution, formulate a pollution risk level assessment standard. The assessment standard should include indicators such as pollutant concentration, diffusion speed, and environmental sensitivity of the affected area. Set the thresholds for different risk levels, such as low, medium, and high risks, to ensure the operability and scientificity of the assessment results. According to the data of the diffusion evolution characteristics, calculate the pollution risk level of each area. Use the established standard to compare the pollutant concentration and diffusion characteristics with the risk level to evaluate the risk of specific areas. Adopt statistical analysis methods (such as multiple regression analysis) to quantify the influence of different factors on the risk level and ensure the accuracy of the assessment results. Record the risk assessment results of each area and generate a detailed risk assessment report. The report should include the risk level, potential impacts, and corresponding management suggestions to provide support for subsequent decision-making. Based on the results of the pollution diffusion risk assessment, design an intelligent early warning decision-making model. The model should combine real-time monitoring data and historical data to evaluate the dynamic changes of pollution risks.Set the warning threshold. When the pollution risk exceeds the set value, the system will automatically issue an alarm so that corresponding measures can be taken in a timely manner. In the warning decision-making model, integrate the intelligent multi-mode network switching strategy to ensure the stability and real-time performance of data transmission in different network environments (such as 4G, 5G, Wi-Fi, etc.). Ensure that the warning information can be transmitted to the relevant management departments and the public in a timely manner to provide support for emergency response. Once the system issues a warning, immediately activate the corresponding emergency response mechanism, including monitoring the affected area, controlling the pollution source, and implementing treatment measures. Collect the feedback data after the warning is implemented, evaluate the effectiveness of the warning strategy, and adjust and optimize the strategy according to the feedback results to ensure that subsequent warning work is more scientific and effective.

[0096] In this embodiment, the specific steps for making an intelligent warning decision according to the water quality pollution diffusion risk assessment result and the intelligent multi-mode network switching strategy, and constructing a water quality pollution source tracing warning strategy are as follows:

[0097] The water quality pollution diffusion risk assessment result is specifically divided into three levels of warnings;

[0098] The intelligent warning decision is specifically as follows:

[0099] Level 1 alarm: The water quality parameters are slightly exceeded, record the data but do not trigger a remote alarm;

[0100] Level 2 alarm: Clear pollution signs are detected, the optimal network is selected based on the intelligent multi-mode network switching strategy, and a warning is sent to the monitoring center;

[0101] Level 3 alarm: Confirm a major pollution event and activate the emergency response mechanism.

[0102] In this embodiment, clear three - level early warning standards are formulated based on water quality monitoring data and pollution diffusion characteristics. The standards for each early warning level should be specific and quantifiable. For example: Level 1 alarm: The water quality parameters slightly exceed the standard, exceeding the normal range but not reaching the warning line (e.g., the pH value slightly exceeds the range of 6.5 - 8.5). Level 2 alarm: Obvious pollution signs are detected, such as the concentration of certain key pollutants (e.g., ammonia nitrogen, total phosphorus) exceeding the preset warning value (e.g., ammonia nitrogen exceeds 0.5 mg / L). Level 3 alarm: A major pollution event is confirmed, and the pollutant concentration seriously exceeds the standard (e.g., heavy metals exceed the national standard by 10 times). In the water quality monitoring system, water quality parameter data are collected in real - time, including pH value, dissolved oxygen, turbidity, and the concentration of specific pollutants. An automated data analysis system is set up to continuously evaluate the real - time data. Through the set thresholds and standards, the current water quality status is automatically judged, and the corresponding early warning level is triggered. Automatic evaluation is carried out after each data collection (e.g., once per minute) to ensure timely response to water quality changes. When the water quality parameters slightly exceed the standard (e.g., the pH value is between 6.3 - 6.5 or 7.5 - 7.8), the system automatically records the relevant data without triggering a remote alarm. This process should ensure the integrity of the data for subsequent analysis. A data recording module is set up to automatically store the exceeded standard data in the database, including the timestamp, the exceeded value, and the corresponding environmental conditions (such as temperature, flow rate, etc.). The system regularly generates a data analysis report summarizing the exceeded standard situations. The report should include the exceeded standard parameters, occurrence frequencies, and their possible environmental impacts, and these data will provide a basis for subsequent risk assessment. The report is archived to ensure the traceability of the data and support possible subsequent investigations and treatments. The water quality parameters continue to be monitored. If a deteriorating trend (such as continuous exceeding of the standard) is found, the system will enter the monitoring state of the Level 2 alarm to ensure dynamic tracking of water quality changes. When obvious pollution signs (such as the concentration of a certain pollutant exceeding the set warning value) are detected, the system will immediately trigger the Level 2 alarm. At this time, the system will select the optimal network for data transmission according to the intelligent multi - mode network switching strategy. The basis for selecting the optimal network includes network stability, bandwidth, and latency, etc., to ensure that the alarm information can be sent to the monitoring center in a timely and accurate manner. The system automatically generates early warning information, including the exceeded water quality parameters, concentration values, location, and time, etc., and sends the early warning to the monitoring center through the selected network (such as 4G / 5G / Wi - Fi). Ensure that the monitoring center can quickly respond after receiving the early warning information and take corresponding monitoring and response measures in a timely manner. Once the Level 2 alarm is triggered, the system will increase the monitoring frequency (e.g., once every 10 seconds) and continuously record the changes in water quality parameters for a quick assessment of the pollution source. The monitoring center will analyze the pollution trend based on the real - time data and evaluate whether to upgrade to the Level 3 alarm. When a major pollution event is confirmed (such as heavy metal concentration exceeding the standard by 10 times, or a toxic substance is detected), the system will trigger the Level 3 alarm and immediately activate the emergency response mechanism.The mechanism includes a variety of emergency measures, such as notifying relevant environmental protection departments, starting on-site sampling and monitoring procedures, etc. Once a level-three alarm is triggered, the system will automatically send an emergency notice to relevant management departments to ensure that they are informed of the severity and urgency of the incident in a timely manner. Activate the on-site emergency monitoring team to quickly go to the site for sampling and analysis, confirm the pollution source and assess the pollution scope. After the emergency response, conduct a detailed environmental investigation and water quality assessment. Record the sampling data, analysis results and emergency response measures at each step to ensure the integrity and accuracy of the data. Generate a detailed emergency response report, including pollution source analysis, environmental impact assessment and subsequent treatment suggestions, to provide reference for long-term environmental protection work.

[0103] In this embodiment, a water pollution source tracing and analysis system based on an intelligent unmanned ship is provided, which is used to execute the water pollution source tracing and analysis method based on an intelligent unmanned ship as described above, and includes:

[0104] A multimodal network switching module, which is used to obtain multimodal network monitoring parameters of the real-time position based on a multimode communication module, make a dynamic multimode network intelligent switching decision, and construct an intelligent multimodal network switching strategy;

[0105] A pollution change detection module, which is used to obtain real-time water area multimodal water quality monitoring parameters of the intelligent unmanned ship according to a multi-dimensional water quality sensor, detect abnormal pollution parameter changes, and mark abnormal change pollution parameters;

[0106] A reverse water quality tracing module, which is used to perform reverse water quality spatial change analysis and gradient descent iterative tracing calculation on abnormal change pollution parameters to generate a potential pollution diffusion path;

[0107] A tracing cruise module, which is used to perform intelligent tracing cruise according to the potential pollution diffusion path, track and locate the pollution source, and obtain the pollution source point;

[0108] A quantitative analysis module, which is used to identify hidden sewage outlets according to the pollution source point and perform quantitative analysis of the pollution source components to obtain water pollution component information;

[0109] An intelligent warning module, which is used to perform pollution source diffusion evolution based on the water pollution component information, make an intelligent warning decision based on the intelligent multimodal network switching strategy, and construct a water pollution source tracing warning strategy.

[0110] The present invention obtains the position of the unmanned ship in real time through multi-mode communication technology, and dynamically optimizes the network switching decision according to the real-time monitoring parameters of the multi-mode network. This enables the unmanned ship to continuously transmit data through the best network connection in a complex environment, ensuring the stability and fluency of data communication. By dynamically selecting the best communication method, the unmanned ship can avoid the loss of monitoring data caused by unstable communication, improving the reliability of task execution. Especially in a complex water area environment, it ensures the real-time and accuracy of data. Through multi-dimensional water quality sensors, water quality data (such as temperature, pH value, dissolved oxygen, turbidity, etc.) are collected in real time, and the module can effectively track the dynamic changes of water quality in the water area. The module can timely detect abnormal changes in water quality, mark the pollution change parameters, and provide data support for subsequent pollution source tracing and treatment, so as to quickly discover potential pollution risks and avoid pollution spread. Through the reverse tracing analysis of abnormal pollution parameters, the spatial position and possible diffusion path of the pollution source can be inferred, which provides a basis for accurately positioning the pollution source and helps to accurately find the root cause of water quality abnormality. Using the gradient descent algorithm for calculation and optimization can efficiently and accurately identify potential pollution sources. Through the iterative calculation of the model, the tracing accuracy and accuracy of the pollution source will be improved. According to the potential pollution diffusion path obtained from the reverse analysis, the unmanned ship is guided to conduct intelligent cruising to track the pollution source in real time. Through real-time cruising, the unmanned ship can effectively track the position of the pollution source and provide data support for subsequent pollution treatment. The intelligent tracing cruise can not only ensure efficient tracking but also avoid resource waste, making the cruising process more accurate and energy-saving. According to the information of the polluted water source point, possible hidden sewage outlets can be identified. Through the quantitative analysis of the components of the pollution source, the types and components of the pollution source (such as organic matter, heavy metals, pesticides, etc.) can be accurately identified, providing accurate data support for treatment measures. Through the analysis of the pollution source, the specific types of pollutants can be identified, providing a decision-making basis for water quality treatment and pollution source control. Accurate pollution component information will help to formulate more effective treatment measures. According to the prediction of the diffusion and evolution of the pollution source, combined with the intelligent multi-mode network switching strategy, an early warning signal of water quality pollution can be sent in advance. By predicting the diffusion trend of pollutants in advance, a time window is provided for emergency response and treatment measures. The intelligent early warning module combined with the intelligent multi-mode network switching strategy can make a rapid early warning decision according to real-time data, network conditions, and pollution source information, helping relevant departments to take timely actions to respond to pollution spread.

[0111] Therefore, in any aspect, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the application documents are intended to be included in the present invention.

[0112] The above are only specific embodiments of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but rather to the broadest scope consistent with the principles and novel features invented herein.

Claims

1. A water pollution source tracing analysis method based on an intelligent unmanned boat, characterized in that: The intelligent unmanned boat is equipped with a multi-dimensional water quality sensor, a multi-mode communication module, and an infrared camera, and includes the following steps: Step S1: Acquire multi-mode network monitoring parameters of real-time location based on the multi-mode communication module, make dynamic multi-mode network intelligent switching decisions, and build an intelligent multi-mode network switching strategy; Step S2: obtaining the real-time multi-dimensional water quality monitoring parameters of the intelligent unmanned boat according to the multi-dimensional water quality sensor, and performing abnormal pollution parameter change detection, marking the abnormal change pollution parameters; Step S3: Perform reverse water quality spatial change analysis and gradient descent iterative source tracing on abnormal pollution parameters to generate potential pollution diffusion paths; Step S4: Conduct intelligent tracing cruise according to the potential pollution diffusion path, and track and locate the polluted water source to obtain the polluted water source point; Step S5: Identify hidden sewage outlets according to polluted water sources, and conduct quantitative analysis of pollution source components to obtain water pollution component information; Step S6: Based on the water pollution component information, the pollution source diffusion evolution is carried out, and based on the intelligent multi-mode network switching strategy, intelligent early warning decision-making is carried out to build a water pollution source tracing early warning strategy.

2. The water pollution source tracing analysis method based on intelligent unmanned boat according to claim 1 is characterized in that: The specific steps of step S1 are: Locate the real-time position of the intelligent unmanned ship and obtain the multi-modal network monitoring parameters of the real-time position based on the multi-mode communication module; Calculating the delay, packet loss rate and bandwidth parameters of the multimodal network monitoring parameters; Perform real-time multi-index parameter change analysis based on latency, packet loss rate, and bandwidth parameters to generate multi-monitoring indicator change characteristics for each network; Perform real-time network status assessment based on the changing characteristics of multiple monitoring indicators of each network to generate a real-time network status assessment value for each network; Based on the real-time network status evaluation value of each network, dynamic multi-mode network intelligent switching decisions are made to build an intelligent multi-mode network switching strategy.

3. The water pollution source tracing analysis method based on intelligent unmanned boat according to claim 1 is characterized in that: The specific steps of step S2 are: Acquire real-time multi-dimensional water quality monitoring parameters of the intelligent unmanned boat based on multi-dimensional water quality sensors; Calculate the average values ​​of pH value, dissolved oxygen, turbidity and conductivity based on the real-time multi-dimensional water quality monitoring parameters of the water area; Water quality change analysis of multiple sampling points is performed based on the average values ​​of pH value, dissolved oxygen, turbidity and conductivity to generate water quality change characteristics of multiple sampling points; Evolve the parameter change trend of water quality change characteristics at multiple sampling points and generate a multi-parameter change trend curve; Abnormal pollution parameter changes are detected on the multi-parameter change trend curve, and abnormal pollution parameters are marked.

4. The water pollution source tracing analysis method based on intelligent unmanned boat according to claim 1 is characterized in that: The specific steps of step S3 are: Conduct water pollution change gradient analysis on abnormally changing pollution parameters to generate water pollution parameter change gradient; According to the gradient of water pollution parameters, reverse water quality spatial change analysis is conducted to generate water pollution spatial distribution data; Identify the fastest pollution concentration direction for water pollution spatial distribution data and extract the fastest pollution concentration direction; Perform gradient descent iterative tracing according to the direction of the fastest pollution concentration to generate a water pollution source trajectory; The hydrodynamic evolution is predicted based on the water pollution source trajectories to generate potential pollution diffusion paths.

5. The water pollution source tracing analysis method based on intelligent unmanned boat according to claim 1 is characterized in that: The specific steps of step S4 are: Conduct intelligent tracing cruise according to the potential pollution diffusion path and collect real-time cruise infrared imaging images; Perform image brightness enhancement processing on the real-time cruise infrared imaging image to obtain a brightness optimized cruise infrared image; Perform visual identification of water obstacles on the brightness-optimized cruise infrared image and mark water obstacle nodes; Calculate target water areas based on potential pollution diffusion paths; Intelligent path planning is performed based on water obstacle nodes and target water points to generate intelligent tracing cruise paths; Based on the intelligent tracing cruise path, the polluted water source is tracked and located to obtain the polluted water source point.

6. The water pollution source tracing analysis method based on intelligent unmanned boat according to claim 5 is characterized in that: The specific steps of performing intelligent tracing cruise according to the potential pollution diffusion path and collecting real-time cruise infrared imaging images are as follows: Start the stealth tracking mode of the intelligent unmanned ship, turn off visible light, enable infrared camera and lidar scanning, conduct sequential tracing cruise along the potential pollution diffusion path, and collect real-time cruise infrared imaging images.

7. The water pollution source tracing analysis method based on intelligent unmanned boat according to claim 1 is characterized in that: The specific steps of step S5 are: When the intelligent unmanned boat reaches the polluted water source, it starts the infrared camera to perform a panoramic scan of the target waters and obtain a panoramic infrared image of the target waters; Use panoramic infrared imaging of the target water area to identify hidden sewage outlets and mark them; Sampling water quality around hidden sewage outlets and extracting water quality sampling parameters of hidden sewage outlets; Classify water pollution based on water quality sampling parameters of hidden sewage outlets to generate water pollution types; Calculate pollutant concentrations based on hidden sewage outfall water quality sampling parameters to generate pollutant concentration values; Based on the water pollution type and pollutant concentration value, the pollution source components are quantitatively analyzed to obtain water pollution component information.

8. The water pollution source tracing analysis method based on intelligent unmanned boat according to claim 1 is characterized in that: The specific steps of step S6 are: Conduct sewage flow distribution analysis on hidden sewage outlets to obtain sewage outlet water flow distribution data; Based on the water flow distribution data of the sewage outlet and the information of water pollution components, the pollution source diffusion evolution is carried out to generate the water pollution diffusion evolution characteristics; Evaluate the pollution risk level of water pollution diffusion evolution characteristics and obtain the water pollution diffusion risk assessment results; Based on the water pollution spread risk assessment results and the intelligent multi-mode network switching strategy, intelligent early warning decisions are made to build a water pollution source tracing early warning strategy.

9. The water pollution source tracing analysis method based on intelligent unmanned boat according to claim 1 is characterized in that: The specific steps of making intelligent early warning decisions based on the water pollution diffusion risk assessment results and the intelligent multi-mode network switching strategy and constructing a water pollution source tracing early warning strategy are as follows: The water pollution diffusion risk assessment results are specifically divided into three levels of warning; The intelligent early warning decision is specifically: Level 1 alarm: When water quality parameters slightly exceed the standard, data will be recorded but no remote alarm will be triggered; Level 2 alarm: When clear signs of pollution are detected, the optimal network is selected based on the intelligent multi-mode network switching strategy, and an early warning is sent to the monitoring center; Level 3 alarm: Confirmation of a major pollution incident and activation of the emergency response mechanism.

10. A water pollution source tracing analysis system based on an intelligent unmanned boat, characterized in that: The method for tracing the source of water pollution based on an intelligent unmanned boat as claimed in claim 1 comprises: The multi-mode network switching module is used to obtain multi-mode network monitoring parameters of real-time location based on the multi-mode communication module, make dynamic multi-mode network intelligent switching decisions, and build intelligent multi-mode network switching strategies; The pollution change detection module is used to obtain the real-time multi-dimensional water quality monitoring parameters of the intelligent unmanned ship based on the multi-dimensional water quality sensor, and to detect abnormal pollution parameter changes and mark abnormal pollution parameter changes; The reverse water quality tracing module is used to perform reverse water quality spatial change analysis and gradient descent iterative tracing of abnormal pollution parameters to generate potential pollution diffusion paths; The source tracing patrol module is used to conduct intelligent source tracing patrols based on the potential pollution diffusion path, and track and locate the polluted water source to obtain the polluted water source point; The quantitative analysis module is used to identify hidden sewage outlets based on polluted water sources and conduct quantitative analysis of pollution source components to obtain water pollution component information; The intelligent early warning module is used to analyze the diffusion evolution of pollution sources based on water pollution component information, make intelligent early warning decisions based on intelligent multi-mode network switching strategies, and build a water pollution source tracing early warning strategy.

Images