Intelligent water quality monitoring method and system for collaborative sampling of bionic fish school and unmanned aerial vehicle, and computer equipment

Abstract

The invention relates to the technical field of environment monitoring, in particular to an intelligent water quality monitoring method and system for collaborative sampling of a bionic fish school and an unmanned aerial vehicle and computer equipment. The method comprises the following steps: dividing monitoring grid units by using GIS data, establishing a layered communication architecture, dynamically deploying a bionic fish school to carry out real-time water quality monitoring, and scheduling and optimizing resource allocation through a fuzzy rule; historical pollution event data and real-time sensing data are integrated to construct a water quality evaluation index system, and a Nash equilibrium strategy is adopted to determine an optimal weight to generate a dynamic pollution situation cloud chart; constructing an inferior fingerprint database to realize rapid identification of pollution events and trigger a two-stage response mechanism; and finally, combining the bionic fish school sampling data and the unmanned aerial vehicle pre-diffusion coordinate to dynamically simulate the effect of the treatment measure. Air-water integrated efficient monitoring is achieved, the accuracy and timeliness of water quality anomaly detection are improved, and comprehensive technical support is provided for water area environment protection.

Description

Technical Field

[0001] The present invention relates to the field of environmental monitoring technology, and in particular to an intelligent water quality monitoring method, system and computer equipment for collaborative sampling of bionic fish schools and drones. Background Art

[0002] With the increasing prevalence of environmental pollution, water quality monitoring has become a crucial tool for protecting the aquatic ecosystem. The continuous development of water quality monitoring technology has exposed a series of significant shortcomings in many past and current solutions. For example, patent document "CN115792165A - A Method and System for Intelligent Monitoring of Environmental Water Quality" demonstrates that this technology primarily utilizes a monitoring module, a communication module, and a display module to achieve water quality monitoring. The monitoring module comprises a water quality detection unit, a processor, and an edge computing module. The water quality detection unit uses a variety of sensors, such as temperature, turbidity, and pH, to collect water quality information. The processor then transmits this information to the edge computing module for screening and processing, ultimately computing it on a cloud computing platform and displaying it on a display terminal. However, this solution has significant shortcomings. While it improves some of the issues associated with manual monitoring, it is limited by a fixed sensor deployment model. Fixed sensors struggle to provide flexible and comprehensive coverage in vast, complex, and ever-changing waters, such as large river basins and offshore areas. They are unable to capture dynamic changes in water quality in a timely manner. Especially in areas with turbulent currents and complex terrain, monitoring data is prone to omissions or deviations, significantly compromising the integrity and accuracy of monitoring.

[0003] In recent years, with the advancement of artificial intelligence, the Internet of Things, and robotics, water quality monitoring using intelligent devices such as drones and bionic fish has become a research hotspot. However, existing technologies lack a robust synergy between drones and bionic fish, failing to fully leverage the strengths of both for efficient and accurate water quality monitoring. For example, challenges remain, such as dynamically allocating monitoring resources based on the geographic information system and hydrological characteristics of target waters, optimizing sampling strategies based on historical pollution incident data, and rapidly identifying and responding to sudden pollution incidents. Summary of the invention

[0004] To address these issues, this paper proposes an intelligent water quality monitoring method and computer equipment that uses collaborative sampling between bionic fish swarms and drones. Through layered collaboration between drones and bionic fish swarms, this method optimizes the matching of monitoring resources with hydrological characteristics, improving the real-time, accurate, and intelligent nature of water quality monitoring. This enhances the ability to respond to sudden pollution incidents, enabling rapid response, dynamic resource scheduling, and three-dimensional situation visualization.

[0005] The technical solutions of the present invention are as follows:

[0006] One of the technical solutions of the present invention is to provide an intelligent water quality monitoring method for cooperative sampling of bionic fish schools and unmanned aerial vehicles, including:

[0007] Dividing monitoring grid units based on the geographical information system data of the target water area, establishing a hierarchical communication architecture for unmanned aerial vehicles and bionic fish schools, dynamically deploying bionic fish schools according to the environmental parameters of the monitoring grid units, and the unmanned aerial vehicle remote sensing and bionic fish school sensors real-time monitor water quality anomalies, and scheduling bionic fish schools through fuzzy rules to achieve the initial adaptation of monitoring resources and hydrological characteristics;

[0008] The unmanned aerial vehicle collects historical pollution event data and real-time fish school sensing data, constructs a water quality evaluation index system, adopts the Nash equilibrium strategy, based on game theory to evaluate the optimal comprehensive weights of the pollutant diffusion speed, concentration gradient change rate, and ecological toxicity index in the evaluation index system, generates a dynamic pollution situation cloud map based on the weight results, and commands the fish school to preferentially cruise in high-weight areas;

[0009] Forming a poor state fingerprint library according to the peak data of stored historical pollution events; when the real-time data detected by the fish school sensors in the high-weight area exceeds the matching degree with the fingerprint library features, immediately trigger a two-level response: 1) The bionic fish school automatically increases the encryption sampling frequency; 2) The unmanned aerial vehicle sends the pollution pre-diffusion coordinates to the control center;

[0010] Access the sampling data of the bionic fish school and the pollution pre-diffusion coordinates obtained by the unmanned aerial vehicle, dynamically simulate the water quality evolution trajectory after taking treatment measures, and judge the feasibility of the treatment measures.

[0011] As a further option of this method, the hierarchical communication architecture includes a three-order cooperation mechanism of an air communication layer, a water surface relay layer, and an underwater communication layer;

[0012] Among them, the air communication layer constructs a dynamic topology network through unmanned aerial vehicles, the water surface relay layer uses adaptive beamforming technology to achieve cross-media signal conversion, and the underwater communication layer executes underwater acoustic communication and energy self-coordination protocols based on the distributed sensing network of bionic fish schools.

[0013] As a further option of this method, the fuzzy rule scheduling mechanism adopts a multi-input multi-output fuzzy inference system, and the input variables include pollutant concentration gradient, water temperature mutation rate, dissolved oxygen vertical stratification coefficient, and turbidity spatio-temporal variation coefficient, and the output variables are the three-dimensional swimming trajectory offset of the bionic fish school and the sampling frequency domain gain coefficient.

[0014] As a further option of this method, the game model constructed by the Nash equilibrium strategy includes three types of decision-making subjects with non-cooperative competition relationships: pollutant migration dynamics subjects, ecological toxicity response subjects, and monitoring resource constraint subjects;

[0015] The form of the game model is as follows:

[0016] ;

[0017] Among them, 、 、 represent the weights of the pollutant diffusion rate, the concentration gradient change rate, and the ecological toxicity index respectively, and are adjustment coefficients;

[0018] The strategy space of each subject is defined as the probability distribution of weight allocation. The utility function comprehensively considers the timeliness of pollution warning, the risk of biological toxicity exposure, and the energy consumption cost constraint, and obtains the Pareto optimal solution of the index weight by solving the mixed strategy Nash equilibrium;

[0019] The calculation rules are as follows:

[0020] ;

[0021] ;

[0022] Among them, is the velocity of the particle, is the position of the particle, that is, the weight configuration, is the historical optimal solution of the particle, is the global optimal solution, is the inertia weight, 、 are acceleration coefficients, 、 are random numbers.

[0023] As a further option of this method, the method for generating the dynamic pollution situation cloud map includes:

[0024] Map the optimal weight result obtained by solving the Nash equilibrium strategy to each monitoring grid unit to generate a pollution risk value, and divide the pollution risk level by using the trapezoidal membership function according to the distribution of the pollution risk value;

[0025] Use GIS technology to map the pollution risk level onto the two-dimensional map of the target water area, and display the pollution risk distribution of the dynamic pollution situation cloud map in the form of a situation cloud map visualization.

[0026] As a further option of this method, the method for constructing and matching the inferior state fingerprint library includes:

[0027] Extract the characteristics of pollutants through historical pollution event data. After the feature extraction is completed, encode the pollutant characteristics to construct an inferior state fingerprint library;

[0028] Evaluate the matching degree by calculating the similarity of the feature vectors and identifying the pollution event based on the threshold.

[0029] As a further option of this method, the simulation formula of the water quality evolution trajectory is:

[0030] ;

[0031] where is the coordinate at time of the pollutant concentration, is the initial pollutant concentration, is the water flow velocity field, is the diffusion coefficient tensor, is the source term of the treatment measure, is the parameter vector of the treatment plan.

[0032] As a further option of this method, the feasibility evaluation of the treatment measure includes: comparing in real time the change rate of the pollutant concentration gradient under different treatment plans with the pollution risk threshold defined by the Nash equilibrium weight, and identifying the intervention effect of the treatment measure on the high-weight area; when the simulation trajectory shows that the core index converges to the safe membership interval within the preset time window, it is determined that the treatment measure is effective.

[0033] The second technical solution of the present invention is to provide an intelligent water quality monitoring system for cooperative sampling of bionic fish schools and unmanned aerial vehicles, including:

[0034] A grid monitoring configuration unit, configured to: access geographic information system data, divide monitoring grid units; construct a hierarchical communication architecture including an air communication layer, a water surface relay layer, and an underwater communication layer; generate dynamic deployment instructions for bionic fish schools according to the water depth gradient and the flow velocity field;

[0035] A fuzzy scheduling control unit, communicatively connected to the bionic fish school sensor network, configured to: receive real-time water quality parameter data, execute the fuzzy rule base to output a bionic fish school aggregation density correction instruction; send a path adjustment signal to the bionic fish school through the hierarchical communication architecture;

[0036] A Nash equilibrium decision engine, configured to: fuse historical pollution event data and real-time sensing data, construct an evaluation index system for pollutant diffusion speed, change rate of concentration gradient, and ecological toxicity index; solve the Pareto optimal weight based on the game model; generate a dynamic pollution situation cloud map and mark high-weight cruising areas;

[0037] A poor state response execution module, including: a fingerprint library memory, storing peak data of historical pollution events encoded as multi-dimensional feature vectors; a real-time matcher, calculating the weighted cosine similarity between the sensing data in the high-weight area and the fingerprint library;

[0038] Two - level response trigger, when the matching degree exceeds the limit: (a) Send encrypted sampling instructions to the bionic fish school; (b) Send pollution pre - diffusion coordinate generation instructions to the unmanned aerial vehicle (UAV).

[0039] Governance simulation verification platform, configured to: access encrypted sampling data of the bionic fish school and pollution pre - diffusion coordinates; parameterize the governance measures and then substitute them into the water quality evolution model for dynamic simulation; output governance feasibility signals based on the convergence of the pollutant concentration gradient change rate.

[0040] Hierarchical communication hardware architecture, including: Air communication layer: UAVs carrying remote sensing equipment, establishing 5G / satellite backhaul links with the ground control center; Water surface relay layer: Deploying self - organizing networking buoys equipped with air - water dual - frequency communication repeaters; Underwater communication layer: Bionic fish schools with built - in underwater acoustic modems, forming a dynamic routing sensing network.

[0041] Control center visualization terminal, configured to: render a dynamic pollution situation cloud map in real - time, marking the pollution risk level with a gradient color system; display the governance simulation trajectory and feasibility assessment results.

[0042] The third technical solution of the present invention is to provide a computer device, which includes: a processor and a memory. At least one instruction, at least one program, a code set or an instruction set is stored in the memory, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by the processor to implement the water quality intelligent monitoring method for collaborative sampling of bionic fish schools and UAVs as described in the first technical solution.

[0043] The beneficial effects brought by the technical solutions provided in the embodiments of this application at least include the following beneficial effects:

[0044] This solution constructs a multi - dimensional dynamic monitoring network by deeply integrating Geographic Information System (GIS) data, UAV remote sensing information, and real - time sensing data of bionic fish schools. Its core advantage lies in the design of the hierarchical communication architecture - the air communication layer realizes global situation awareness, the water surface relay layer breaks through the cross - medium signal conversion bottleneck, and the underwater communication layer relies on the distributed sensing network of bionic fish schools to form an air - space - ground integrated collaborative monitoring system, significantly improving the data collection efficiency and coverage breadth in complex water environments.

[0045] Based on the Nash equilibrium strategy of game theory, it innovatively solves the problem of dynamic allocation of water quality evaluation index weights. Through non - cooperative game modeling of pollutant diffusion speed, concentration gradient change rate, and ecological toxicity index, it realizes Pareto - optimal decision - making under multi - objective conflicts. Combined with the fuzzy rule scheduling mechanism, it can drive the bionic fish school to adaptively adjust the sampling density and swimming path in real - time, making the monitoring resources accurately match the hydrological characteristics and forming an intelligent closed - loop of "risk prediction - dynamic response - continuous optimization".

[0046] By constructing a historical pollution event inferior state fingerprint library to achieve sub-linear matching efficiency, after triggering the two-level response mechanism, high-frequency encrypted sampling of bionic fish schools and coordinate forecasting of drone pollution diffusion can be synchronously started. Combined with water quality evolution simulation, not only can the migration trajectory of pollutants after the implementation of treatment measures be dynamically predicted, but also by introducing a parameterized model of treatment measures (such as the non-linear term of adsorption materials and the boundary correction term of physical barriers), a high-precision digital twin verification platform for pollution treatment can be provided, realizing the full-process closed-loop control of "monitoring - early warning - simulation - decision-making". BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a schematic diagram of the overall process of the intelligent water quality monitoring method for collaborative sampling of bionic fish schools and drones; Figure 2 It is a detailed flowchart of step S100 of the intelligent water quality monitoring method for collaborative sampling of bionic fish schools and drones; Figure 3 It is a detailed flowchart of step S200 of the intelligent water quality monitoring method for collaborative sampling of bionic fish schools and drones; Figure 4 It is a detailed flowchart of step S300 of the intelligent water quality monitoring method for collaborative sampling of bionic fish schools and drones; Figure 5 It is a detailed flowchart of step S400 of the intelligent water quality monitoring method for collaborative sampling of bionic fish schools and drones. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0048] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without making creative efforts belong to the scope of protection of the present application.

[0049] In the existing water quality monitoring technology, the traditional manual sampling method has problems such as limited monitoring range, poor real-time performance, and high labor costs; the sensor monitoring network at fixed points is difficult to flexibly adapt to the dynamic changes of complex water environments and has insufficient response capabilities for sudden pollution events; although the single drone monitoring has a certain degree of mobility, it is limited by the endurance and monitoring depth and cannot comprehensively obtain water quality data at different levels of the water body. In addition, the existing technology lacks an intelligent collaborative mechanism in the dynamic allocation of monitoring resources, pollution risk assessment, and early warning, and it is difficult to achieve accurate and efficient monitoring of water quality conditions. To solve the above problems, please refer to Figure 1 , which shows an intelligent water quality monitoring method for collaborative sampling of bionic fish schools and drones provided by an embodiment of the present invention. The method includes:

[0050] S100: Divide the monitoring grid units based on the geographical information system data of the target water area, establish a hierarchical communication architecture for drones and bionic fish swarms, dynamically deploy bionic fish swarms according to the environmental parameters of the monitoring grid units, and use drone remote sensing and bionic fish swarm sensors to monitor water quality anomalies in real time. Schedule the bionic fish swarms through fuzzy rules to achieve the initial adaptation of monitoring resources and hydrological characteristics.

[0051] S200: The drone collects historical pollution event data and real-time fish swarm sensing data, constructs a water quality evaluation index system, adopts the Nash equilibrium strategy, evaluates the optimal comprehensive weights of the pollutant diffusion speed, concentration gradient change rate, and ecological toxicity index in the evaluation index system based on game theory, generates a dynamic pollution situation cloud map based on the weight results, and commands the fish swarm to cruise in the high-weight area preferentially;

[0052] S300: Form a poor state fingerprint library according to the peak data of historical pollution events stored; when the fish swarm sensors in the high-weight area detect that the matching degree between the real-time data and the fingerprint library features exceeds the limit, immediately trigger a two-level response: 1) The bionic fish swarm automatically increases the encryption sampling frequency; 2) The drone sends the pollution pre-diffusion coordinates to the control center.

[0053] S400: Access the sampling data of the bionic fish swarm and the pollution pre-diffusion coordinates obtained by the drone, dynamically simulate the water quality evolution trajectory after taking treatment measures, and judge the feasibility of the treatment measures.

[0054] S100 - S400 propose a collaborative monitoring technical solution combining bionic fish swarms and drones. Through means such as grid division by GIS data, fuzzy rule scheduling, Nash equilibrium weight evaluation, and dynamic pollution simulation, it realizes efficient and accurate water quality monitoring and treatment optimization, and has the remarkable advantages of intelligent resource allocation, rapid pollution response, and scientific decision-making.

[0055] The specific solution is as follows:

[0056] In the water quality intelligent monitoring method of collaborative sampling by bionic fish swarms and drones, S100 constructs a basic framework for water quality intelligent monitoring of collaborative sampling by bionic fish swarms and drones by integrating geographical information system (GIS) data, hierarchical communication architecture, and dynamic resource allocation strategy. S100 includes: analysis of pollution risks and hydrological characteristics based on GIS to achieve adaptive division and dynamic optimization of monitoring grids. Design of a hierarchical communication architecture to solve the problems of stability and real-time of cross-media data transmission. A depth-flow rate collaborative allocation mechanism for bionic fish swarms, which can sense water quality in real time through multi-parameter sensors and dynamically adjust the sampling density. Drone remote sensing and fuzzy rule scheduling, combined with remote sensing anomaly recognition and bionic fish swarm aggregation strategy, to achieve the initial adaptation of monitoring resources and hydrological characteristics.

[0057] Please refer to Figure 2, which shows a flowchart of an exemplary water quality intelligent monitoring method S100 for collaborative sampling of a bionic fish school and an unmanned aerial vehicle (UAV) in this application. The content includes:

[0058] S110: Obtain Geographic Information System (GIS) data of the target water area and divide the monitoring grid units based on the GIS data.

[0059] The acquisition of GIS data mainly relies on remote sensing images, topographic maps, hydrological monitoring data, and historical pollution event databases.

[0060] Specifically, remote sensing images obtain high-resolution surface and water body distribution information through satellite or UAV aerial photography, which is used to identify water area boundaries, river network structures, and surrounding land use types. Topographic maps provide elevation change information of the target water area, which is used to analyze water flow direction, water depth distribution, and the impact of terrain on pollutant diffusion. Hydrological monitoring data includes parameters such as flow velocity, water depth, and temperature, which usually come from ground monitoring stations or lidar scanning systems carried by UAVs. The historical pollution event database records the occurrence locations, pollutant types, concentration peaks, and diffusion paths of past pollution events, providing a reference basis for monitoring grid division and risk prediction.

[0061] After the acquisition and preprocessing of GIS data are completed, it enters the stage of dividing the monitoring grid units. The stage of dividing the monitoring grid units divides the target water area into several monitoring grid units and dynamically adjusts the grid layout according to hydrological characteristics and pollution risks to optimize the allocation of monitoring resources.

[0062] In a possible implementation manner, a spatial division method is used to divide the monitoring grid units, and the grid layout is optimized by hydrological characteristics. The specific process is as follows:

[0063] a. Convert remote sensing image and topographic map data into vector data, and extract water body boundaries, river network distributions, and key monitoring points.

[0064] b. Use a spatial division method to divide the target water area into several initial grid units. Exemplarily, the spatial division method uses Thiessen polygons or rasterization methods. Thiessen polygons are suitable for irregular water areas, while rasterization is suitable for regularly distributed monitoring areas.

[0065] c. Combine the hydrological characteristics model to dynamically adjust the initial grid. Exemplarily, in areas with higher pollution risks, the grid unit area can be reduced to 50m×50m, while in areas with lower pollution risks, the grid unit area can be expanded to 200m×200m.

[0066] S120: Establish a hierarchical communication architecture between the UAV and the bionic fish school.

[0067] The hierarchical communication architecture between the unmanned aerial vehicle (UAV) and the biomimetic fish swarm consists of an aerial communication layer, a water surface relay layer, and an underwater communication layer, ensuring efficient data interaction between the biomimetic fish swarm and the UAV.

[0068] Specifically, the aerial communication layer is composed of the UAV, which is responsible for high-altitude remote sensing data collection, global monitoring grid division, and communication with the ground control center. The water surface relay layer consists of water surface base stations and buoy-type communication nodes, serving as a bridge between aerial and underwater communication. The underwater communication layer is composed of the biomimetic fish swarm and its carried sensor network, responsible for underwater environment data collection and local communication.

[0069] S130: Dynamically deploy the biomimetic fish swarm according to the environmental parameters of the monitoring grid unit.

[0070] After completing the monitoring grid division and communication architecture establishment, enter the dynamic allocation stage of the biomimetic fish swarm. Deploy the biomimetic fish swarm reasonably according to the environmental parameters to optimize the coverage rate and monitoring accuracy of data collection.

[0071] In a possible implementation manner, the deployment of the biomimetic fish swarm is based on the water depth in the environmental parameters. The water depth directly affects the vertical distribution of pollutants, so the deployment of the biomimetic fish swarm needs to combine the water depth data. The specific deployment strategies include:

[0072] Calculate the water depth distribution of each grid unit through the topographic map in GIS data and hydrological monitoring data, and adjust the release density of the biomimetic fish swarm accordingly. In deep water areas, the deployment density of the biomimetic fish swarm is relatively low to reduce energy consumption and avoid over-sampling; in shallow water areas, the deployment density of the biomimetic fish swarm is relatively high to improve the spatio-temporal resolution of monitoring.

[0073] In another possible implementation manner, the deployment of the biomimetic fish swarm is based on the water flow velocity in the environmental parameters. The water flow velocity directly affects the diffusion path and spatial distribution of pollutants, so the distribution of the biomimetic fish swarm needs to be dynamically adjusted in combination with the flow velocity data. The specific deployment strategies include:

[0074] In river areas with relatively fast water flow velocity, the deployment density of the biomimetic fish swarm is relatively high to improve the tracking ability of pollutant migration; in lake or reservoir areas with relatively slow water flow velocity, the deployment density of the biomimetic fish swarm can be appropriately reduced to extend the battery life of the equipment.

[0075] S140: Schedule the biomimetic fish swarm through fuzzy rules.

[0076] The input variables of the fuzzy rule scheduling are derived from the sensors carried by the biomimetic fish swarm and the UAV remote sensing data. Specifically, they include: pollutant concentration, water temperature, dissolved oxygen (DO) content, pH value, conductivity, turbidity.

[0077] In a possible implementation, the rule base of the fuzzy rules is determined based on environmental parameters. It consists of a series of "IF-THEN" rules used to describe the mapping relationship between environmental parameters and the scheduling instructions of the bionic fish swarm.

[0078] Exemplary:

[0079] IF the pollutant concentration is high AND the diffusion speed is fast THEN the aggregation density of the bionic fish swarm increases significantly;

[0080] IF the pollutant concentration is medium AND the water toxicity index is high THEN the aggregation density of the bionic fish swarm increases moderately;

[0081] IF the pollutant concentration is low AND the diffusion speed is slow THEN the aggregation density of the bionic fish swarm remains unchanged.

[0082] The UAV remote sensing and the bionic fish swarm sensors monitor water quality anomalies in real time. Based on the scheduling rules of fuzzy logic, combined with multi-source environmental parameters, the distribution density and swimming path of the bionic fish swarm are dynamically adjusted to achieve the initial adaptation of monitoring resources and hydrological characteristics.

[0083] In the intelligent water quality monitoring method for the collaborative sampling of the bionic fish swarm and the UAV, S200 focuses on the construction and optimization of the water quality evaluation index system. First, the UAV and the bionic fish swarm are used to jointly collect historical pollution event data and real-time water quality sensing data, and an evaluation system is constructed by combining the three core indicators of pollutant diffusion speed, concentration gradient change rate, and ecological toxicity index. Based on the Nash equilibrium strategy of game theory, the optimal comprehensive weights of each index are dynamically solved, and the weights are adaptively adjusted through the particle swarm optimization algorithm to ensure the evaluation accuracy under different pollution scenarios. Subsequently, the pollution risk levels are divided by using weight mapping and trapezoidal membership functions, and a dynamic pollution situation cloud map is generated by combining Kriging interpolation to guide the bionic fish swarm to preferentially cruise in high-risk areas.

[0084] Please refer to Figure 3 , which shows the flowchart of an exemplary intelligent water quality monitoring method S200 for the collaborative sampling of the bionic fish swarm and the UAV in this application, and its content includes:

[0085] S210: The UAV collects historical pollution event data and real-time fish swarm sensing data.

[0086] The UAV is responsible for collecting historical pollution event data of the target water area and real-time sensing data of the bionic fish swarm to construct a complete water quality evaluation data set. The historical pollution event database records the occurrence locations, pollutant types, concentration peaks, and diffusion paths of past pollution events, providing a reference basis for monitoring grid division and risk prediction.

[0087] Meanwhile, the sensor network carried by the bionic fish school collects water quality parameters in real time, including pollutant concentration, water temperature, dissolved oxygen (DO) content, pH value, conductivity, turbidity, etc. The water quality parameters are transmitted to the surface relay node through the underwater communication layer and then received and integrated by the UAV.

[0088] In a possible implementation, after the historical pollution event data and the real-time fish school sensing data are collected, the two types of data are fused. This process includes data standardization, feature extraction, and spatial interpolation to eliminate the dimensional differences between different data sources and enhance the spatial continuity of the data. Finally, the integrated dataset provides basic support for the construction of the subsequent water quality evaluation index system.

[0089] S220: Construct a water quality evaluation index system.

[0090] After the historical pollution event data and the real-time sensing data of the bionic fish school are collected, a scientific and quantifiable evaluation standard is established based on multi-source data to accurately reflect the pollution status of the target water area. The water quality evaluation index system mainly includes three key indicators: pollutant diffusion speed, concentration gradient change rate, and ecological toxicity index, which are used to measure the migration ability of pollutants, the changing trend of spatial distribution, and the potential harm to the ecological environment, respectively.

[0091] Specifically, the pollutant diffusion speed is an important parameter to measure the migration ability of pollutants in water and directly affects the expansion speed of the pollution range.

[0092] In a possible implementation, the calculation of the pollutant diffusion speed is based on the pollutant diffusion path in the historical pollution event database, combined with the water flow speed, water temperature, and water depth data collected by the bionic fish school in real time. The calculation formula is as follows:

[0093] ;

[0094] where is the pollutant diffusion speed, is the spatial displacement of the pollutant within the time interval . Through this formula, the diffusion ability of pollutants in different regions is quantified, and the urgency of pollution events is judged accordingly.

[0095] Specifically, the concentration gradient change rate is used to describe the changing trend of pollutant concentration in space and reflects the diffusion intensity of the pollution source and the evolution of the pollution range.

[0096] In a possible implementation, the calculation of the concentration gradient change rate is based on the pollutant concentration data collected by the bionic fish school and combined with the concentration peak information in the historical pollution event database. The calculation formula is as follows:

[0097] ;

[0098] Among them, is the concentration gradient change rate, is the pollutant concentration difference between adjacent grid cells, is the distance between grid cells. Through this formula, the areas where the pollutant concentration rises or falls rapidly are identified, thereby optimizing the sampling strategy of the bionic fish school.

[0099] Specifically, the ecological toxicity index is used to evaluate the potential harm of pollutants to the aquatic ecosystem, taking into account the toxicity and bioaccumulation ability of pollutants.

[0100] In a possible implementation manner, the calculation of the ecological toxicity index is based on the pollutant type, concentration, and bioaccumulation coefficient, and combines the ecological impact records in the historical pollution event database. The calculation formula is as follows:

[0101] ;

[0102] Among them, is the ecological toxicity index, is the weight of the pollutant type, is the pollutant concentration, is the bioaccumulation coefficient of the pollutant. Through this formula, the impact of pollutants on aquatic organisms is quantified, and the sampling priority of the bionic fish school is adjusted accordingly.

[0103] S230: Use the Nash equilibrium strategy to solve the optimal comprehensive weight of the water quality evaluation index system.

[0104] Since the importance of pollutant diffusion speed, concentration gradient change rate, and ecological toxicity index varies in different pollution events, a single fixed weight is difficult to adapt to the complex and changeable hydrological environment. Therefore, the Nash equilibrium strategy is adopted to optimize the comprehensive weight of each index based on game theory, enabling the water quality evaluation system to maintain optimal decision-making ability under different pollution scenarios.

[0105] In a possible implementation manner, the implementation of the Nash equilibrium strategy mainly includes the following steps:

[0106] a. Take the pollutant diffusion speed, concentration gradient change rate, and ecological toxicity index as game participants, set their respective strategy spaces, that is, the weight adjustment range, and establish a game model to measure the impact of different weight combinations on water quality evaluation; the form of the game model is as follows:

[0107] ;

[0108] Among them, , , represent the weights of the pollutant diffusion rate, the concentration gradient change rate, and the ecological toxicity index respectively, and are adjustment coefficients used to balance the weights of accuracy and adaptability.

[0109] b. In the game model, the solution process of the Nash equilibrium involves iterative calculations to find the optimal weight combination. The iterative calculation rules are as follows:

[0110] ;

[0111] ;

[0112] wherein, is the velocity of the particle, is the position of the particle, i.e., the weight configuration, is the historical optimal solution of the particle, is the global optimal solution, is the inertia weight, , are acceleration coefficients, , are random numbers. Through this algorithm, it is possible to quickly converge to the Nash equilibrium solution in the weight space.

[0113] S240: Generate a dynamic pollution situation cloud map based on the weight results.

[0114] After completing the optimal weight configuration of the water quality evaluation index system, a dynamic pollution situation cloud map is generated based on the weight results. The dynamic pollution situation cloud map is used to visually display the pollution risk distribution of the target water area and guide the bionic fish school to preferentially cruise in the high-weight areas to improve the monitoring efficiency and data collection accuracy.

[0115] In a possible implementation manner, the generation process of the dynamic pollution situation cloud map includes:

[0116] a. Map the optimal weight results obtained from the Nash equilibrium strategy to each monitoring grid unit to generate pollution risk values, and divide the pollution risk levels using a trapezoidal membership function according to the distribution of the pollution risk values.

[0117] In a possible implementation manner, since the weights of the pollutant diffusion rate, the concentration gradient change rate, and the ecological toxicity index reflect the importance of different pollution characteristics, the pollution risk value of each grid unit is calculated by weighted summation.

[0118] In a possible implementation manner, the trapezoidal membership function is defined as:

[0119] ;

[0120] wherein, , , , are the thresholds of the pollution risk levels, corresponding to the four levels of "safe", "warning", "dangerous", and "highly toxic" respectively. Through the trapezoidal membership function, the pollution risk value can be converted into the probabilities of different levels, forming the pollution risk level, which provides a basis for the visualization of the subsequent dynamic pollution situation cloud map.

[0121] b. Use GIS technology to map the pollution risk level onto the two-dimensional map of the target water area, and adopt the visualization method of the situation cloud map to display the pollution risk distribution of the dynamic pollution situation cloud map.

[0122] In a possible implementation manner, the color coding scheme of the dynamic pollution situation cloud map adopts a gradient color system, where blue represents the "safe" area, yellow represents the "warning" area, orange represents the "dangerous" area, and red represents the "highly toxic" area. Through this visualization method, the monitoring personnel can intuitively identify the areas with higher pollution risks and adjust the cruising strategies of the bionic fish groups accordingly.

[0123] After the dynamic pollution situation cloud map is generated, formulate the path planning strategy of the bionic fish group based on the pollution risk level. The dynamic pollution situation cloud map can effectively guide the bionic fish group to cruise the high-pollution risk areas preferentially, improve the pertinence of water quality monitoring and the accuracy of data collection, and provide a scientific basis for subsequent pollution control decisions.

[0124] In the water quality intelligent monitoring method of the collaborative sampling of bionic fish groups and unmanned aerial vehicles, S300 includes the construction of a poor state fingerprint library and a pollution event response mechanism. First, extract the pollutant characteristics based on the historical pollution event data to construct the poor state fingerprint library. Compare the water quality data collected by the sensors of the bionic fish group with the poor state fingerprint library in real time. When the matching degree exceeds the limit, trigger a two-level response. Finally, form a closed-loop management of "real-time monitoring - event recognition - response regulation" to ensure the rapid response and treatment efficiency of pollution events.

[0125] Please refer to Figure 4 , which shows the flowchart of an exemplary water quality intelligent monitoring method S300 for the collaborative sampling of bionic fish groups and unmanned aerial vehicles in this application. Its content includes:

[0126] S310: Construct a poor state fingerprint library.

[0127] Extract the characteristics of pollutants through historical pollution event data. After the feature extraction is completed, encode the pollutant characteristics to construct a poor state fingerprint library.

[0128] In a possible implementation manner, the goal of feature extraction is to extract key pollutant characteristics from historical pollution event data, including pollutant types, concentration peaks, diffusion rates, toxicity indices, and spatial distribution patterns.

[0129] In a possible implementation, the pollutant feature encoding method uses a multi-dimensional feature vector representation. Each pollutant feature corresponds to a feature dimension, forming a multi-dimensional feature space. For example, the pollutant type uses One-Hot encoding to convert different pollutant categories into binary vectors. Finally, each historical pollution event is represented as a high-dimensional feature vector in the following format:

[0130] ;

[0131] where, is the pollutant type encoding, is the diffusion speed, is the toxicity index, is the spatial distribution pattern of the pollutant. This feature vector constitutes the basic unit of the inferior state fingerprint database and is stored in the database for subsequent real-time data comparison.

[0132] As an option for this step, in a possible implementation, to improve the retrieval efficiency of the inferior state fingerprint database, an inverted index technology is used to optimize the indexing of pollutant features. The inverted index builds an index table based on key features such as pollutant type, concentration peak, diffusion speed, toxicity index, etc., enabling quick location of similar pollution events.

[0133] S320: Analysis of the matching degree between real-time data and the inferior state fingerprint database.

[0134] After the inferior state fingerprint database is constructed, the real-time water quality data collected by drone remote sensing and bionic fish school sensors is compared with the characteristics of historical pollution events in the inferior state fingerprint database to identify potential pollution events and evaluate their matching degree.

[0135] In a possible implementation, the evaluation of the matching degree mainly depends on the calculation of feature vector similarity and the identification of pollution events based on thresholds.

[0136] Specifically, the cosine similarity is used to calculate the matching degree between the real-time data feature vector and the historical pollution event feature vector in the inferior state fingerprint database. The calculation formula of the cosine similarity is as follows:

[0137] ;

[0138] where, is the real-time data feature vector, is the feature vector in the inferior state fingerprint database, represents the dot product of vectors, and represent the norms of the vectors respectively. Through this formula, the similarity degree between real-time data and historical pollution events is quantified. The closer the similarity value is to 1, the higher the matching degree.

[0139] In an alternative embodiment, the weighted cosine similarity is adopted to further optimize the calculation of the matching degree to enhance the weight of key features.

[0140] Specifically, when the matching degree of real-time data exceeds the threshold, it is determined that the current water quality condition is highly similar to the historical pollution event, and the pollution event recognition process is triggered. The pollution event recognition process includes pollutant type identification and pollution source location. Pollutant type identification is based on the record in the inferior state fingerprint library with the highest matching degree to determine the main pollutant category of the current pollution event; pollution source location is based on the real-time position of the bionic fish school to identify the most likely pollution source location.

[0141] S330: If the matching degree exceeds the set threshold, immediately trigger the two-level response mechanism.

[0142] After the matching degree analysis of the real-time data and the inferior state fingerprint library is completed, if the matching degree exceeds the set threshold, immediately trigger the two-level response mechanism to ensure that the pollution event can be processed in a timely manner. The response mechanism includes: the first-level response, the bionic fish school automatically increases the encryption sampling frequency, and the second-level response: the drone sends the pollution pre-diffusion coordinates to the control center.

[0143] The first-level response: The bionic fish school automatically increases the sampling frequency.

[0144] Specifically, the sampling frequency improvement strategy of the bionic fish school is dynamically adjusted based on the pollution risk level and the pollutant diffusion speed. In areas with a higher pollution risk, the sampling frequency of the bionic fish school will be increased to 2-3 times that under normal conditions.

[0145] The second-level response: The drone sends the pollution pre-diffusion coordinates to the control center.

[0146] While the bionic fish school increases the sampling frequency, the drone will execute the second-level response, that is, send the pollution pre-diffusion coordinates to the ground control center. The goal of this response mechanism is to provide early warning for emergency response and support the prediction of the pollution diffusion path.

[0147] In a possible implementation, the drone predicts the diffusion path of pollutants based on the real-time data collected by the bionic fish school and the historical pollution event database, in combination with the hydrological model.

[0148] In the intelligent water quality monitoring method of the collaborative sampling of the bionic fish school and the drone, S400 involves the formulation, simulation and evaluation of pollution control measures. By formulating and parameterizing the control measures, simulating the water quality evolution trajectory and evaluating the control effect, the optimization and verification of the pollution control plan are realized.

[0149] Please refer to Figure 5, which shows the flowchart of an exemplary water quality intelligent monitoring method S400 for collaborative sampling of bionic fish schools and drones in this application. Its content includes:

[0150] S410: Formulate treatment measures and parameterize the treatment measure parameters.

[0151] The treatment plan is formulated based on the real-time monitoring data of bionic fish schools and drones and the dynamic pollution situation cloud map, and combines the treatment experience in the historical pollution event database.

[0152] Exemplarily, for heavy metal pollution events, the treatment plan includes: adsorption material placement, physical barrier setting, or artificial aeration for oxygenation.

[0153] To simulate the impact of treatment measures on water quality evolution, parameterize the treatment measures as the source term or boundary conditions of the model. Based on the parameterization of treatment measures, simulate the impact of different treatment plans on the water quality evolution trajectory, and predict the water quality state after treatment.

[0154] S420: Access the sampling data of bionic fish schools and the pollution pre-diffusion coordinates obtained by drones, and simulate the water quality evolution trajectory.

[0155] The simulation formula of the water quality evolution trajectory is as follows:

[0156] ;

[0157] Among them, is the pollutant concentration at coordinate at time , is the initial pollutant concentration, is the water flow velocity field, is the diffusion coefficient tensor, is the source term of the treatment measure, is the treatment plan parameter vector.

[0158] S430: Feasibility assessment of treatment measures.

[0159] Compare the change rate of pollutant concentration gradient under different treatment plans with the pollution risk threshold defined by the Nash equilibrium weight in real time, and identify the intervention effect of treatment measures on high-weight areas. When the simulation trajectory shows that the core indicators converge to the safe membership interval within the preset time window, it is determined that the treatment measures are effective.

[0160] S100 - S400 includes: dividing monitoring grid units using GIS data, establishing a hierarchical communication architecture, dynamically deploying bionic fish swarms for real - time water quality monitoring, and optimizing resource allocation through fuzzy rule scheduling; integrating historical pollution event data and real - time sensing data to construct a water quality evaluation index system, using the Nash equilibrium strategy to determine the optimal weights to generate a dynamic pollution situation cloud map; constructing a poor - state fingerprint library to achieve rapid identification of pollution events and trigger a two - level response mechanism; finally, dynamically simulating the effects of treatment measures by combining bionic fish swarm sampling data and UAV pre - diffusion coordinates. It realizes air - water integrated and efficient monitoring, improves the accuracy and timeliness of water quality anomaly detection; optimizes the monitoring resource configuration through intelligent scheduling and data analysis; enhances the scientificity and feasibility of pollution treatment decisions with the help of game theory and dynamic simulation, providing comprehensive technical support for water area environmental protection.

[0161] This application also provides a water quality intelligent monitoring system for collaborative sampling of bionic fish swarms and UAVs, including:

[0162] A grid - based monitoring configuration unit, configured to: access geographic information system data, divide monitoring grid units; construct a hierarchical communication architecture including an air communication layer, a water surface relay layer, and an underwater communication layer; generate dynamic deployment instructions for bionic fish swarms according to the water depth gradient and flow velocity field;

[0163] A fuzzy scheduling control unit, communicatively connected to the bionic fish swarm sensor network, configured to: receive real - time water quality parameter data, execute the fuzzy rule base to output bionic fish swarm aggregation density correction instructions; send path adjustment signals to the bionic fish swarm through the hierarchical communication architecture;

[0164] A Nash equilibrium decision engine, configured to: integrate historical pollution event data and real - time sensing data, construct an evaluation index system for pollutant diffusion speed, concentration gradient change rate, and ecological toxicity index; solve for the Pareto optimal weights based on the game model; generate a dynamic pollution situation cloud map and mark high - weight cruising areas;

[0165] A poor - state response execution module, including: a fingerprint library memory that stores historical pollution event peak data encoded as multi - dimensional feature vectors; a real - time matcher that calculates the weighted cosine similarity between the sensing data in high - weight areas and the fingerprint library;

[0166] A two - level response trigger, when the matching degree exceeds the limit: (a) send encrypted sampling instructions to the bionic fish swarm; (b) send pollution pre - diffusion coordinate generation instructions to the UAV;

[0167] A governance simulation verification platform, configured to: access bionic fish swarm encrypted sampling data and pollution pre - diffusion coordinates; parameterize the treatment measures and substitute them into the water quality evolution model for dynamic simulation; output a governance feasibility signal based on the convergence of the pollutant concentration gradient change rate;

[0168] Hierarchical communication hardware architecture, including: Air communication layer: A drone carrying remote sensing equipment establishes a 5G / satellite backhaul link with the ground control center; Water surface relay layer: Deploy self-organizing networking buoys equipped with air-water dual-band communication repeaters; Underwater communication layer: A bionic fish school with an underwater acoustic modem forms a dynamic routing sensing network;

[0169] The visualization terminal of the control center is configured to: Render a dynamic pollution situation cloud map in real time, and mark the pollution risk level using a gradient color system; Display the treatment simulation trajectory and the feasibility evaluation results.

[0170] This application also provides a computer device, which includes: a processor and a memory. At least one instruction, at least one program, a code set, or an instruction set is stored in the memory. The at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by the processor to implement the intelligent water quality monitoring method for collaborative sampling of bionic fish schools and drones.

[0171] The basic principles of this application are described above in conjunction with specific embodiments. However, it should be noted that the advantages, benefits, effects, etc. mentioned in this application are only examples and not limitations, and it cannot be considered that these advantages, benefits, effects, etc. are essential for each embodiment of this application. Additionally, the specific details disclosed above are only for illustrative and easy-to-understand purposes, not limitations, and these details do not limit this application to necessarily implement using the above specific details.

[0172] The block diagrams of the devices, apparatuses, and equipment involved in this application are only illustrative examples and do not intend to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, and equipment can be connected, arranged, and configured in any way. Words such as "including", "comprising", "having", etc. are open-ended terms, meaning "including but not limited to", and can be used interchangeably with each other. The words "or" and "and" used here refer to the phrase "and / or" and can be used interchangeably with it, unless the context clearly indicates otherwise. The word "such as" used here refers to the phrase "such as but not limited to" and can be used interchangeably with it.

[0173] It should also be noted that in the devices, equipment, and methods of this application, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent solutions of this application.

[0174] The above description of the disclosed aspects enables any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of the present application. Therefore, the present application is not intended to be limited to the aspects shown herein, but rather to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0175] The above are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent substitutions, etc. made within the spirit and principle of the present application shall be included within the protection scope of the present application.

Claims

1. An intelligent water quality monitoring method for collaborative sampling of bionic fish schools and unmanned aerial vehicles, characterized in that, Including: Dividing monitoring grid units based on the geographic information system data of the target water area, establishing a hierarchical communication architecture for drones and bionic fish swarms, dynamically deploying bionic fish swarms according to the environmental parameters of the monitoring grid units, and using drone remote sensing and bionic fish swarm sensors to monitor water quality anomalies in real time. Scheduling the bionic fish swarms through fuzzy rules to achieve the initial adaptation of monitoring resources and hydrological characteristics; The drone collects historical pollution event data and real-time fish swarm sensing data, constructs a water quality evaluation index system, adopts the Nash equilibrium strategy, and based on game theory, evaluates the optimal comprehensive weights of the pollutant diffusion speed, concentration gradient change rate, and ecological toxicity index in the evaluation index system. Generates a dynamic pollution situation cloud map based on the weight results, and commands the fish swarm to preferentially cruise in high-weight areas; Forming a poor state fingerprint library based on the peak data of stored historical pollution events; when the fish swarm sensors in high-weight areas detect that the real-time data exceeds the matching degree with the fingerprint library features, immediately trigger a two-level response: 1) The bionic fish swarm automatically increases the encryption sampling frequency; 2) The drone sends the pollution pre-diffusion coordinates to the control center; Access the bionic fish swarm sampling data and the pollution pre-diffusion coordinates obtained by the drone, dynamically simulate the water quality evolution trajectory after taking treatment measures, and judge the feasibility of the treatment measures.

2. The intelligent water quality monitoring method for collaborative sampling of bionic fish schools and unmanned aerial vehicles according to claim 1, wherein, The hierarchical communication architecture includes a three-order cooperation mechanism of an air communication layer, a water surface relay layer, and an underwater communication layer; Among them, the air communication layer constructs a dynamic topology network through drones, the water surface relay layer uses adaptive beamforming technology to achieve cross-media signal conversion, and the underwater communication layer executes underwater acoustic communication and energy self-coordination protocols based on the distributed sensing network of bionic fish swarms.

3. The intelligent water quality monitoring method for collaborative sampling of bionic fish schools and unmanned aerial vehicles according to claim 1, wherein The fuzzy rule scheduling mechanism adopts a multi-input multi-output fuzzy inference system. The input variables include pollutant concentration gradient, water temperature mutation rate, dissolved oxygen vertical stratification coefficient, and turbidity spatio-temporal variation coefficient. The output variables are the three-dimensional swimming trajectory offset of the bionic fish swarm and the sampling frequency domain gain coefficient.

4. The intelligent water quality monitoring method for collaborative sampling of bionic fish schools and unmanned aerial vehicles according to claim 1, wherein The game model constructed by the Nash equilibrium strategy includes three types of decision-making subjects with non-cooperative competition relationships: pollutant migration dynamics subject, ecological toxicity response subject, and monitoring resource constraint subject; The form of the game model is as follows: ； Among them, , , represent the weights of the pollutant diffusion rate, the concentration gradient change rate, and the ecological toxicity index respectively, and are adjustment coefficients; The strategy space of each subject is defined as the weight distribution probability distribution. The utility function comprehensively considers the timeliness of pollution warning, the risk of biological toxicity exposure, and the energy consumption cost constraint, and obtains the Pareto optimal solution of the index weight by solving the mixed strategy Nash equilibrium; The calculation rules are as follows: ； ； Among them, is the velocity of the particle, is the position of the particle, i.e., the weight configuration, is the historical best solution of the particle, is the global best solution, is the inertial weight, , are the acceleration coefficients, , are random numbers.

5. The intelligent water quality monitoring method for collaborative sampling of bionic fish schools and unmanned aerial vehicles according to claim 1, characterized in that The generation method of the dynamic pollution situation cloud map includes: Mapping the optimal weight results obtained by solving the Nash equilibrium strategy to each monitoring grid unit to generate pollution risk values, and based on the distribution of pollution risk values, using a trapezoidal membership function to divide the pollution risk levels; Using GIS technology to map the pollution risk levels to the two-dimensional map of the target water area, and using the situation cloud map visualization method to display the pollution risk distribution of the dynamic pollution situation cloud map.

6. The intelligent water quality monitoring method for collaborative sampling of bionic fish schools and unmanned aerial vehicles according to claim 1, characterized in that, The construction and matching method of the poor state fingerprint library includes: Extracting the characteristics of pollutants through historical pollution event data, and after the feature extraction is completed, encoding the pollutant characteristics to construct a poor state fingerprint library; Calculating the similarity of feature vectors and evaluating the matching degree of pollution events based on thresholds.

7. The intelligent water quality monitoring method for collaborative sampling of bionic fish schools and unmanned aerial vehicles according to claim 1, characterized in that The simulation formula of the water quality evolution trajectory is as follows: ； wherein, is the coordinate at time the pollutant concentration, is the initial pollutant concentration, is the water flow velocity field, is the diffusion coefficient tensor, is the source term of the treatment measure, is the parameter vector of the treatment plan.

8. The intelligent water quality monitoring method for collaborative sampling of bionic fish schools and unmanned aerial vehicles according to claim 7, characterized in that, The feasibility evaluation of the governance measures includes: comparing in real time the change rate of the pollutant concentration gradient under different governance schemes with the pollution risk threshold defined by the Nash equilibrium weight, and identifying the intervention effect of the governance measures on the high-weight areas; when the simulation trajectory shows that the core indicators converge to the safe membership interval within the preset time window, it is determined that the governance measures are effective.

9. An intelligent water quality monitoring system for collaborative sampling of bionic fish schools and unmanned aerial vehicles, using the method according to any one of claims 1-8, characterized in that, It includes: A grid monitoring configuration unit, configured to: access geographic information system data and divide monitoring grid units; construct a hierarchical communication architecture including an air communication layer, a water surface relay layer, and an underwater communication layer; generate bionic fish swarm dynamic deployment instructions according to the water depth gradient and the flow velocity field; A fuzzy scheduling control unit, communicatively connected to the bionic fish swarm sensor network, configured to: receive real-time water quality parameter data, execute the fuzzy rule base and output bionic fish swarm aggregation density correction instructions; send path adjustment signals to the bionic fish swarm through the hierarchical communication architecture; A Nash equilibrium decision engine, configured to: fuse historical pollution event data and real-time sensing data, construct an evaluation index system for pollutant diffusion speed, change rate of concentration gradient, and ecological toxicity index; solve the Pareto optimal weight based on the game model; Generate a dynamic pollution situation cloud map and mark the high-weight cruising areas; A poor state response execution module, including: a fingerprint library memory for storing the peak data of historical pollution events encoded as multi-dimensional feature vectors; a real-time matcher for calculating the weighted cosine similarity between the sensing data in the high-weight area and the fingerprint library; A two-level response trigger, when the matching degree exceeds the limit: (a) send an encrypted sampling instruction to the bionic fish swarm; (b) send a pollution pre-diffusion coordinate generation instruction to the unmanned aerial vehicle; A governance simulation verification platform, configured to: access the encrypted sampling data of the bionic fish swarm and the pollution pre-diffusion coordinates; parameterize the governance measures and then substitute them into the water quality evolution model for dynamic simulation; output a governance feasibility signal based on the convergence of the pollutant concentration gradient change rate; A hierarchical communication hardware architecture, including: an air communication layer: an unmanned aerial vehicle carrying remote sensing equipment, establishing a 5G / satellite backhaul link with the ground control center; a water surface relay layer: deploying self-organizing networking buoys equipped with air-water dual-frequency communication repeaters; an underwater communication layer: bionic fish swarms with built-in underwater acoustic modems, forming a dynamic routing sensing network; A control center visualization terminal, configured to: render the dynamic pollution situation cloud map in real time, mark the pollution risk level using a gradient color system; display the governance simulation trajectory and the feasibility evaluation result.

10. A computer device, characterized in that, The computer device includes: a processor and a memory, and at least one instruction, at least one program, a code set or an instruction set is stored in the memory, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by the processor to implement the water quality intelligent monitoring method for collaborative sampling of bionic fish swarms and unmanned aerial vehicles as described in any one of claims 1 to 7.

Images