A water quality monitoring and inspection method, device and equipment based on sea-air cross-domain cooperation

Abstract

The application relates to a water quality monitoring and inspection method, device and equipment based on sea-air cross-domain cooperation, which comprises the following steps: acquiring a target monitoring area and a plurality of preset monitoring points; controlling a UAV to preliminarily detect the target monitoring area to obtain a suspected pollution area; obtaining a global monitoring path in the target monitoring area according to position information of the suspected pollution area and position information of the preset monitoring points; and finally controlling an unmanned ship to accurately detect the target monitoring area according to the global monitoring path to obtain a monitoring result of the target monitoring area. Compared with the prior art, the application provides a specific scheme for water quality monitoring by cooperation of a UAV and an unmanned ship, the advantages of the two different devices are fully utilized, the unmanned ship can accurately go to the destination for accurate detection, meaningless repeated cruising is avoided, the problem of poor endurance of the UAV is solved, and the detection efficiency is greatly improved.

Description

Technical Field

[0001] This invention relates to the field of water quality monitoring technology, and in particular to a water quality monitoring and inspection method, device and equipment based on cross-domain collaboration between sea and air. Background Technology

[0002] Unmanned aerial vehicles (UAVs) and unmanned surface vessels (USVs), as two types of unmanned aerial vehicles with high mobility and flexibility, are gradually being applied in various fields, including water quality monitoring. However, at present, most water quality monitoring relies on UAVs or USVs operating alone. The limited endurance of UAVs and the limited monitoring range of USVs inevitably limit their operation, making it difficult to achieve full regional coverage and sampling monitoring in complex and ever-changing water conditions.

[0003] Correspondingly, research on the collaboration between UAVs and unmanned surface vessels (USVs) mainly focuses on joint combat and collaborative landing. However, there are still many gaps in research on the collaborative use of UAVs and USVs for water quality monitoring. There is no suitable solution for the comprehensive coverage of water quality monitoring in irregular areas, nor is there a high-efficiency inspection planning scheme adapted to the collaboration between UAVs and USVs.

[0004] Therefore, there is an urgent need for an efficient cross-domain collaborative water quality monitoring and inspection solution. Summary of the Invention

[0005] In view of this, it is necessary to provide a water quality monitoring and inspection method, device and equipment based on cross-domain sea and air collaboration to solve the problem of how to use drones and unmanned surface vessels to achieve cross-domain sea and air collaborative water quality monitoring and inspection.

[0006] To achieve the above-mentioned technical objectives, the present invention adopts the following technical solution:

[0007] In a first aspect, the present invention provides a water quality monitoring and inspection method based on cross-domain sea-air collaboration, comprising:

[0008] Obtain the target monitoring area and multiple preset monitoring points within the target monitoring area;

[0009] The drone is controlled to conduct a preliminary inspection of the target monitoring area to identify suspected contaminated areas within the target monitoring area;

[0010] Based on the location information of the suspected contaminated area and the location information of the preset monitoring points, a global monitoring path is obtained within the target monitoring area;

[0011] The unmanned surface vessel is controlled to accurately detect the target monitoring area according to the global monitoring path, and the monitoring results of the target monitoring area are obtained.

[0012] Furthermore, acquiring the target monitoring area and multiple preset monitoring points within the target monitoring area includes:

[0013] The monitoring sea area is obtained and then divided into multiple sub-regions.

[0014] Multiple preset monitoring points are selected in each of the sub-regions;

[0015] The monitoring execution order is obtained based on the positional relationship of the multiple sub-regions;

[0016] Based on the monitoring execution order, the sub-region that the UAV needs to detect at the current moment is selected from the multiple sub-regions as the target monitoring region, and multiple preset monitoring points are determined within the target monitoring region;

[0017] The monitoring execution order is the sequential order of multiple sub-regions.

[0018] Furthermore, the multiple sub-regions are divided according to the communication distance between the UAV and the unmanned surface vessel, and the UAV and the unmanned surface vessel remain in two adjacent sub-regions respectively when performing detection.

[0019] Furthermore, obtaining the global monitoring path within the target monitoring area based on the location information of the suspected contaminated area and the location information of the preset monitoring points includes:

[0020] Both the location of the suspected contaminated area and the location of the preset monitoring point are used as task monitoring points;

[0021] The global monitoring path is obtained by calculating the path that passes through all task monitoring points in sequence based on the path planning algorithm.

[0022] Furthermore, the controlled drone performs preliminary detection on the target monitoring area to identify suspected contaminated areas within the target monitoring area, including:

[0023] The drone is controlled to conduct a preliminary inspection of the target monitoring area to identify suspected contaminated areas and obstacles within the target monitoring area;

[0024] The global monitoring path is obtained by calculating the path that passes through all task monitoring points sequentially based on the path planning algorithm, including:

[0025] The initial monitoring path is obtained by calculating the path that passes through all task monitoring points in sequence based on the path planning algorithm;

[0026] Based on the location information of the obstacle, a local monitoring path between two adjacent task monitoring points in the initial monitoring path is calculated based on the obstacle avoidance algorithm;

[0027] The initial monitoring path is optimized based on the local monitoring path to obtain the global monitoring path.

[0028] Furthermore, the initial monitoring path, calculated sequentially through all task monitoring points using a path planning algorithm, includes:

[0029] Based on the task monitoring points, a solution space is established based on all possible paths between them;

[0030] Based on environmental parameters, UAV parameters, and unmanned surface vessel parameters, a pheromone evaluation model is established, wherein the pheromone is used to characterize the cost between two task monitoring points;

[0031] Multiple ants are initialized in the solution space, and the position of each ant in the solution space represents a possible path.

[0032] Based on the pheromone evaluation model, the position of the ant in the solution space is iteratively optimized to obtain the initial monitoring path.

[0033] Furthermore, the step of calculating the local monitoring path between two adjacent task monitoring points in the initial monitoring path based on the obstacle's location information and an obstacle avoidance algorithm includes:

[0034] Based on the initial monitoring path, two adjacent task monitoring points are obtained;

[0035] Establish the target solution space based on the spatial range between two adjacent task monitoring points;

[0036] Using a task monitoring point as the root node, a fast exploration random tree is established in the target solution space. The leaf nodes of the fast exploration random tree are randomly expanded in the target solution space and avoid the obstacles. The fast exploration random tree includes a leaf node that reaches another task monitoring point.

[0037] The local monitoring path is obtained based on the fast exploration random tree.

[0038] Secondly, the present invention also provides a water quality monitoring and inspection device based on cross-domain sea-air collaboration, comprising:

[0039] The parameter initialization module is used to obtain the target monitoring area and multiple preset monitoring points within the target monitoring area;

[0040] The drone control module is used to control the drone to perform preliminary detection of the target monitoring area and obtain the suspected pollution area within the target monitoring area;

[0041] The path planning module is used to obtain the global monitoring path within the target monitoring area based on the location information of the suspected contaminated area and the location information of the preset monitoring points;

[0042] The unmanned surface vessel (USV) control module is used to control the USV to accurately detect the target monitoring area according to the global monitoring path, and obtain the monitoring results of the target monitoring area.

[0043] Thirdly, the present invention also provides an electronic device, including a memory and a processor, wherein,

[0044] Memory, used to store programs;

[0045] The processor, coupled to the memory, is used to execute the program stored in the memory to implement the steps in the water quality monitoring and inspection method based on cross-domain sea-air collaboration in any of the above implementation methods.

[0046] Fourthly, the present invention also provides a computer-readable storage medium for storing a computer-readable program or instruction, which, when executed by a processor, can implement the steps in the water quality monitoring and inspection method based on cross-domain sea-air collaboration in any of the above implementation methods.

[0047] This invention provides a water quality monitoring and inspection method, apparatus, and equipment based on cross-domain sea-air collaboration. It first acquires a target monitoring area and multiple preset monitoring points within the target monitoring area. Then, it controls a drone to perform preliminary detection of the target monitoring area, identifying suspected contaminated areas. Next, based on the location information of the suspected contaminated areas and the location information of the preset monitoring points, it obtains a global monitoring path within the target monitoring area. Finally, it controls an unmanned surface vessel (USV) to perform precise detection of the target monitoring area according to the global monitoring path, obtaining the monitoring results. Compared to existing technologies, this invention proposes a specific scheme for water quality monitoring through the collaborative cooperation of drones and USVs, fully leveraging the advantages of both devices. This allows the USV to accurately reach its destination for precise detection, avoiding meaningless repeated patrols, and simultaneously solving the problem of limited drone endurance, significantly improving detection efficiency. Attached Figure Description

[0048] Figure 1 This is a flowchart illustrating an embodiment of a water quality monitoring and inspection method based on cross-domain sea-air collaboration provided by the present invention.

[0049] Figure 2 for Figure 1 A flowchart of a method according to an embodiment of step S103;

[0050] Figure 3 for Figure 2A flowchart of a method according to an embodiment of step S202;

[0051] Figure 4 This is a schematic diagram of an embodiment of the water quality monitoring and inspection device based on cross-domain sea-air collaboration provided by the present invention.

[0052] Figure 5 A schematic diagram of an embodiment of the electronic device provided by the present invention. Detailed Implementation

[0053] Preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings, which form part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not intended to limit the scope of the present invention.

[0054] It is understood that the technical terms and English abbreviations that appear in the following text are all existing technologies, and those skilled in the art can understand their meaning based on the context. Due to space limitations, they will not be explained in detail in this article.

[0055] In the description of this application, "multiple" means two or more, unless otherwise expressly and specifically defined.

[0056] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0057] This invention provides a water quality monitoring and inspection method, device, equipment, and storage medium based on cross-domain sea-air collaboration, which will be described below.

[0058] Combination Figure 1 As shown, a specific embodiment of the present invention discloses a water quality monitoring and inspection method based on cross-domain sea-air collaboration, comprising:

[0059] S101. Obtain the target monitoring area and multiple preset monitoring points within the target monitoring area;

[0060] S102. Control the drone to conduct preliminary detection of the target monitoring area to obtain the suspected pollution area within the target monitoring area;

[0061] S103. Based on the location information of the suspected contaminated area and the location information of the preset monitoring points, obtain the global monitoring path within the target monitoring area;

[0062] S104. Control the unmanned surface vessel to accurately detect the target monitoring area according to the global monitoring path, and obtain the monitoring results of the target monitoring area.

[0063] Compared with existing technologies, this invention proposes a specific scheme for water quality monitoring through the collaborative cooperation of drones and unmanned surface vessels (USVs). It fully leverages the advantages of the two different devices, enabling USVs to accurately reach their destinations for precise testing, avoiding meaningless repeated patrols, and solving the problem of limited drone endurance, thus greatly improving testing efficiency.

[0064] Specifically, in a preferred embodiment, step S101, obtaining the target monitoring area and multiple preset monitoring points within the target monitoring area, includes:

[0065] The monitoring sea area is obtained and then divided into multiple sub-regions.

[0066] Multiple preset monitoring points are selected in each of the sub-regions;

[0067] The monitoring execution order is obtained based on the positional relationship of the multiple sub-regions;

[0068] Based on the monitoring execution order, the sub-region that the UAV needs to detect at the current moment is selected from the multiple sub-regions as the target monitoring region, and multiple preset monitoring points are determined within the target monitoring region;

[0069] The monitoring execution order is the sequential order of multiple sub-regions.

[0070] The above process involves the UAV and the unmanned surface vessel sequentially detecting multiple sub-regions according to the monitoring execution order, with the sub-region that the UAV needs to detect at the current moment being the target detection region.

[0071] Furthermore, in a preferred embodiment, the multiple sub-regions are divided according to the communication distance between the UAV and the unmanned surface vessel, and the UAV and the unmanned surface vessel remain in two adjacent sub-regions respectively when performing detection.

[0072] The above step S102, controlling the drone to perform preliminary detection on the target monitoring area to obtain the suspected pollution area within the target monitoring area, is implemented using existing technology and will not be described in detail in this article.

[0073] Furthermore, in a preferred embodiment, step S102 further includes:

[0074] The drone is controlled to conduct a preliminary inspection of the target monitoring area to obtain suspected contaminated areas and obstacles within the target monitoring area. In other words, during the preliminary inspection, the drone can detect other information such as obstacles in addition to suspected contaminated areas.

[0075] Furthermore, in combination Figure 2 As shown, in a preferred embodiment, step S103, obtaining the global monitoring path within the target monitoring area based on the location information of the suspected contaminated area and the location information of the preset monitoring points, includes:

[0076] S201. The location of the suspected contaminated area and the location of the preset monitoring point are both taken as task monitoring points;

[0077] S202. Calculate the path that passes through all task monitoring points in sequence based on the path planning algorithm to obtain the global monitoring path.

[0078] It is understandable that in step S201, when there is no suspected contaminated area in the initial detection results of the UAV, the preset detection point can be used as the task monitoring point.

[0079] Furthermore, in combination Figure 3 As shown, in a preferred embodiment, step S202 above, which involves calculating the path that sequentially passes through all task monitoring points based on the path planning algorithm to obtain the global monitoring path, specifically includes:

[0080] S301. Calculate the path that passes through all task monitoring points in sequence based on the path planning algorithm to obtain the initial monitoring path;

[0081] S302. Based on the location information of the obstacle, calculate the local monitoring path between two adjacent task monitoring points in the initial monitoring path using an obstacle avoidance algorithm.

[0082] S303. Optimize the initial monitoring path based on the local monitoring path to obtain the global monitoring path.

[0083] The above process optimizes the initial detection path using an obstacle avoidance algorithm to achieve obstacle avoidance during the operation of the unmanned surface vessel. It can be understood that when no obstacles exist, the initial detection path can be directly used as the final desired global detection path.

[0084] Specifically, in a preferred embodiment, step S301 above, which involves calculating the path sequentially passing through all task monitoring points based on a path planning algorithm to obtain the initial monitoring path, wherein the ant colony algorithm is used for path planning, and the specific process includes:

[0085] Based on the task monitoring points, a solution space is established based on all possible paths between them;

[0086] Based on environmental parameters, UAV parameters, and unmanned surface vessel parameters, a pheromone evaluation model is established, wherein the pheromone is used to characterize the cost between two task monitoring points;

[0087] Multiple ants are initialized in the solution space, and the position of each ant in the solution space represents a possible path.

[0088] Based on the pheromone evaluation model, the position of the ant in the solution space is iteratively optimized to obtain the initial monitoring path.

[0089] Furthermore, in a preferred embodiment, step S302 above, calculating the local monitoring path between two adjacent task monitoring points in the initial monitoring path based on the obstacle location information and an obstacle avoidance algorithm, wherein the RRT algorithm is used for obstacle avoidance path planning, the specific process of which includes:

[0090] Based on the initial monitoring path, two adjacent task monitoring points are obtained;

[0091] Establish the target solution space based on the spatial range between two adjacent task monitoring points;

[0092] Using a task monitoring point as the root node, a fast exploration random tree is established in the target solution space. The leaf nodes of the fast exploration random tree are randomly expanded in the target solution space and avoid the obstacles. The fast exploration random tree includes a leaf node that reaches another task monitoring point.

[0093] The local monitoring path is obtained based on the fast exploration random tree.

[0094] The present invention also provides a more detailed embodiment to more clearly illustrate the above steps S101 to S104:

[0095] After determining the scope of the monitoring sea area, the monitoring sea area is first divided into multiple sub-areas, and the monitoring execution order of the sub-areas is planned according to the monitoring task (that is, the order in which the UAV and the unmanned surface vessel perform the detection in turn. After the UAV and the unmanned surface vessel complete the monitoring task independently in their respective sub-areas, they enter the next sub-area to perform the task according to the monitoring execution order. Each time a detection is performed, the sub-area that needs to be detected is the target monitoring area). Several preset monitoring points are set up in the sub-areas.

[0096] The preset monitoring points within a sub-region can be set using any method, including random setting and selection according to certain rules. In this embodiment, two methods can be used: default autonomous coverage preset monitoring points and custom preset monitoring points. Autonomous coverage means that for each sub-region, the four equal division points of the lines connecting each vertex to the key points of the sub-region polygon are selected as preset monitoring points; custom preset monitoring points are selected manually according to the actual situation, and can be customized for key monitoring points such as sewage outlets and river inlets.

[0097] During the detection process, UAVs and unmanned surface vessels (USVs) must coordinate and perform patrol missions according to the planned monitoring sequence. The UAVs first conduct sweeping patrols over the sub-regions, using their onboard multispectral cameras to capture images of the water area and transmit these spectral images back to the shore-based platform in real time. The shore-based platform then analyzes the water quality of the monitored area based on the spectral images and makes preliminary judgments about suspected pollution areas and obstacles. Simultaneously, it sends the location information of suspected pollution areas and obstacles to the USVs. Throughout the process, the monitoring sequence must be followed: initial monitoring by UAVs in each sub-region, followed by precise monitoring by USVs. Furthermore, to ensure that the UAVs and USVs can maintain communication at all times, the sub-region division in this embodiment references the communication distance between the UAVs and USVs. During collaborative monitoring, the UAVs and USVs always remain within two adjacent sub-regions.

[0098] When communication is restricted due to drones and unmanned surface vessels (USVs) operating in two non-adjacent sub-areas, the drone can be controlled to hover or slow down to wait for the USV while maintaining uninterrupted communication, allowing both to continue collaborative monitoring operations within a certain distance. Furthermore, during the collaborative downtime when the drone is charging, the USV provides coverage monitoring of the sub-area where the drone is not operating. Once the drone is fully charged, it departs first and resumes collaborative operations according to the planned sub-area monitoring sequence.

[0099] Once the unmanned surface vessel (USV) completes its inspection mission in its assigned sub-area, and the unmanned aerial vehicle (UAV) completes its initial monitoring of the same sub-area, the USV will autonomously proceed to the suspected contaminated area to perform precise monitoring, based on the operational route and monitoring points for the next sub-area in the monitoring execution sequence. Simultaneously, the UAV will autonomously proceed to the next sub-area to perform its monitoring mission according to the monitoring execution sequence. When the UAV's battery level drops below a set value, it can return to the USV for charging, and the USV will then perform coverage monitoring of the sub-area where the UAV was not operating.

[0100] During its journey, the unmanned surface vessel (USV) uses pre-set monitoring points and suspected contaminated areas as monitoring task points (if there are no suspected contaminated areas, only the pre-set monitoring points are used as monitoring task points). Based on the location of the monitoring task points, the USV plans a global monitoring path within a sub-region, sequentially passing through each monitoring task point, using either the ant colony algorithm or the self-organizing map network algorithm (other path planning algorithms can also be used in practice). Furthermore, between two monitoring task points, the USV plans a local monitoring path using the RRT algorithm (other obstacle avoidance algorithms can also be used in practice) based on the location information of obstacles, thereby achieving obstacle avoidance.

[0101] The process of ant colony optimization (ACO) finding the optimal path can be summarized in the following steps:

[0102] 1. Initialize pheromones:

[0103] Before the algorithm begins, the pheromone concentration needs to be initialized. Generally, the pheromone concentration on all edges can be initialized to a small positive number, representing the pheromone left by the ant on each path.

[0104] 2. Random initialization of ants:

[0105] Randomly assign a starting node to each ant and place it in the starting node.

[0106] 3. The movement of ants:

[0107] Each ant chooses its next node to move to based on a certain probability function. Commonly used probability functions include roulette wheel selection or maximum value selection. Ants make their choices based on the pheromone concentration of the current node and heuristic information (such as distance). During their movement, ants leave behind pheromones to indicate the quality of the path.

[0108] 4. Solution space search:

[0109] All ants move according to a probability function until every ant reaches the destination. During the search, ants choose nodes with potentially better paths based on pheromone guidance and heuristic information. Ants can communicate with each other.

[0110] 5. Pheromone Update:

[0111] Once all ants have reached the destination, the pheromone concentration is updated based on the path quality. Typically, the current pheromone level is decayed, and then the new pheromone left by the ants is added. Path quality is generally determined by an objective function (such as path length). The pheromone concentration on better paths will increase, while the pheromone concentration on worse paths will decrease.

[0112] 6. Termination condition determination:

[0113] The decision is made based on preset termination conditions, such as a limit on the number of iterations or the discovery of a solution that meets specific conditions.

[0114] 7. Repeated iteration:

[0115] If the termination condition is not met, repeat steps 3 through 6 to continue searching for a better path. Each iteration uses the pheromone update from the previous iteration, and the ant's movement path may also change.

[0116] Through continuous iteration and pheromone updates, the ant colony algorithm can gradually converge to the optimal path. Ants tend to choose paths with high pheromone concentrations, but they also exhibit a degree of exploratory behavior, thus potentially finding a globally optimal solution or a solution close to the optimal one.

[0117] In this embodiment, the location of the monitoring task points is known, and the location information of possible suspected contamination areas can be obtained through drones to establish a solution space. Then, based on environmental parameters (water temperature, wave undulation, resistance, etc., which can be set with default values), drone parameters (drone driving capability, operating speed, fuel consumption rate, etc.), and unmanned surface vessel (USV) parameters (USV driving capability, operating speed, fuel consumption rate, etc.), a pheromone evaluation model is established. Pheromones are used to characterize the cost between two monitoring task points. Then, multiple ants are randomly initialized in the solution space, and parameters such as trajectory persistence 1-ρ, relative importance α, relative importance of visibility β, iteration count t, and ant population size m are set during the optimal path solving process. In the solution process of this embodiment, the probability function based on the k-th ant choosing the destination (i.e., the optimal path for the USV in this problem) is:

[0118]

[0119] The pheromone concentration update formula in the pheromone model of this embodiment is as follows:

[0120] τ ij (t+n)=(1-ρ)·τ ij (t)+Δτ ij (t)

[0121]

[0122] Where, Δτ ij k (i) represents the pheromone concentration released by the k-th ant on the link path between i and j, where ηij is the visibility between the two monitoring task points i and j, allowk is the set of nodes (nodes are possible paths) that the k-th ant has not yet visited, and τ ij (t) represents the pheromone intensity from monitoring task point i to monitoring task point j at the current iteration number t;

[0123] By iterating through the positions of multiple ants based on the pheromones possessed by each ant (obtained through a pheromone evaluation model), the optimal global monitoring path within the current sub-region can be calculated.

[0124] In another preferred embodiment, the global monitoring path of the unmanned surface vessel (USV) employs a self-organizing map network algorithm, namely the SOM algorithm. First, an SOM network is constructed based on the environmental map of the monitored sea area. In the SOM network, neurons correspond to different monitoring task points on the map. Then, the location information within the target monitoring sea area is converted into a vector representation, normalized, and input into the network. Next, a competitive learning algorithm is used to continuously adjust the neuron weights to obtain the mapping space between neurons. A moving average method is used to decay the update magnitude when updating the weights to ensure the stability of the algorithm. Finally, a search algorithm is used to search for the optimal path to obtain the global monitoring path.

[0125] If there are no obstacles in the sub-region, the unmanned surface vessel (USV) can perform a cruise inspection according to the global monitoring path described above. If there are obstacles in the sub-region, the USV can use the RRT algorithm to plan the local monitoring path between the two monitoring task points based on the location information of the obstacles. The global monitoring path is then used as the initial monitoring path and optimized through the local monitoring path to obtain the optimized global monitoring path, thereby enabling obstacle avoidance.

[0126] The RRT (Rapidly-exploring Random Tree) algorithm is a path planning algorithm that can be used to avoid obstacles.

[0127] The obstacle avoidance process of the RRT algorithm is as follows:

[0128] 1. Initialization:

[0129] First, we need to define the starting point and the target point, with the starting point as the root node of the tree. We also need to determine the location and shape of the obstacles.

[0130] 2. Add a node:

[0131] A new node is generated by creating a random point or selecting a point according to certain rules. This node will be added to the tree. To explore unknown spaces, the new node may fall outside the already generated tree.

[0132] 3. Find the nearest neighbor node:

[0133] Find the node closest to the new node from the existing tree. This can be done by calculating the Euclidean distance or using other distance metrics.

[0134] 4. Expanded Tree:

[0135] According to certain rules, an edge is added from the nearest neighbor node to the new node. This expands the tree and makes the new node a child of the nearest neighbor node.

[0136] 5. Obstacle avoidance detection:

[0137] During the tree expansion process, collision detection between new nodes and obstacles is required. If a new node collides with an obstacle, the node is discarded and a new node is generated.

[0138] 6. Determine the termination condition:

[0139] Check if the new node is close to the target point. If it is close enough to the target point, the algorithm can stop and return to the final path. Otherwise, return to step 2 and continue generating new nodes.

[0140] 7. Iteration:

[0141] By repeatedly performing steps 2 through 6, a path connecting the starting point and the target point is found.

[0142] Ultimately, the RRT algorithm generates a tree whose leaf nodes are near the target point and avoid obstacles as much as possible. Depending on the needs, the optimal path can be selected, or post-processing can be performed on the generated tree to obtain the final path. The RRT algorithm considers obstacle avoidance while also possessing the ability to quickly explore unknown spaces.

[0143] In this embodiment, the RRT algorithm works by continuously calculating the heading during the movement of the unmanned surface vessel. At each time step (i.e., each time the tree is expanded), a point is randomly sampled from the target space (i.e., the area between two monitoring task points). Then, the random tree is expanded, and the heading to the destination is continuously calculated until a motion trajectory is generated. It is then determined whether the path can reach the destination, and finally the obstacle avoidance path is obtained, which is the local monitoring path between the two monitoring task points.

[0144] In this embodiment, an improved integral LOS guidance algorithm is used to eliminate attitude errors during the unmanned surface vessel's (USV) movement, and the obtained desired speed and desired heading angle are converted into PWM signals to control the navigation speed and direction. A neural network PID controller is employed to improve dynamic response performance.

[0145] After the unmanned surface vessel (USV) arrives at a suspected contaminated area, it uses its onboard water quality monitoring components to collect and analyze water samples from the area and compares the results with water quality parameters in the database. If the water quality parameters exceed the standards, the USV retains the contaminated water sample from that area and then proceeds with the mission.

[0146] In this embodiment, the water quality monitoring component uses an STM32F103R6 as the main control chip and is equipped with multiple sensor probes sensitive to different water quality indicators. These sensor probes are connected to the detection circuit, and their output is a 4-20mA current signal. After A / D conversion, the signal is output using six A / D channels, corresponding to six main water quality indicators: water temperature, pH value, dissolved oxygen, turbidity, oxidation-reduction potential, and ammonia nitrogen. To ensure sufficient accuracy of the data collected by the water quality sensors, this embodiment uses a precision I / V conversion integrated circuit composed of RCV420, operating at an industrial-grade temperature range of -25℃ to +85℃, to convert the 4-20mA current into a 0-5V voltage before A / D conversion.

[0147] By working closely together, unmanned surface vessels (USVs) and unmanned aerial vehicles (UAVs) compensate for the deficiencies and blind spots of individual operations. The USV's take-off and landing platform provides power to the UAVs, solving their endurance problem. It also compensates for the monitoring efficiency during the UAVs' charging downtime, achieving intelligent, dynamic, and real-time monitoring, which greatly improves monitoring efficiency.

[0148] This embodiment has the following effects and advantages:

[0149] 1. This water quality monitoring and inspection method and system based on cross-domain sea and air collaboration fully combines the advantages of UAVs and unmanned surface vessels, making up for the shortcomings of single-unit operation in terms of poor endurance and limited monitoring range.

[0150] 2. A collaborative patrol mode was designed, and the optimal detection route was replanned for the monitoring points and patrol path. This also made up for the problem of weak operation during the collaborative downtime of drone charging, and solved the shortcomings of traditional inspection methods such as small operation range and monotonous operation, thus efficiently achieving full coverage of monitoring and inspection.

[0151] To better implement the water quality monitoring and inspection method based on sea-air cross-domain collaboration in this invention, based on the water quality monitoring and inspection method based on sea-air cross-domain collaboration, please refer to the corresponding... Figure 4 , Figure 4 This is a schematic diagram of an embodiment of the water quality monitoring and inspection device based on sea-air cross-domain collaboration provided by the present invention. The water quality monitoring and inspection device 400 based on sea-air cross-domain collaboration provided by this embodiment includes:

[0152] The parameter initialization module 410 is used to acquire the target monitoring area and multiple preset monitoring points within the target monitoring area;

[0153] The UAV control module 420 is used to control the UAV to perform preliminary detection on the target monitoring area and obtain the suspected pollution area within the target monitoring area;

[0154] The path planning module 430 is used to obtain a global monitoring path within the target monitoring area based on the location information of the suspected contaminated area and the location information of the preset monitoring points.

[0155] The unmanned surface vessel control module 440 is used to control the unmanned surface vessel to accurately detect the target monitoring area according to the global monitoring path, and obtain the monitoring results of the target monitoring area.

[0156] It should be noted that the corresponding device 400 provided in the above embodiments can implement the technical solutions described in the above method embodiments. The specific implementation principles of the above modules or units can be found in the corresponding content in the above method embodiments, and will not be repeated here.

[0157] Please see Figure 5 , Figure 5 This is a schematic diagram of the electronic device provided in an embodiment of the present invention. Based on the above-described water quality monitoring and inspection method based on cross-domain sea-air collaboration, the present invention also provides a water quality monitoring and inspection device 500 based on cross-domain sea-air collaboration, i.e., the aforementioned electronic device. The water quality monitoring and inspection device 500 based on cross-domain sea-air collaboration can be a mobile terminal, desktop computer, laptop, handheld computer, server, or other computing device. The water quality monitoring and inspection device 500 based on cross-domain sea-air collaboration includes a processor 510, a memory 520, and a display 530. Figure 5 Only some components of the water quality monitoring and inspection equipment based on cross-domain sea-air collaboration are shown. However, it should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented instead.

[0158] In some embodiments, the memory 520 can be an internal storage unit of the water quality monitoring and inspection equipment 500 based on sea-air cross-domain collaboration, such as a hard disk or memory of the water quality monitoring and inspection equipment 500. In other embodiments, the memory 520 can also be an external storage device of the water quality monitoring and inspection equipment 500 based on sea-air cross-domain collaboration, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the water quality monitoring and inspection equipment 500 based on sea-air cross-domain collaboration. Furthermore, the memory 520 can also include both internal storage units and external storage devices of the water quality monitoring and inspection equipment 500 based on sea-air cross-domain collaboration. The memory 520 is used to store application software and various types of data installed on the water quality monitoring and inspection equipment 500 based on sea-air cross-domain collaboration, such as the program code of the water quality monitoring and inspection equipment 500 based on sea-air cross-domain collaboration. The memory 520 can also be used to temporarily store data that has been output or will be output. In one embodiment, the memory 520 stores a water quality monitoring and inspection program 540 based on sea-air cross-domain collaboration. The water quality monitoring and inspection program 540 based on sea-air cross-domain collaboration can be executed by the processor 510 to realize the water quality monitoring and inspection method based on sea-air cross-domain collaboration in the various embodiments of this application.

[0159] In some embodiments, processor 510 may be a central processing unit (CPU), microprocessor or other data processing chip, used to run program code stored in memory 520 or process data, such as executing a water quality monitoring and inspection method based on cross-domain sea and air collaboration.

[0160] In some embodiments, display 530 may be an LED display, a liquid crystal display, a touch-screen liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. Display 530 is used to display information from the sea-air cross-domain collaborative water quality monitoring and inspection equipment 500 and to display a user interface for visualization. Components 510-530 of the sea-air cross-domain collaborative water quality monitoring and inspection equipment 500 communicate with each other via a system bus.

[0161] In one embodiment, when the processor 510 executes the water quality monitoring and inspection program 540 based on sea-air cross-domain collaboration in the memory 520, the steps in the water quality monitoring and inspection method based on sea-air cross-domain collaboration as described above are implemented.

[0162] This embodiment also provides a computer-readable storage medium storing a water quality monitoring and inspection program based on cross-domain sea-air collaboration. When the water quality monitoring and inspection program based on cross-domain sea-air collaboration is executed by a processor, it can implement the steps in the above embodiment.

[0163] This invention provides a water quality monitoring and inspection method, apparatus, and equipment based on cross-domain sea-air collaboration. It first acquires a target monitoring area and multiple preset monitoring points within the target monitoring area. Then, it controls a drone to perform preliminary detection of the target monitoring area, identifying suspected contaminated areas. Next, based on the location information of the suspected contaminated areas and the location information of the preset monitoring points, it obtains a global monitoring path within the target monitoring area. Finally, it controls an unmanned surface vessel (USV) to perform precise detection of the target monitoring area according to the global monitoring path, obtaining the monitoring results. Compared to existing technologies, this invention proposes a specific scheme for water quality monitoring through the collaborative cooperation of drones and USVs, fully leveraging the advantages of both devices. This allows the USV to accurately reach its destination for precise detection, avoiding meaningless repeated patrols, and simultaneously solving the problem of limited drone endurance, significantly improving detection efficiency.

[0164] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. A water quality monitoring and inspection method based on cross-domain sea-air collaboration, characterized in that, include: Obtain the target monitoring area and multiple preset monitoring points within the target monitoring area; The drone is controlled to conduct a preliminary inspection of the target monitoring area to identify suspected contaminated areas within the target monitoring area; Based on the location information of the suspected contaminated area and the location information of the preset monitoring points, a global monitoring path is obtained within the target monitoring area, including: taking the location of the suspected contaminated area and the location of the preset monitoring points as task monitoring points; and calculating the path that passes through all task monitoring points in sequence based on a path planning algorithm to obtain the global monitoring path. The unmanned surface vessel is controlled to accurately detect the target monitoring area according to the global monitoring path, and the monitoring results of the target monitoring area are obtained; The controlled drone performs preliminary detection on the target monitoring area to identify suspected contaminated areas within the target monitoring area, including: The drone is controlled to conduct a preliminary inspection of the target monitoring area to identify suspected contaminated areas and obstacles within the target monitoring area; The global monitoring path is obtained by calculating the path that passes through all task monitoring points sequentially based on the path planning algorithm, including: The initial monitoring path is obtained by calculating the path that passes through all task monitoring points in sequence based on the path planning algorithm. Based on the location information of the obstacle, a local monitoring path between two adjacent task monitoring points in the initial monitoring path is calculated based on the obstacle avoidance algorithm; The initial monitoring path is optimized based on the local monitoring path to obtain the global monitoring path.

2. The water quality monitoring and inspection method based on cross-domain sea-air collaboration according to claim 1, characterized in that, The acquisition of the target monitoring area and multiple preset monitoring points within the target monitoring area includes: The monitoring sea area is obtained and then divided into multiple sub-regions. Multiple preset monitoring points are selected in each of the sub-regions; The monitoring execution order is obtained based on the positional relationship of the multiple sub-regions; Based on the monitoring execution order, the sub-region that the UAV needs to detect at the current moment is selected from the multiple sub-regions as the target monitoring region, and multiple preset monitoring points are determined within the target monitoring region; The monitoring execution order is the sequential order of multiple sub-regions.

3. The water quality monitoring and inspection method based on cross-domain sea-air collaboration according to claim 2, characterized in that, The multiple sub-regions are divided according to the communication distance between the UAV and the unmanned surface vessel, and the UAV and the unmanned surface vessel remain in two adjacent sub-regions respectively when performing detection.

4. The water quality monitoring and inspection method based on cross-domain sea-air collaboration according to claim 1, characterized in that, The initial monitoring path is obtained by calculating the path that passes through all task monitoring points sequentially based on the path planning algorithm, including: Based on the task monitoring points, a solution space is established based on all possible paths between the task monitoring points; Based on environmental parameters, UAV parameters, and unmanned surface vessel parameters, a pheromone evaluation model is established, wherein the pheromone is used to characterize the cost between two task monitoring points; Multiple ants are initialized in the solution space, and the position of each ant in the solution space represents a possible path. Based on the pheromone evaluation model, the position of the ant in the solution space is iteratively optimized to obtain the initial monitoring path.

5. The water quality monitoring and inspection method based on cross-domain sea-air collaboration according to claim 1, characterized in that, The step of calculating the local monitoring path between two adjacent task monitoring points in the initial monitoring path based on the obstacle's location information and an obstacle avoidance algorithm includes: Based on the initial monitoring path, two adjacent task monitoring points are obtained; Establish the target solution space based on the spatial range between two adjacent task monitoring points; Using a task monitoring point as the root node, a fast exploration random tree is established in the target solution space. The leaf nodes of the fast exploration random tree are randomly expanded in the target solution space and avoid the obstacles. The fast exploration random tree includes a leaf node that reaches another task monitoring point. The local monitoring path is obtained based on the fast exploration random tree.

6. A water quality monitoring and inspection device based on cross-domain sea-air collaboration, characterized in that, include: The parameter initialization module is used to obtain the target monitoring area and multiple preset monitoring points within the target monitoring area; The drone control module is used to control the drone to perform preliminary detection of the target monitoring area and obtain the suspected pollution area within the target monitoring area; The path planning module is used to obtain a global monitoring path within the target monitoring area based on the location information of the suspected contaminated area and the location information of the preset monitoring points, including: taking the location of the suspected contaminated area and the location of the preset monitoring points as task monitoring points; and calculating the path that passes through all task monitoring points in sequence based on the path planning algorithm to obtain the global monitoring path. The unmanned surface vessel (USV) control module is used to control the USV to accurately detect the target monitoring area according to the global monitoring path and obtain the monitoring results of the target monitoring area. The controlled drone performs preliminary detection on the target monitoring area to identify suspected contaminated areas within the target monitoring area, including: The drone is controlled to conduct a preliminary inspection of the target monitoring area to identify suspected contaminated areas and obstacles within the target monitoring area; The global monitoring path is obtained by calculating the path that passes through all task monitoring points sequentially based on the path planning algorithm, including: The initial monitoring path is obtained by calculating the path that passes through all task monitoring points in sequence based on the path planning algorithm. Based on the location information of the obstacle, a local monitoring path between two adjacent task monitoring points in the initial monitoring path is calculated based on the obstacle avoidance algorithm; The initial monitoring path is optimized based on the local monitoring path to obtain the global monitoring path.

7. An electronic device, characterized in that, Including memory and processor, among which, The memory is used to store programs; The processor, coupled to the memory, is used to execute the program stored in the memory to implement the steps in the water quality monitoring and inspection method based on cross-domain sea-air collaboration as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, Used to store computer-readable programs or instructions, which, when executed by a processor, are capable of implementing the steps in the water quality monitoring and inspection method based on cross-domain sea-air collaboration as described in any one of claims 1 to 5.

Images