Water quality pollution intelligent monitoring system and method based on big data

Abstract

The invention relates to the technical field of water quality monitoring, in particular to a water quality pollution intelligent monitoring system and method based on big data, and the intelligent monitoring method comprises the steps: S10, planning a plurality of monitoring points of a monitored water area, and generating an inspection task containing the position information of the monitoring points; s20, instructing the unmanned aerial vehicle group to distribute a water quality detection device to a specified water layer for water sample collection according to the inspection task; s30, after the water sample is collected, the water quality detection device generates water quality detection data according to preset index parameters, and if it is detected that any index parameter exceeds a safety threshold value, water quality early warning is triggered; s40, sampling and detection of the current monitoring point are completed; evaluating whether all the monitoring points in the inspection task are completed or not; s50, if the evaluation result is that the task is completed, instructing the unmanned aerial vehicle to return to the initial position along a preset return route; and if the assessment result is that the task is not completed, instructing the unmanned aerial vehicle to inspect the next monitoring point information preset in the task.

Description

Technical Field

[0001] This invention relates to the field of water quality monitoring technology, specifically to an intelligent water pollution monitoring system and method based on big data. Background Technology

[0002] Intelligent water pollution monitoring utilizes modern information technologies (such as the Internet of Things, big data, artificial intelligence, and sensor technology) to monitor, analyze, and provide early warnings of water quality in real time, continuously, automatically, and intelligently. With the rapid advancement of drone and IoT technologies, water quality monitoring methods are undergoing a revolution. Integrating intelligent water quality monitoring systems into drone platforms, coupled with linked algorithms, enables rapid and accurate remote collection of water quality data.

[0003] However, in the existing technology, the development of water quality detection using integrated intelligent water quality monitoring systems based on drones is still not perfect. In particular, for drone sampling, it only samples water from the target water area according to preset instructions and paths, and cannot automatically adjust the sampling area according to the degree of water pollution, which makes it impossible to analyze the range of pollution sources in a timely manner. Summary of the Invention

[0004] The purpose of this invention is to provide a smart water pollution monitoring system and method based on big data to solve the problems raised in the prior art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a smart monitoring method for water pollution based on big data, the smart monitoring method comprising:

[0006] S10. Plan several monitoring points in the water area to be monitored, and generate an inspection task containing the location information of the monitoring points;

[0007] S20: The command drone swarm, in accordance with the inspection task, flies along the preset route to the target monitoring point and deploys water quality testing devices to the designated water layer to collect water samples.

[0008] S30. After collecting water samples, the water quality detection device generates water quality detection data based on preset index parameters; it analyzes the water quality detection data in real time, and if any index parameter is detected to exceed the safety threshold, a water quality warning is triggered.

[0009] S40. After completing the sampling and testing at the current monitoring point, retrieve the water quality testing device; assess whether all monitoring points in the aforementioned inspection task have been completed.

[0010] S50. If the evaluation result indicates that the mission has been completed, instruct the UAV to return to the starting position along the preset return route.

[0011] If the assessment result indicates that the task is not completed, the UAV is instructed to autonomously navigate to the next target monitoring point based on the preset next monitoring point information in the inspection task, and then return to step S20 to execute.

[0012] The specific steps for establishing several monitoring points in the planned monitoring water area are as follows:

[0013] Acquire top-view image data of the monitoring area, wherein the monitoring area is the entire water area where water quality monitoring is required; identify the top-view image data and extract pollutant characteristics, wherein the pollutant characteristics are solid objects floating in the water; mark continuous areas containing pollutant characteristics and mark the center point of the area as the point to be determined; obtain the historical pollution areas marked in historical pollution events; wherein the historical pollution events are water events in which pollution has occurred.

[0014] Mark the undetermined points that overlap with historical pollution areas as pollution areas to be tested. Connect the remaining undetermined points in pairs. If a line connects to a pollution area to be tested, delete the undetermined point corresponding to that line. Calculate the distance D between the remaining undetermined points and their adjacent pollution areas to be tested. If the distance D is less than the distance threshold, delete the undetermined point. If the distance D is greater than the distance threshold, use the undetermined point as the center point and set an area with a radius of R as the new pollution area to be tested.

[0015] Each area to be contaminated is treated as a monitoring point. The newly added areas to be contaminated are integrated to obtain a set of monitoring point coordinates. Several flight paths are automatically generated based on the path algorithm and sent to the corresponding drones.

[0016] Step S20 includes:

[0017] The command drone swarm shares mission data through a mesh network and flies to monitoring points in different areas;

[0018] After hovering, the water quality testing device is deployed. If the sensor malfunctions, the system will automatically switch to the backup group and calibrate.

[0019] Step S30 includes:

[0020] The water quality testing device collects water samples through a multispectral sensor array and generates structured water quality testing data based on preset index parameters; the index parameters include pH value, dissolved oxygen, turbidity, heavy metal ion concentration, and organic pollutant concentration.

[0021] A lightweight convolutional neural network model is run in the edge computing module built into the water quality testing device to calculate the pollution risk score in real time by inputting water quality testing data.

[0022] If any indicator parameter exceeds the safety threshold or the pollution risk score is higher than the risk threshold, a water quality warning will be triggered.

[0023] Simultaneously, the time, coordinates, and parameters of the exceeded water quality warning will be generated into a data packet and sent to the monitoring center. Users can then view the data packet through the monitoring center.

[0024] The specific steps for retrieving the water quality testing device include:

[0025] Set the recovery speed and recover the detection device to the initial position in conjunction with the drone;

[0026] During the recovery process, the pressure value of the sealed chamber of the detection device is measured in real time. If the pressure change rate exceeds the stable threshold range, a leakage alarm is triggered.

[0027] If a leak alarm is triggered during the retraction of the water quality testing device, the following actions will be taken:

[0028] Then stop the recovery and release the backup detection device;

[0029] Send an alert to the monitoring platform containing location coordinates, fault type code, and risk area range;

[0030] The recycling process of the detection device will be written into the blockchain log.

[0031] The specific steps for assessing whether all monitoring points in the inspection task have been completed include: retrieving the preset set of monitoring point coordinates P = {p1, p2, ..., p...} in the inspection task. n};

[0032] Extract the monitoring points that have completed sampling and testing from set P to set C of completed monitoring points. When P = 0, the inspection task is considered complete.

[0033] Obtain the remaining battery value of each drone in the drone swarm and generate a battery matrix E = [e1, e2, ..., e2]. m ]; where E represents the set of electrical quantity matrices, e1, e2, ..., e m The remaining battery power values ​​are represented sequentially as follows: the remaining battery power value of the 1st drone, the remaining battery power value of the 2nd drone, ..., the remaining battery power value of the mth drone;

[0034] Send a migration command to drones with remaining power values ​​less than the power protection threshold, and migrate their tasks at monitoring points to the nearest drone with remaining power values ​​greater than the power protection threshold.

[0035] The updated task assignment table is broadcast via the Mesh network, triggering the autonomous flight path replanning of the receiving drone.

[0036] A smart water pollution monitoring system based on big data, the monitoring system comprising:

[0037] Inspection task module: Collects image data of the monitored water area, marks several water quality monitoring points on the image, and generates an inspection task containing the location information of the monitoring points;

[0038] Sampling module: The drone is instructed to fly along a preset route to the current target monitoring point according to the inspection task; after hovering above the target water area, it deploys a water quality testing device to the designated water layer to collect water samples;

[0039] Real-time detection module: After collecting water samples, the water quality detection device generates water quality detection data based on preset index parameters; it analyzes the water quality detection data in real time, and if any index parameter is detected to exceed the safety threshold, a water quality warning is immediately triggered;

[0040] Device recovery module: After completing sampling and testing at the current monitoring point, retrieve the water quality testing device; assess whether all preset monitoring points in the inspection task have been completed;

[0041] Task decision module:

[0042] If the assessment result indicates that the mission has been completed, the drone is instructed to return to the starting position along the preset return route;

[0043] If the assessment result indicates that the task is not completed, the UAV is instructed to autonomously navigate to the next target monitoring point based on the preset next monitoring point information in the inspection task, and then return to the sampling module.

[0044] The inspection task module includes a planning unit and a transport unit, wherein the planning unit includes:

[0045] Acquire top-view image data of the monitoring area, where the monitoring area is the entire water area where water quality monitoring is required;

[0046] Obtain the location information of historical monitoring points from the last inspection mission, establish a coordinate system, and mark the locations of historical monitoring points in the monitoring area;

[0047] Acquire water flow velocity, pollutant diffusion coefficient, and topographic data from historical pollution events;

[0048] With the goal of minimizing the pollution source location error, a candidate set of monitoring points is generated through Monte Carlo simulation;

[0049] By combining the drone's endurance, a greedy algorithm is used to filter the final set of monitoring point coordinates;

[0050] The transmission unit is used to send the set of monitoring point coordinates obtained by the planning unit to the designated UAV.

[0051] Compared with the prior art, the beneficial effects of the present invention are:

[0052] 1. Based on historical pollution diffusion models and real-time hydrological data, the system dynamically generates the optimal monitoring point coordinates, breaking through the limitations of preset fixed monitoring points. It predicts pollution paths through big data, adaptively adjusts the monitoring network, improves monitoring efficiency, and can locate pollution sources, minimizing pollution source location errors.

[0053] 2. Upgrade stand-alone operation to swarm intelligence, utilize collaborative algorithms to reduce inspection time and data transmission latency, and achieve millisecond-level early warning response. Attached Figure Description

[0054] Figure 1 This is a flowchart illustrating a smart water pollution monitoring method based on big data according to the present invention. Detailed Implementation

[0055] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0056] Example: Figure 1 As shown, this invention provides a smart water pollution monitoring method based on big data, the smart monitoring method comprising:

[0057] S10. Plan several monitoring points in the water area to be monitored, and generate an inspection task containing the location information of the monitoring points;

[0058] S20: The command drone swarm, in accordance with the inspection task, flies along the preset route to the target monitoring point and deploys water quality testing devices to the designated water layer to collect water samples.

[0059] S30. After collecting water samples, the water quality detection device generates water quality detection data based on preset index parameters; it analyzes the water quality detection data in real time, and if any index parameter is detected to exceed the safety threshold, a water quality warning is triggered.

[0060] S40. After completing the sampling and testing at the current monitoring point, retrieve the water quality testing device; assess whether all monitoring points in the aforementioned inspection task have been completed.

[0061] S50. If the evaluation result indicates that the mission has been completed, instruct the UAV to return to the starting position along the preset return route.

[0062] If the assessment result indicates that the task is not completed, the UAV is instructed to autonomously navigate to the next target monitoring point based on the preset next monitoring point information in the inspection task, and then return to step S20 to execute.

[0063] The specific steps for establishing several monitoring points in the planned monitoring water area are as follows:

[0064] Acquire top-view image data of the monitoring area, wherein the monitoring area is the entire water area where water quality monitoring is required; identify the top-view image data and extract pollutant characteristics, wherein the pollutant characteristics are solid objects floating in the water; mark continuous areas containing pollutant characteristics and mark the center point of the area as the point to be determined; obtain the historical pollution areas marked in historical pollution events; wherein the historical pollution events are water events in which pollution has occurred.

[0065] Mark the undetermined points that overlap with historical pollution areas as pollution areas to be tested. Connect the remaining undetermined points in pairs. If a line connects to a pollution area to be tested, delete the undetermined point corresponding to that line. Calculate the distance D between the remaining undetermined points and their adjacent pollution areas to be tested. If the distance D is less than the distance threshold, delete the undetermined point. If the distance D is greater than the distance threshold, use the undetermined point as the center point and set an area with a radius of R as the new pollution area to be tested.

[0066] Each area to be contaminated is treated as a monitoring point. The newly added areas to be contaminated are integrated to obtain a set of monitoring point coordinates. Several flight paths are automatically generated based on the path algorithm and sent to the corresponding drones.

[0067] Step S20 includes:

[0068] The command drone swarm shares mission data through a mesh network and flies to monitoring points in different areas;

[0069] After hovering, the water quality testing device is deployed. If the sensor malfunctions, the system will automatically switch to the backup group and calibrate.

[0070] Step S30 includes:

[0071] The water quality testing device collects water samples through a multispectral sensor array and generates structured water quality testing data based on preset index parameters; the index parameters include pH value, dissolved oxygen, turbidity, heavy metal ion concentration, and organic pollutant concentration.

[0072] A lightweight convolutional neural network model is run in the edge computing module built into the water quality testing device to calculate the pollution risk score in real time by inputting water quality testing data.

[0073] If any indicator parameter exceeds the safety threshold or the pollution risk score is higher than the risk threshold, a water quality warning will be triggered.

[0074] Simultaneously, the time, coordinates, and parameters of the exceeded water quality warning will be generated into a data packet and sent to the monitoring center. Users can then view the data packet through the monitoring center.

[0075] The specific steps for retrieving the water quality testing device include:

[0076] Set the recovery speed and recover the detection device to the initial position in conjunction with the drone;

[0077] During the recovery process, the pressure value of the sealed chamber of the detection device is measured in real time. If the pressure change rate exceeds the stable threshold range, a leakage alarm is triggered.

[0078] If a leak alarm is triggered during the retraction of the water quality testing device, the following actions will be taken:

[0079] Then stop the recovery and release the backup detection device;

[0080] Send an alert to the monitoring platform containing location coordinates, fault type code, and risk area range;

[0081] The recycling process of the detection device will be written into the blockchain log.

[0082] The specific steps for assessing whether all monitoring points in the inspection task have been completed include: retrieving the preset set of monitoring point coordinates P = {p1, p2, ..., p...} in the inspection task. n};

[0083] Extract the monitoring points that have completed sampling and testing from set P to set C of completed monitoring points. When P = 0, the inspection task is considered complete.

[0084] Obtain the remaining battery value of each drone in the drone swarm and generate a battery matrix E = [e1, e2, ..., e2]. m ]; where E represents the set of electrical quantity matrices, e1, e2, ..., e m The remaining battery power values ​​are represented sequentially as follows: the remaining battery power value of the 1st drone, the remaining battery power value of the 2nd drone, ..., the remaining battery power value of the mth drone;

[0085] Send a migration command to drones with remaining power values ​​less than the power protection threshold, and migrate their tasks at monitoring points to the nearest drone with remaining power values ​​greater than the power protection threshold.

[0086] The updated task assignment table is broadcast via the Mesh network, triggering the autonomous flight path replanning of the receiving drone.

[0087] A smart water pollution monitoring system based on big data, the monitoring system comprising:

[0088] Inspection task module: Collects image data of the monitored water area, marks several water quality monitoring points on the image, and generates an inspection task containing the location information of the monitoring points;

[0089] Sampling module: The drone is instructed to fly along a preset route to the current target monitoring point according to the inspection task; after hovering above the target water area, it deploys a water quality testing device to the designated water layer to collect water samples;

[0090] Real-time detection module: After collecting water samples, the water quality detection device generates water quality detection data based on preset index parameters; it analyzes the water quality detection data in real time, and if any index parameter is detected to exceed the safety threshold, a water quality warning is immediately triggered;

[0091] Device recovery module: After completing sampling and testing at the current monitoring point, retrieve the water quality testing device; assess whether all preset monitoring points in the inspection task have been completed;

[0092] Task decision module:

[0093] If the assessment result indicates that the mission has been completed, the drone is instructed to return to the starting position along the preset return route;

[0094] If the assessment result indicates that the task is not completed, the UAV is instructed to autonomously navigate to the next target monitoring point based on the preset next monitoring point information in the inspection task, and then return to the sampling module.

[0095] The inspection task module includes a planning unit and a transport unit, wherein the planning unit includes:

[0096] Acquire top-view image data of the monitoring area, where the monitoring area is the entire water area where water quality monitoring is required;

[0097] Obtain the location information of historical monitoring points from the last inspection mission, establish a coordinate system, and mark the locations of historical monitoring points in the monitoring area;

[0098] Acquire water flow velocity, pollutant diffusion coefficient, and topographic data from historical pollution events;

[0099] With the goal of minimizing the pollution source location error, a candidate set of monitoring points is generated through Monte Carlo simulation;

[0100] By combining the drone's endurance, a greedy algorithm is used to filter the final set of monitoring point coordinates;

[0101] The transmission unit is used to send the set of monitoring point coordinates obtained by the planning unit to the designated UAV.

[0102] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. A smart water pollution monitoring method based on big data, characterized in that: The intelligent monitoring method includes: S10. Plan several monitoring points in the water area to be monitored, and generate an inspection task containing the location information of the monitoring points; S20: The command drone swarm, in accordance with the inspection task, flies along the preset route to the target monitoring point and deploys water quality testing devices to the designated water layer to collect water samples. S30. After collecting water samples, the water quality detection device generates water quality detection data based on preset index parameters; it analyzes the water quality detection data in real time, and if any index parameter is detected to exceed the safety threshold, a water quality warning is triggered. S40. After completing the sampling and testing at the current monitoring point, retrieve the water quality testing device; assess whether all monitoring points in the aforementioned inspection task have been completed. S50. If the evaluation result indicates that the mission has been completed, instruct the UAV to return to the starting position along the preset return route. If the assessment result indicates that the task is not completed, the UAV is instructed to autonomously navigate to the next target monitoring point based on the preset next monitoring point information in the inspection task, and then return to step S20 to execute.

2. The intelligent water pollution monitoring method based on big data according to claim 1, characterized in that: The specific steps for establishing several monitoring points in the planned monitoring water area are as follows: Acquire top-view image data of the monitoring area, wherein the monitoring area is the entire water area where water quality monitoring is required; identify the top-view image data and extract pollutant characteristics, wherein the pollutant characteristics are solid objects floating in the water; mark continuous areas containing pollutant characteristics and mark the center point of the area as the point to be determined; obtain the historical pollution areas marked in historical pollution events; wherein the historical pollution events are water events in which pollution has occurred. Mark the undetermined points that overlap with the historical pollution areas as the pollution areas to be tested. Connect the remaining undetermined points in pairs. If a line overlaps with a pollution area to be tested, delete the undetermined point corresponding to that line. The distance D between the remaining undetermined points and their adjacent contaminated areas is calculated. If the distance D is less than the distance threshold, the undetermined point is deleted; if the distance D is greater than the distance threshold, the undetermined point is used as the center point, and an area with a radius of R is set as the newly added contaminated area. Each area to be contaminated is treated as a monitoring point. The newly added areas to be contaminated are integrated to obtain a set of monitoring point coordinates. Several flight paths are automatically generated based on the path algorithm and sent to the corresponding drones.

3. The intelligent water pollution monitoring method based on big data according to claim 1, characterized in that: Step S20 includes: The command drone swarm shares mission data through a mesh network and flies to monitoring points in different areas; After hovering, the water quality testing device is deployed. If the sensor malfunctions, the system will automatically switch to the backup group and calibrate.

4. The intelligent water pollution monitoring method based on big data according to claim 1, characterized in that: Step S30 includes: The water quality testing device collects water samples through a multispectral sensor array and generates structured water quality testing data based on preset index parameters; the index parameters include pH value, dissolved oxygen, turbidity, heavy metal ion concentration, and organic pollutant concentration. A lightweight convolutional neural network model is run in the edge computing module built into the water quality testing device to calculate the pollution risk score in real time by inputting water quality testing data. If any indicator parameter exceeds the safety threshold or the pollution risk score is higher than the risk threshold, a water quality warning will be triggered. Simultaneously, the time, coordinates, and parameters of the exceeded water quality warning will be generated into a data packet and sent to the monitoring center. Users can then view the data packet through the monitoring center.

5. The intelligent water pollution monitoring method based on big data according to claim 1, characterized in that: The specific steps for retrieving the water quality testing device include: Set the recovery speed and recover the detection device to the initial position in conjunction with the drone; During the recovery process, the pressure value of the sealed chamber of the detection device is measured in real time. If the pressure change rate exceeds the stable threshold range, a leakage alarm is triggered. If a leak alarm is triggered during the retraction of the water quality testing device, the following actions will be taken: Then stop the recovery and release the backup detection device; Send an alert to the monitoring platform containing location coordinates, fault type code, and risk area range; The recycling process of the detection device will be written into the blockchain log.

6. The intelligent water pollution monitoring method based on big data according to claim 1, characterized in that: The specific steps for assessing whether all monitoring points in the inspection task have been completed include: retrieving the preset set of monitoring point coordinates P = {p1, p2, ..., p...} in the inspection task. n }; Extract the monitoring points that have completed sampling and testing from set P to set C of completed monitoring points. When P = 0, the inspection task is considered complete.

7. The intelligent water pollution monitoring method based on big data according to claim 1, characterized in that: Obtain the remaining battery value of each drone in the drone swarm and generate a battery matrix. E = [e1, e2, ..., e] m ]; where E represents the set of electrical quantity matrices, e1, e2, ..., e m The remaining battery power values ​​are represented sequentially as follows: the remaining battery power value of the 1st drone, the remaining battery power value of the 2nd drone, ..., the remaining battery power value of the mth drone; For drones with remaining battery power less than the power protection threshold, a migration command is sent to relocate their tasks at monitoring points to the nearest drone with remaining battery power greater than the power protection threshold. The updated task allocation table is broadcast through the Mesh network to trigger the autonomous flight path replanning of the receiving drones.

8. A big data-based intelligent water pollution monitoring system, applied to the big data-based intelligent water pollution monitoring method described in any one of claims 1 to 7, characterized in that: The monitoring system includes: Inspection task module: Collects image data of the monitored water area, marks several water quality monitoring points on the image, and generates an inspection task containing the location information of the monitoring points; Sampling module: The drone is instructed to fly along a preset route to the current target monitoring point according to the inspection task; after hovering above the target water area, it deploys a water quality testing device to the designated water layer to collect water samples; Real-time detection module: After collecting water samples, the water quality detection device generates water quality detection data based on preset index parameters; it analyzes the water quality detection data in real time, and if any index parameter is detected to exceed the safety threshold, a water quality warning is immediately triggered; Device recovery module: After completing sampling and testing at the current monitoring point, retrieve the water quality testing device; assess whether all preset monitoring points in the inspection task have been completed; Task decision module: If the assessment result indicates that the mission has been completed, the drone is instructed to return to the starting position along the preset return route; If the assessment result indicates that the task is not completed, the UAV is instructed to autonomously navigate to the next target monitoring point based on the preset next monitoring point information in the inspection task, and then return to the sampling module.

9. The intelligent water pollution monitoring system based on big data according to claim 8, characterized in that: The inspection task module includes a planning unit and a transport unit, wherein the planning unit includes: Acquire top-view image data of the monitoring area, where the monitoring area is the entire water area where water quality monitoring is required; Obtain the location information of historical monitoring points from the last inspection mission, establish a coordinate system, and mark the locations of historical monitoring points in the monitoring area; Acquire water flow velocity, pollutant diffusion coefficient, and topographic data from historical pollution events; With the goal of minimizing the pollution source location error, a candidate set of monitoring points is generated through Monte Carlo simulation; By combining the drone's endurance, a greedy algorithm is used to filter the final set of monitoring point coordinates; The transmission unit is used to send the set of monitoring point coordinates obtained by the planning unit to the designated UAV.

Images