Water level information monitoring method and device based on navigation mark and fused with multiple intelligent sensors

Abstract

The invention relates to the technical field of water level information monitoring based on a navigation mark, and discloses a water level information monitoring method and device based on fusion of multiple intelligent sensors of the navigation mark, and the method comprises the steps: carrying out the correction estimation of the water depth based on a correction term through the data of multiple sensors after preprocessing, and obtaining the water depth after the correction estimation; performing position matching analysis on the beacon vessel embodied position and the beacon vessel body reference coordinate, and judging whether the beacon vessel embodied position meets the navigation standard or not by combining with the water depth; and if the navigation mark vessel embodied position does not conform to the navigation standard, generating an optimal adjustment path, and driving the navigation mark vessel body to the recommended position. According to the method, correction terms are constructed through the flow speed, the temperature and the attitude angle, the water depth estimation precision is improved, Beidou position information and reference coordinates are combined for matching, whether the navigation mark hull deviates from the navigation standard or not is judged, once deviation occurs, the navigation mark hull is driven to adjust the position through path planning, and integration of water level monitoring and navigation mark management and control is achieved.

Description

Technical Field

[0001] The present invention relates to the field of water level information monitoring based on navigation marks, and in particular to a water level information monitoring method and device based on navigation mark multi-intelligent sensor fusion. Background Art

[0002] In navigable waters such as rivers, harbors, and lakes, accurate water level monitoring is crucial for ensuring waterway safety, guiding ship traffic, and optimizing scheduling and management. With the continuous development of intelligent navigation aids and the Internet of Things (IoT) technology, floating navigation aid platforms have gradually acquired capabilities for data collection, edge computing, and remote communication, becoming a crucial vehicle for the digitalization of waterborne infrastructure. In complex hydrodynamic environments, a single sensor is susceptible to disturbances such as flow velocity, temperature differences, and fluctuations, making it difficult to provide stable, high-precision water level data. Therefore, integrating multi-source sensors, dynamically sensing environmental changes, and enabling intelligent judgment and path control have become key research areas for enhancing the intelligence of navigation aid systems.

[0003] Patent publication CN111103038B proposes a method and system for monitoring hydrological information. This method primarily obtains hydrological information (water level, area) from measurement points, plots a water level-area time curve, and infers topographic information to estimate the water storage capacity of the reservoir area. When the water level or storage capacity exceeds a preset threshold, the drainage system is triggered for regulation. This method emphasizes dynamic modeling of water level and area within the macroscopic water body. It is suitable for water storage management scenarios in reservoirs or static lakes. Measurement points are fixed, the water environment is relatively stable, and there is no movement or drift of monitoring nodes. Furthermore, it lacks multi-dimensional environmental perception capabilities.

[0004] In addition, traditional water level monitoring systems mostly rely on radar or ultrasonic water level gauges deployed at fixed sites on the shore, or obtain hydrological information through manual inspections, remote sensing images, and other means (for example, CN106228579B, CN111142165A). However, these systems have defects such as high deployment rigidity, poor adaptability, and weak data real-time performance. This makes it difficult to achieve efficient and reliable water level perception and regulation, especially under floating navigation platforms and complex flow conditions.

[0005] To address this problem, this patent proposes a water level information monitoring method based on the fusion of multiple intelligent sensors of navigation marks, which improves the accuracy and real-time performance of water level monitoring by fusing multi-sensor data to perform water depth correction estimation. Summary of the Invention

[0006] This invention provides a water level monitoring method based on the fusion of multiple intelligent sensors for navigational aids. This method effectively addresses technical issues such as insufficient accuracy, inability to detect position offsets in real time, difficulty correcting for hydrological anomalies, and inability to monitor equipment operating status, as observed with traditional water level monitoring methods. Traditional methods often rely on single radar or pressure-type water level gauges, which are susceptible to fluctuations, water flow disturbances, and attitude changes, resulting in large data errors and difficulty adapting to dynamic and complex water environments. This method deploys multiple types of intelligent sensors (such as radar flowmeters and temperature sensors), fuses multi-source data, and introduces water level correction terms based on physical factors such as temperature, flow velocity, and attitude angle. This significantly improves the stability and accuracy of water level estimation. Furthermore, this method can detect navigational aid hull offsets and determine navigation standards. By integrating water level information, it dynamically generates adjustment paths and controls the hull's return to its docking position, improving navigational stability and safety. Furthermore, this method addresses the issues of invisibility of on-site equipment status and delayed fault diagnosis. By reporting the operating status of intelligent sensors and uploading full-process data, this method achieves digital and visual water level monitoring.

[0007] To achieve the above object, the present invention provides a water level information monitoring method based on multi-intelligent sensor fusion of navigation marks, comprising the following steps: S1: deploy intelligent sensors on the buoy hull, collect multi-sensor data and pre-process them to obtain pre-processed multi-sensor data; S2: Using the pre-processed multi-sensor data, a correction estimate is made on the water depth based on the correction term to obtain a corrected estimated water depth; S3: Perform position matching analysis on the actual position of the buoy vessel in the pre-processed multi-sensor data and the reference coordinates of the buoy vessel, calculate the drift distance, and determine whether the actual position of the buoy vessel meets the navigation standards based on the water depth; S4: If the current position of the buoy hull does not meet the navigation standards, an optimal adjustment path is generated to drive the buoy hull to the recommended position. The smart sensor status information, pre-processed multi-sensor data, corrected estimated water depth, drift distance and buoy hull position information are uploaded to the management platform for visual management. The smart sensor status information includes the smart sensor battery level and operating time.

[0008] As a further improvement method of the present invention: Optionally, collect multi-sensor data and perform pre-processing, including: The intelligent sensor includes a temperature sensor, a Beidou positioning module, a liquid level meter, and a radar flow meter. The temperature sensor is used to monitor the water temperature, the Beidou positioning module is used to locate the position of the buoy hull, wherein the position of the buoy hull is the longitude and latitude coordinates, the liquid level meter is used to monitor the water pressure, and the radar flow meter is used to monitor the water depth, the attitude angle of the buoy hull, and the water flow rate and direction. The deployed smart sensors are used to monitor the hydrological information of the buoy's hull at a fixed time period every day to obtain daily multi-sensor data. The multi-sensor data is in the form of a multi-dimensional data sequence, including water temperature data sequence, buoy hull position data sequence, water pressure data sequence, water depth data sequence, buoy hull attitude angle data sequence, water flow rate and flow direction sequence; The data sequence in the multi-sensor data is filtered and interpolated in sequence, and the last data value of the data sequence is extracted to form the pre-processed multi-sensor data; The pre-processed multi-sensor data consists of water temperature, buoy hull location, water pressure, water depth, buoy hull attitude angle, water flow rate and flow direction, wherein water temperature, buoy hull location, water pressure, water depth, buoy hull attitude angle, water flow rate and flow direction are, respectively, the last data values ​​in the water temperature data sequence, buoy hull location data sequence, water pressure data sequence, water depth data sequence, buoy hull attitude angle data sequence, water flow rate and flow direction sequence after filtering and interpolation completion processing.

[0009] Optionally, the pre-processed multi-sensor data is used to perform a correction estimation of the water depth based on a correction term, including: Extracting water depth from the pre-processed multi-sensor data , integrating water temperature, attitude angle of the buoy hull and water velocity to generate correction terms, and make correction estimates for the extracted water depth, where the correction terms include flow correction terms and height deviation correction terms; The calculation formula of the flow correction term is: ; in, is the flow correction term based on water temperature and flow velocity, V represents the flow velocity, Indicates the standard water density at the set standard water temperature. Indicates the water temperature, Indicates water temperature The density of water below; The calculation formula of the height measurement deviation correction term is: ; in, It represents the height deviation correction item, h represents the installation height of the radar flowmeter, are the attitude angles of the buoy ship in the pre-processed multi-sensor data. They are the pitch angle and roll angle of the buoy ship respectively; The flow correction term and the height deviation correction term are weighted to generate the correction term , the water depth in the preprocessed multi-sensor data Make a corrected estimate to get the corrected estimated water depth .

[0010] Optionally, performing position matching analysis on the actual position of the navigation beacon hull and the reference coordinates of the navigation beacon hull, and calculating the drift distance, including; Extracting the actual position of the buoy vessel from pre-processed multi-sensor data , and obtain the reference coordinates of the buoy hull , set the elliptical area centered on the reference coordinates of the navigation mark ship as the recommended navigation area, and calculate the actual position of the navigation mark ship Whether it deviates from the deviation coefficient of the recommended navigation area , as the result of position matching analysis, where ,like If it is 0, it means the navigation mark ship is at its current position. Without deviating from the recommended navigation area, if If it is 1, it means the navigation mark ship is in the actual position Departure from the recommended navigation area, where the navigation aid vessel is located Reference coordinates of the buoy and the ship All are latitude and longitude coordinates; Calculate the actual position of the buoy ship using the Haversine formula Reference coordinates of the buoy and the ship The distance between the two is used as the navigation mark of the ship's actual location. Drift distance.

[0011] Optionally, judging whether the current position of the buoy vessel meets the navigation standards in combination with the water depth and the position matching analysis result includes: Get the corrected estimated water depth ,like Greater than the preset minimum water depth difference, and the position matches the analysis results , then determine the actual position of the navigation mark ship It does not meet the navigation standards, where H represents the critical safety water level. Specifically, H is set to 10 meters and the preset minimum water depth difference is 5 meters.

[0012] Optionally, if the current position of the buoy vessel does not meet the navigation standard, an optimal adjustment path is generated, including: If the buoy vessel's current position does not meet the navigation standards, a recommended position corresponding to the buoy vessel's current position is selected from the candidate position set, wherein the candidate position set is composed of multiple buoy vessel docking positions that can be used for temporary docking, and the buoy vessel docking position is the latitude and longitude coordinates. The corresponding recommended position selection formula is: ; in, Indicates the actual position of the navigation vessel The corresponding recommended location, represents the set of candidate locations, , p represents any buoy hull docking position in the candidate position set, Indicates the docking position of the navigation mark ship The actual position of the navigation mark vessel The evaluation results of the evaluation index at the k-th position, where , The smaller it is, the closer the buoy is to the docking position of the ship. The better the performance of the evaluation index at the kth position, is the evaluation coefficient of the k-th position evaluation index, set Specifically, set They are 0.4, 0.4, and 0.2 respectively; Represents the set of candidate locations The buoy hull berthing position with the best comprehensive evaluation result of the position evaluation index is selected as the buoy hull setting position Corresponding recommended location ; Indicates the docking position of the navigation mark ship The actual position of the buoy ship The distance cost index represents the docking position of the navigation mark ship The current position of the buoy ship The distance between Indicates the docking position of the navigation mark ship The actual position of the navigation mark vessel The water flow interference index represents the docking position of the navigation mark ship. The current position of the buoy ship The difference between the azimuth and the direction of water flow, Indicates the docking position of the navigation mark ship The actual position of the navigation mark vessel The docking heat index represents the docking position of the navigation mark ship Number of hulls that have docked at the buoy; The waters where the buoy hull is located are divided into multiple continuous grid areas, and each grid area is regarded as a grid. The grid where the buoy hull is located and the grid where the recommended position is located are obtained as the starting point and the target point respectively. The improved A* search algorithm is used to solve the optimal adjustment path between the starting point and the target point, in which the buoy hull is deployed in each divided grid.

[0013] Optionally, using the improved A* search algorithm to solve and obtain the optimal adjustment path between the starting point and the target point includes: The improved A* search algorithm integrates the water level information monitored by all navigational buoys, introduces the differences in water depth and water flow direction between adjacent grids, and optimizes the path cost function in the A* search algorithm, making the water level changes of the optimal adjustment path smoother and safer. The water level information includes the corrected estimated water depth and water flow direction of each grid.

[0014] In order to solve the above problem, the present invention further provides an electronic device, comprising: a memory storing at least one instruction; Communication interfaces to enable electronic equipment to communicate; and The processor executes the instructions stored in the memory to implement the above-mentioned water level information monitoring method based on multi-intelligent sensor fusion of navigation marks.

[0015] In order to solve the above problems, the present invention also provides a computer-readable storage medium, which stores at least one instruction, and the at least one instruction is executed by a processor in an electronic device to implement the above-mentioned water level information monitoring method based on multi-intelligent sensor fusion of navigation marks.

[0016] Compared with the existing technology, the present invention proposes a water level information monitoring method based on the fusion of multiple intelligent sensors of navigation marks, which has the following beneficial effects: First, the flow correction and height deviation correction terms significantly improve the radar flowmeter's measurement accuracy and system stability in dynamic hydrological environments. In natural water bodies, the effect of water temperature on liquid density can cause slight elevation or depression of the radar wave reflection interface, particularly in areas with high flow velocities or significant temperature differences. The flow correction term effectively compensates for systemic water level deviations caused by thermal expansion and contraction and changes in fluid viscosity, enhancing the seasonal consistency and lateral comparability of the measured data. Furthermore, the attitude angle changes caused by the buoy's hull under wave disturbances can cause the radar flowmeter's ranging direction to deviate from the vertical axis, resulting in underestimation of the actual measured value. A cosine correction model based on attitude angle calculation enables real-time dynamic compensation for radar antenna height projection errors, effectively eliminating high-frequency noise interference from short-term fluctuations on the depth data. This significantly improves the continuity and smoothness of the depth curve, keeping ranging errors within the centimeter range, especially in windy and choppy conditions with frequent surface disturbances. These two correction mechanisms work synergistically to provide the buoy's depth measurement system with multi-factor dynamic stability enhancement capabilities for real-world waters.

[0017] At the same time, for the recommended location selection method, the distance cost item is based on the Haversine distance metric, which can accurately evaluate the geographical offset between the actual position of the buoy vessel and the docked position, ensuring that the recommended position will not cause large-scale channel offset; the water flow direction interference cost constructs a similarity function based on the angle between the main direction of the water flow and the direction of the candidate position, which is particularly effective in turbulent or complex hydrological areas, reducing the drift or rotation of the site caused by the impact of the water flow; the docking heat cost can intelligently avoid high-frequency navigation areas and reduce the offset of the buoy caused by human interference or collision. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A schematic flow chart of a water level information monitoring method based on fusion of multiple intelligent sensors of navigation marks provided in one embodiment of the present invention; Figure 2 A table of correspondence between instructions and hydrological parameters for an HQ1601 radar flowmeter is provided in accordance with one embodiment of the present invention; Figure 3 A schematic diagram of a radar flow meter deployment example provided by one embodiment of the present invention; Figure 4 as well as Figure 5 A water level information monitoring visualization management diagram provided by an embodiment of the present invention; The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0019] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0020] The embodiment of the present application provides a water level information monitoring method based on the fusion of multiple intelligent sensors of navigation marks. The execution subject of the water level information monitoring method based on the fusion of multiple intelligent sensors of navigation marks includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present application. In other words, the water level information monitoring method based on the fusion of multiple intelligent sensors of navigation marks can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0021] Reference Figure 1 , embodiment 1 of the present invention is: S1: Deploy smart sensors on the buoy hull, collect multi-sensor data and pre-process them to obtain pre-processed multi-sensor data.

[0022] Collect and pre-process multi-sensor data, including: The intelligent sensor includes a temperature sensor, a Beidou positioning module, a liquid level meter, and a radar flow meter. The temperature sensor is used to monitor the water temperature, the Beidou positioning module is used to locate the position of the buoy hull, wherein the position of the buoy hull is the longitude and latitude coordinates, the liquid level meter is used to monitor the water pressure, and the radar flow meter is used to monitor the water depth, the attitude angle of the buoy hull, and the water flow rate and direction. Specifically, the liquid level gauge is an HQ-P1000 pressure level gauge, which uses a high-performance diffused silicon pressure sensor as a measuring element. It measures the static pressure of the liquid, which is proportional to the liquid depth, and converts it into a standard current, voltage or digital signal output through a signal conditioning circuit to achieve accurate measurement of the liquid pressure. The HQ-P1000 pressure level gauge uses the MODBUS communication protocol. The radar flow meter is HQ1601 radar flow meter, which uses MODBUS-RTU instructions based on MODBUS communication protocol to control the radar flow meter to collect information such as water depth, attitude angle of the navigation buoy hull, water flow rate and flow direction, etc. Figure 2 The following table shows the correspondence between commands and hydrological parameters for HQ1601 radar flow meter. It should be noted that the radar flow meter is installed on the inner side of the ship near the river, and its collection surface is facing the direction of the flow velocity. The level gauge on the top of the radar flow meter is kept horizontally installed, and the power supply is provided by the ZB-CT310S navigation beacon telemetry and remote control terminal and the data transmission is carried out through the 485 expansion interface. Figure 3 The radar flow meter deployment example diagram shown in the figure shows that the temperature sensor and liquid level gauge are deployed in submerged areas of the water body, and the Beidou positioning module is deployed on top of the buoy hull. The deployed smart sensors are used to monitor the hydrological information at the location of the buoy during a fixed time period each day to obtain daily multi-sensor data, wherein the multi-sensor data is in the form of a multi-dimensional data sequence, including a water temperature data sequence, a buoy hull position data sequence, a water pressure data sequence, a water depth data sequence, a buoy hull attitude angle data sequence, and a water flow rate and flow direction sequence. As an embodiment of the present application, the fixed time period for monitoring the hydrological information is set to 9:45 to 9:50 every day. The data sequences in the multi-sensor data are filtered and interpolated in sequence, and the last data value of the data sequence is extracted to form the pre-processed multi-sensor data; specifically, the filtering method is a median filtering method based on a sliding window, and the interpolation and completion processing methods include a linear interpolation method, a Lagrange interpolation method, and a cubic spline interpolation method, wherein the Lagrange interpolation method is applicable to the navigation buoy hull position data sequence, the cubic spline interpolation method is applicable to the navigation buoy hull attitude angle data sequence, and the linear interpolation method is applicable to other data sequences except the navigation buoy hull position data sequence and the attitude angle data sequence; The pre-processed multi-sensor data consists of water temperature, navigation buoy hull set position, water pressure, water depth, navigation buoy hull attitude angle, water flow rate and flow direction, wherein water temperature, navigation buoy hull set position, water pressure, water depth, navigation buoy hull attitude angle, water flow rate and flow direction are respectively the last data value in the water temperature data sequence, navigation buoy hull position data sequence, water pressure data sequence, water depth data sequence, navigation buoy hull attitude angle data sequence, water flow rate and flow direction sequence after filtering and interpolation completion processing. The pre-processed multi-sensor data is used as the water depth data, water temperature, flow rate and other data transmitted back every day to judge whether the navigation buoy hull set position meets the navigation standards, and adjust the position of the navigation buoy hull in time to avoid accidental grounding of passing navigable ships due to improper installation of the navigation buoy hull, thereby ensuring smooth navigation of the waterway.

[0023] S2: Using the preprocessed multi-sensor data, the water depth is estimated based on the correction term to obtain the corrected estimated water depth.

[0024] The pre-processed multi-sensor data is used to estimate the water depth based on the correction term, including: Extracting water depth from the pre-processed multi-sensor data , integrating water temperature, attitude angle of the buoy hull and water velocity to generate correction terms, and make correction estimates for the extracted water depth, where the correction terms include flow correction terms and height deviation correction terms; The calculation formula of the flow correction term is: ; in, is the flow correction term based on water temperature and flow velocity, V represents the flow velocity, Indicates the standard water density at the set standard water temperature. Indicates the water temperature, Indicates water temperature It should be noted that the standard water temperature is 4 degrees Celsius, and the standard water density at 4 degrees Celsius is about 10,000 kilograms per cubic meter; Since water temperature changes can significantly affect water density, they indirectly affect the flow velocity distribution of the water body and the stability of the water surface fluctuations measured by the radar flowmeter. For example, at higher temperatures, the viscosity of the water body decreases, turbulence increases, and the amplitude of water surface fluctuations increases, resulting in unstable water depth measurement by the radar flowmeter, requiring flow disturbance correction. Therefore, in the flow correction term proposed in this application, thermal expansion and contraction and viscosity changes are taken into account. When water expands due to heat, the mass per unit volume decreases (i.e., the density decreases), but the overall volume increases. Therefore, under the same water volume, the water depth may increase slightly; The calculation formula of the height measurement deviation correction term is: ; in, It represents the height deviation correction item, h represents the installation height of the radar flowmeter, are the attitude angles of the buoy ship in the pre-processed multi-sensor data. They are the pitch angle and roll angle of the buoy ship respectively; Since the buoy's hull often tilts slightly due to the influence of waves, currents or wind, this tilt will cause the emission angle of the radar flow meter carried on it to change, thereby affecting the vertical accuracy of water depth measurement. It is necessary to correct the vertical accuracy in combination with the attitude angle of the buoy's hull.

[0025] The flow correction term and the height deviation correction term are weighted to generate the correction term , the water depth in the preprocessed multi-sensor data Make a corrected estimate to get the corrected estimated water depth .

[0026] It should be noted that the weighted processing weight of the flow correction term represents the amplifying effect of unit density change on measurement interference. Depending on the radar altitude, detection angle and floating body motion characteristics (the setting range is 0.3-0.8), the setting range of the weighted processing weight of the height deviation correction term is 0.2-0.4.

[0027] S3: Perform position matching analysis on the actual position of the buoy ship in the preprocessed multi-sensor data and the reference coordinates of the buoy ship, calculate the drift distance, and judge whether the actual position of the buoy ship meets the navigation standards in combination with the water depth.

[0028] Perform position matching analysis on the actual position of the buoy ship and the reference coordinates of the buoy ship, and calculate the drift distance, including; Extracting the actual position of the buoy vessel from pre-processed multi-sensor data , and obtain the reference coordinates of the buoy hull , set the elliptical area centered on the reference coordinates of the navigation mark ship as the recommended navigation area, and calculate the actual position of the navigation mark ship Whether it deviates from the deviation coefficient of the recommended navigation area , as the result of position matching analysis, where ,like If it is 0, it means the navigation mark ship is at its current position. Without deviating from the recommended navigation area, if If it is 1, it means the navigation mark ship is in the actual position Departure from the recommended navigation area, where the navigation aid vessel is located Reference coordinates of the buoy and the ship are all longitude and latitude coordinates; specifically, the calculation formula of the deviation coefficient is: ; in, Indicates the ellipse parameters of the ellipse area (the default value of a is 10 meters and b is 5 meters). a represents the semi-major axis of the ellipse area in the precision direction (unit: meter), and b represents the semi-major axis of the ellipse area in the latitude direction (unit: meter). represents a symbolic function, if ,but ,otherwise ; Calculate the actual position of the buoy ship using the Haversine formula Reference coordinates of the buoy and the ship The distance between the two is used as the navigation mark of the ship's actual location. Drift distance.

[0029] Combined with the water depth and the position matching analysis results, determine whether the location of the buoy vessel meets the navigation standards, including: Get the corrected estimated water depth ,like Greater than the preset minimum water depth difference, and the position matches the analysis results , then determine the actual position of the navigation mark ship It does not meet the navigation standards, where H represents the critical safety water level. Specifically, H is set to 10 meters and the preset minimum water depth difference is 5 meters.

[0030] S4: If the current position of the buoy hull does not meet the navigation standards, an optimal adjustment path is generated to drive the buoy hull to the recommended position. The intelligent sensor status information, pre-processed multi-sensor data, corrected estimated water depth, drift distance and buoy hull position information are uploaded to the management platform for visual management.

[0031] If the current position of the buoy vessel does not meet the navigation standards, the optimal adjustment path is generated, including: If the buoy vessel's current position does not meet the navigation standards, a recommended position corresponding to the buoy vessel's current position is selected from the candidate position set, wherein the candidate position set is composed of multiple buoy vessel docking positions that can be used for temporary docking, and the buoy vessel docking position is the latitude and longitude coordinates. The corresponding recommended position selection formula is: ; ; ; ; in, Indicates the actual position of the navigation vessel The corresponding recommended location, represents the set of candidate locations, , p represents any buoy hull docking position in the candidate position set, Indicates the docking position of the navigation mark ship The actual position of the navigation mark vessel The evaluation results of the evaluation index at the k-th position, where , The smaller it is, the closer the buoy is to the docking position of the ship. The better the performance of the evaluation index at the kth position, is the evaluation coefficient of the k-th position evaluation index, set Specifically, set They are 0.4, 0.4, and 0.2 respectively; Represents the set of candidate locations The buoy hull berthing position with the best comprehensive evaluation result of the position evaluation index is selected as the buoy hull setting position Corresponding recommended location ; Indicates the docking position of the navigation mark ship The actual position of the navigation mark vessel The distance cost index represents the docking position of the navigation mark ship The current position of the buoy ship The distance between Indicates the docking position of the navigation mark ship The actual position of the navigation mark vessel The water flow interference index represents the docking position of the navigation mark ship. The current position of the buoy ship The difference between the azimuth and the direction of water flow, Indicates the docking position of the navigation mark ship The actual position of the navigation mark vessel The docking heat index represents the docking position of the navigation mark ship Number of hulls that have docked at the buoy; The waters where the buoy hull is located are divided into multiple continuous grid areas, and each grid area is regarded as a grid. The grid where the buoy hull is located and the grid where the recommended position is located are obtained as the starting point and the target point respectively. The improved A* search algorithm is used to solve the optimal adjustment path between the starting point and the target point, in which the buoy hull is deployed in each divided grid.

[0032] Indicates the use of Haversine formula to calculate the berthing position of the navigation mark ship The current position of the buoy ship The distance between Indicates the maximum hull travel distance (preset to 60km); represents the flow direction of water in the multi-sensor data after preprocessing, Indicates the docking position of the navigation mark ship The current position of the buoy ship The azimuth between Indicates the docking position of the navigation mark ship The number of hulls that have docked at the buoys, Indicates the maximum number of berthing positions for navigational aid vessels (preset to 20).

[0033] The recommended location selection method proposed in this application can intelligently select the optimal location from multiple available candidate points when the buoy's current location does not meet navigation standards, improving the scientific and automated level of buoy deployment. By constructing a weighted cost function based on multi-dimensional evaluation indicators, it comprehensively considers three key factors: distance cost from the current location, water flow interference cost, and docking heat cost. This significantly improves the environmental adaptability and navigation safety of docking location decisions.

[0034] Specifically, the distance cost term is based on the Haversine distance metric, which can accurately evaluate the geographical offset between the actual position of the buoy vessel and the docked position, ensuring that the recommended position will not cause large-scale channel deviation; the water flow direction interference cost constructs a similarity function based on the angle between the main direction of the water flow and the direction of the candidate position, which is particularly effective in turbulent or complex hydrological areas, reducing the drift or rotation of the site caused by the impact of the water flow; the docking heat cost can intelligently avoid high-frequency navigation areas and reduce the deviation of the buoy caused by human interference or collision.

[0035] The improved A* search algorithm is used to solve the optimal adjustment path between the starting point and the target point, including: The improved A* search algorithm integrates the water level information monitored by all navigation buoys, introduces the water depth differences and water flow direction differences between adjacent grids, and optimizes the path cost function in the A* search algorithm to make the water level changes of the optimal adjustment path smoother and safer. The water level information includes the corrected estimated water depth and water flow direction of each grid. The optimization formula for the path cost between adjacent grids is: ; ; ; in, Represents the path cost between the nth and mth grids, where the nth and mth grids are adjacent grids. , Q represents the total number of grids, and ; Represents the distance between the center of the nth grid and the center of the mth grid, represents the difference in water depth between the nth and mth grids, Represents the difference in water flow direction between the nth and mth grids; specifically, the distance The calculation method is Haversine distance metric; is the estimated corrected water depth of the nth grid, represents the corrected estimated water depth of the mth grid, and H represents the critical safety water level; Indicates the azimuth from the center of the nth grid to the center of the mth grid, Indicates the direction of water flow from the center of the nth grid to the center of the mth grid; This path cost function introduces water level difference and water flow interference as environmental constraint variables in the A* algorithm, effectively breaking through the single perspective of the traditional A* algorithm that only uses Euclidean or Manhattan distance as the path cost, and has significant advantages in perception-driven and dynamic adaptation. In traditional methods, path planning often ignores the non-uniformity of the hydrological environment, causing navigation vessels to adjust their positions in high water level fluctuation areas or countercurrent areas, resulting in unstable offset, increased energy consumption, and even navigation interference. This method introduces the water level change term to , significantly improving the ability to avoid flooded areas or shallow areas; the difference in water flow direction This method enhances the natural alignment of the path with the downstream direction, reducing propulsion energy consumption and the frequency of anchor adjustments. Field measurements show that this method reduces the average path adjustment time by 18% compared to the traditional A* algorithm in various typical estuary waters, making it suitable for highly reliable navigation buoy hull positioning in complex hydrological environments.

[0036] Upload the intelligent sensor status information, pre-processed multi-sensor data, corrected estimated water depth, drift distance and buoy hull position information to the management platform for the following Figure 4 as well as Figure 5 The visual management shown in the figure includes the smart sensor status information including the smart sensor power level and operating time.

[0037] Example 2: A water level information monitoring device includes a data acquisition device, a water depth correction module, and a navigation management module: The data acquisition device is used to deploy intelligent sensors on the buoy hull, collect multi-sensor data and pre-process it to obtain pre-processed multi-sensor data; The water depth correction module is used to use the pre-processed multi-sensor data to perform a correction estimate on the water depth based on the correction term to obtain a corrected estimated water depth; The navigation management module is used to perform position matching analysis on the actual position of the buoy ship in the pre-processed multi-sensor data and the reference coordinates of the buoy ship, calculate the drift distance, and judge whether the actual position of the buoy ship meets the navigation standards in combination with the water depth. If the actual position of the buoy ship does not meet the navigation standards, an optimal adjustment path is generated to drive the buoy ship to the recommended position, and the intelligent sensor status information, pre-processed multi-sensor data, corrected estimated water depth, drift distance and buoy ship position information are uploaded to the management platform for visual management.

[0038] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0039] It should be noted that the serial numbers of the above-mentioned embodiments of the present invention are for descriptive purposes only and do not represent the advantages or disadvantages of the embodiments. In addition, the terms "including", "comprising" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "including a ..." does not exclude the presence of other identical elements in the process, device, article or method comprising the element.

[0040] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better embodiment. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present invention.

[0041] The above are only preferred embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A water level information monitoring method based on multi-intelligent sensor fusion of navigation marks, characterized in that: The method comprises: S1: deploy intelligent sensors on the buoy hull, collect multi-sensor data and pre-process them to obtain pre-processed multi-sensor data; S2: Using the pre-processed multi-sensor data, a correction estimate is made on the water depth based on the correction term to obtain a corrected estimated water depth; S3: Perform position matching analysis on the actual position of the buoy vessel in the pre-processed multi-sensor data and the reference coordinates of the buoy vessel, calculate the drift distance, and determine whether the actual position of the buoy vessel meets the navigation standards based on the water depth; S4: If the current position of the buoy hull does not meet the navigation standards, an optimal adjustment path is generated to drive the buoy hull to the recommended position. The smart sensor status information, pre-processed multi-sensor data, corrected estimated water depth, drift distance and buoy hull position information are uploaded to the management platform for visual management. The smart sensor status information includes the smart sensor battery level and operating time.

2. The water level information monitoring method based on multi-intelligent sensor fusion of navigation marks according to claim 1 is characterized in that: Collect and pre-process multi-sensor data, including: The intelligent sensor includes a temperature sensor, a Beidou positioning module, a liquid level meter, and a radar flow meter. The temperature sensor is used to monitor the water temperature, the Beidou positioning module is used to locate the position of the buoy hull, wherein the position of the buoy hull is the longitude and latitude coordinates, the liquid level meter is used to monitor the water pressure, and the radar flow meter is used to monitor the water depth, the attitude angle of the buoy hull, and the water flow rate and direction. The deployed smart sensors are used to monitor the hydrological information of the buoy's hull at a fixed time period every day to obtain daily multi-sensor data. The multi-sensor data is in the form of a multi-dimensional data sequence, including water temperature data sequence, buoy hull position data sequence, water pressure data sequence, water depth data sequence, buoy hull attitude angle data sequence, water flow rate and flow direction sequence; The data sequence in the multi-sensor data is filtered and interpolated in sequence, and the last data value of the data sequence is extracted to form the pre-processed multi-sensor data; The pre-processed multi-sensor data consists of water temperature, buoy hull location, water pressure, water depth, buoy hull attitude angle, water flow rate and flow direction, wherein water temperature, buoy hull location, water pressure, water depth, buoy hull attitude angle, water flow rate and flow direction are, respectively, the last data values ​​in the water temperature data sequence, buoy hull location data sequence, water pressure data sequence, water depth data sequence, buoy hull attitude angle data sequence, water flow rate and flow direction sequence after filtering and interpolation completion processing.

3. The water level information monitoring method based on multi-intelligent sensor fusion of navigation marks as claimed in claim 2 is characterized in that: The pre-processed multi-sensor data is used to estimate the water depth based on the correction term, including: Extracting water depth from the pre-processed multi-sensor data , integrating water temperature, attitude angle of the buoy hull and water velocity to generate correction terms, and make correction estimates for the extracted water depth, where the correction terms include flow correction terms and height deviation correction terms; The calculation formula of the flow correction term is: ； in, is the flow correction term based on water temperature and flow velocity, V represents the flow velocity, Indicates the standard water density at the set standard water temperature. Indicates the water temperature, Indicates water temperature The density of water below; The calculation formula of the height measurement deviation correction term is: ； in, It represents the height deviation correction item, h represents the installation height of the radar flowmeter, are the attitude angles of the buoy ship in the pre-processed multi-sensor data. They are the pitch angle and roll angle of the buoy ship respectively; The flow correction term and the height deviation correction term are weighted to generate the correction term , the water depth in the preprocessed multi-sensor data Make a corrected estimate to get the corrected estimated water depth .

4. The water level information monitoring method based on multi-intelligent sensor fusion of navigation marks according to claim 1 is characterized in that: Perform position matching analysis on the actual position of the buoy ship and the reference coordinates of the buoy ship, and calculate the drift distance, including; Extracting the actual position of the buoy vessel from pre-processed multi-sensor data , and obtain the reference coordinates of the buoy hull , set the elliptical area centered on the reference coordinates of the navigation mark ship as the recommended navigation area, and calculate the actual position of the navigation mark ship Whether it deviates from the deviation coefficient of the recommended navigation area , as the result of position matching analysis, where ,like If it is 0, it means the navigation mark ship is at its current position. If the recommended navigation area is not deviated, If it is 1, it means the navigation mark ship is in the actual position. Departure from the recommended navigation area, where the navigation aid vessel is located Reference coordinates of the buoy and the ship All are latitude and longitude coordinates; Calculate the actual position of the buoy ship using the Haversine formula Reference coordinates of the buoy and the ship The distance between the two is used as the navigation mark of the ship's actual location. Drift distance.

5. The water level information monitoring method based on multi-intelligent sensor fusion of navigation marks as claimed in claim 4 is characterized in that: Combined with the water depth and the position matching analysis results, determine whether the buoy ship's location meets the navigation standards, including: Get the corrected estimated water depth ,like Greater than the preset minimum water depth difference, and the position matches the analysis results , then determine the actual position of the navigation mark ship It does not meet the navigation standards, where H represents the critical safety water level.

6. The water level information monitoring method based on multi-intelligent sensor fusion of navigation marks according to claim 5 is characterized in that: If the current position of the buoy vessel does not meet the navigation standards, the optimal adjustment path is generated, including: If the buoy vessel's current position does not meet the navigation standards, a recommended position corresponding to the buoy vessel's current position is selected from the candidate position set, wherein the candidate position set is composed of multiple buoy vessel docking positions that can be used for temporary docking, and the buoy vessel docking position is the latitude and longitude coordinates. The corresponding recommended position selection formula is: ； in, Indicates the actual position of the navigation mark vessel The corresponding recommended location, represents the set of candidate locations, , p represents any buoy hull docking position in the candidate position set, Indicates the docking position of the navigation mark ship The actual position of the buoy ship The evaluation results of the evaluation index at the k-th position, where , The smaller it is, the closer the buoy is to the docking position of the ship. The better the performance of the evaluation index at the kth position, is the evaluation coefficient of the k-th position evaluation index, set ; Represents the set of candidate locations The buoy hull berthing position with the best comprehensive evaluation result of the position evaluation index is selected as the buoy hull setting position Corresponding recommended location ; Indicates the docking position of the navigation mark ship The actual position of the buoy ship The distance cost index represents the docking position of the navigation mark ship The current position of the buoy ship The distance between Indicates the docking position of the navigation mark ship The actual position of the buoy ship The water flow interference index represents the docking position of the navigation mark ship. The current position of the buoy ship The difference between the azimuth and the direction of water flow, Indicates the docking position of the navigation mark ship The actual position of the buoy ship The docking heat index represents the docking position of the navigation mark ship Number of hulls that have docked at the buoy; The waters where the buoy hull is located are divided into multiple continuous grid areas, and each grid area is regarded as a grid. The grid where the buoy hull is located and the grid where the recommended position is located are obtained as the starting point and the target point respectively. The improved A* search algorithm is used to solve the optimal adjustment path between the starting point and the target point, in which the buoy hull is deployed in each divided grid.

7. The water level information monitoring method based on multi-intelligent sensor fusion of navigation marks according to claim 6 is characterized in that: The improved A* search algorithm is used to solve the optimal adjustment path between the starting point and the target point, including: The improved A* search algorithm integrates the water level information monitored by all navigational buoys, introduces the differences in water depth and water flow direction between adjacent grids, and optimizes the path cost function in the A* search algorithm, making the water level changes of the optimal adjustment path smoother and safer. The water level information includes the corrected estimated water depth and water flow direction of each grid.

8. A water level information monitoring device, characterized in that: The water level information monitoring device includes a data acquisition device, a water depth correction module and a navigation management module: The data acquisition device is used to deploy intelligent sensors on the buoy hull, collect multi-sensor data and pre-process it to obtain pre-processed multi-sensor data; The water depth correction module is used to use the pre-processed multi-sensor data to perform a correction estimate on the water depth based on the correction term to obtain a corrected estimated water depth; The navigation management module is used to perform position matching analysis on the actual position of the buoy hull in the pre-processed multi-sensor data and the reference coordinates of the buoy hull, calculate the drift distance, and judge whether the actual position of the buoy hull meets the navigation standards in combination with the water depth. If the actual position of the buoy hull does not meet the navigation standards, an optimal adjustment path is generated to drive the buoy hull to the recommended position, and the intelligent sensor status information, pre-processed multi-sensor data, corrected estimated water depth, drift distance and buoy hull position information are uploaded to the management platform for visual management; To realize the water level information monitoring method based on multi-intelligent sensor fusion of navigation marks as described in any one of claims 1-7.

Images