Water area intelligent mapping system based on edge computing

Abstract

The application relates to the technical field of water area surveying and mapping, and discloses an intelligent water area surveying and mapping system based on edge computing, which comprises an AI environment sensing module, a flight control module, a winch module, an edge computing module and a cloud service platform. The flight control module identifies the state of a depth sounding weight based on the change of a measuring rope tension and triggers data collection, the AI environment sensing module collects environment data and controls the total delay, the winch module guides the active correction of the posture of the unmanned aerial vehicle by calculating the horizontal offset, so that the inclination is constrained within a threshold range, the edge computing module subtracts the effective vertical depth from the RTK elevation of the unmanned aerial vehicle and the total error of the system, so that the real-time solution of the underwater elevation is realized, and the cloud service platform is in communication connection with the edge computing module and is used for receiving the solution results. The application realizes the real-time surveying and mapping of the underwater terrain, and effectively solves the problems of high risk, low precision and serious lag of the traditional surveying and mapping results.

Description

Technical Field

[0001] This invention relates to the field of water surveying technology, specifically to an intelligent water surveying system based on edge computing. Background Technology

[0002] Underwater topographic mapping is a fundamental task in fields such as water conservancy projects, waterway management, environmental protection, and emergency rescue. Traditional underwater topographic mapping mainly uses manual shipboard bathymetry equipment or unmanned surface vessels equipped with bathymetry instruments.

[0003] However, existing technologies have the following obvious shortcomings:

[0004] First, manual surveying is risky and inefficient. Traditional methods require surveyors to travel by boat to the target waters, where personnel safety is difficult to guarantee in complex waters such as rapids, shoals, and reefs. Furthermore, the efficiency of the operation is constrained by weather and hydrological conditions, making it difficult to achieve large-scale and rapid coverage.

[0005] Second, unmanned surface vessel (USV) mapping faces the challenge of being unable to measure or accurately measure. Existing USV mapping systems are limited by the ship's draft, making it difficult to enter extremely shallow waters; in areas with rapid currents or dense aquatic plants, maintaining the ship's position is difficult, resulting in poor reliability of measurement data and an inability to obtain accurate underwater elevation information.

[0006] Third, the updating of surveying and mapping results is seriously lagging behind. The traditional surveying and mapping model follows a serial process of field data collection, data export, indoor post-processing, and result output. From data acquisition to final result delivery, it often takes several hours or even days, which is completely unable to meet the application scenarios with extremely high requirements for the timeliness of results, such as emergency surveying and mapping during the flood season and real-time monitoring of engineering projects. Summary of the Invention

[0007] To address the shortcomings of existing technologies, this invention provides an intelligent water mapping system based on edge computing. It features edge computing and multi-sensor fusion, enabling real-time mapping of underwater topography that can be obtained instantly. This system effectively solves the problems of high risk, low accuracy, and severe delays in results associated with traditional mapping, thus resolving the aforementioned technical issues.

[0008] To achieve the above objectives, the present invention provides the following technical solution: an intelligent water mapping system based on edge computing, comprising an AI environmental perception module, a flight control module, a winch module, an edge computing module, and a cloud service platform;

[0009] The flight control module identifies the current state of the sounding hammer based on the rope tension and controls whether the AI ​​environment perception module starts collecting data.

[0010] The AI ​​environment perception module includes an environment acquisition unit and a time delay constraint unit. The environment acquisition unit is used to collect environmental data of the environment where the sounding hammer is located, and the time delay constraint unit is used to control the total delay from the start of data acquisition to the transmission of the final result to the cloud service platform.

[0011] The winch module is connected to the AI ​​environmental perception module via a measuring rope for correcting the rope's posture.

[0012] The edge computing module is used to calculate the underwater elevation directly beneath the drone;

[0013] The cloud service platform is communicatively connected to the edge computing module to receive the calculated underwater elevation.

[0014] As a preferred technical solution of the present invention, the flight control module identifies the current state of the sounding hammer based on the rope tension, specifically: when At that time, and Within the set range, the sounding hammer is determined to be in a suspended, lowered state at this time; when ,and If the force is less than the bottoming force threshold and the duration is greater than the bottoming time threshold, the sounding hammer is considered to have made its first bottoming contact. And if the duration is greater than the over-release time threshold, the sounding hammer state is determined to be rope accumulation; when If the duration is greater than the bottoming time threshold, the sounding hammer is considered to be in a bottoming state; when When the depth sounding hammer's condition is below the escape force threshold, it is considered successfully freed. Indicates the tension of the measuring rope. Indicates the rate of change of the tension in the measuring rope. It is a time variable; This indicates the change in the tension of the measuring rope at the current moment compared to the previous moment;

[0015] The control of whether the AI ​​environment perception module starts collecting data is as follows: when the flight control module recognizes that the sounding hammer has touched the bottom for the first time, it sends a data collection start signal to the AI ​​environment perception module, and the module starts collecting environmental data.

[0016] As a preferred embodiment of the present invention, the environmental acquisition unit includes a depth sensor and an attitude sensor, used to sense the underwater depth measurement data of the sounding hammer and the spatial attitude of the sounding rope.

[0017] As a preferred embodiment of the present invention, the constraint expression for the total delay is as follows:

[0018] ;

[0019] in, This represents the total latency from data collection to the final results being available in the cloud; This indicates the time taken for the edge computing module to complete the elevation calculation; This indicates the time taken to transmit the calculated underwater elevation to the cloud service platform via the link. Indicates the maximum allowed delay.

[0020] As a preferred embodiment of the present invention, the attitude correction of the measuring rope specifically involves: based on the angle between the measuring rope and the vertical direction... To determine whether to perform posture correction for rope measurement, when... >Maximum permissible tilt angle At that time, the rope posture was corrected.

[0021] As a preferred embodiment of the present invention, the correction of the measuring rope attitude includes the following steps:

[0022] Step A1: Based on the included angle Determine the horizontal offset distance ;

[0023] Step A2: Calculate the amount of horizontal redundant offset that needs to be eliminated. Its expression is as follows:

[0024] ;

[0025] in, This indicates the amount of redundant horizontal offset that needs to be eliminated; This indicates the horizontal offset distance between the drone's hovering point and the measuring plumb line. Indicates the length of the measuring rope; Indicates the maximum permissible tilt angle; It is a sine function.

[0026] As a preferred embodiment of the present invention, the horizontal offset distance in step A1 The expression is as follows:

[0027] ;

[0028] in, This indicates the horizontal offset distance between the drone's hovering point and the measuring plumb line. Indicates the length of the measuring rope; Indicates the angle between the measuring rope and the vertical direction; It is a sine function.

[0029] As a preferred embodiment of the present invention, the underwater elevation directly beneath the UAV is expressed as follows:

[0030] ;

[0031] in, Indicates the underwater elevation directly beneath the drone; Indicates the PTK elevation of the drone; Indicates the effective vertical depth after compensation; This represents the total error.

[0032] As a preferred technical solution of the present invention, the effective vertical depth The expression is as follows:

[0033] ;

[0034] in, Indicates the length of the measuring rope; Indicates the angle between the measuring rope and the vertical direction; It is a cosine function.

[0035] As a preferred technical solution of the present invention, the total error The expression is as follows:

[0036] ;

[0037] in, This indicates the vertical offset error of the RTK antenna phase center relative to the center of gravity of the UAV; This indicates the encoder counting error of the winch; This indicates environmental data acquisition error; Indicates other errors.

[0038] Compared with existing technologies, this invention provides an intelligent water mapping system based on edge computing, which has the following advantages:

[0039] 1. This invention identifies five states of the sounding hammer based on the change in rope tension using a flight control module: suspension and descent, first contact with the bottom, rope accumulation, snagging, and successful escape. The first contact with the bottom is used as a trigger signal to control the AI ​​environmental perception module to start collecting data, thus achieving full automation of measurement triggering. This completely eliminates manual judgment and operation, fundamentally solving the problems of high risk and low efficiency in traditional manual measurement.

[0040] 2. This invention, through the winch module, calculates the excess horizontal offset when the measuring rope inclination angle exceeds the limit and guides the UAV to actively move towards the sounding hammer to reduce the inclination angle. At the physical level, it constrains the measuring rope to an approximately vertical state, fundamentally reducing nonlinear errors. Simultaneously, through the edge computing module, the effective vertical depth and the total system error are subtracted from the UAV's RTK elevation. The total system error covers antenna phase center offset, winch counting error, environmental temperature influence, and other random errors. Multi-source errors are quantified and compensated item by item, realizing real-time calculation of underwater elevation at the centimeter level. This effectively solves the industry problem of inaccurate or unmeasurable measurements in complex waters. Attached Figure Description

[0041] Figure 1 This is a schematic diagram of the system framework of the present invention. Detailed Implementation

[0042] 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.

[0043] Please see Figure 1 The intelligent water mapping system based on edge computing includes: an AI environmental perception module, a flight control module, a winch module, an edge computing module, and a cloud service platform;

[0044] The flight control module identifies the current state of the sounding hammer based on the tension of the measuring rope and controls whether the AI ​​environment perception module starts collecting data.

[0045] The flight control module identifies the current state of the sounding hammer based on the rope tension, specifically: when At that time, and Within the set range Inside, at this point, the sounding hammer is determined to be in a suspended, lowered state; when ,and If the force is less than the bottoming force threshold of 20N and the duration is greater than the bottoming time threshold of 2S, the sounding hammer is considered to have made its first bottoming contact. And if the duration is greater than the over-release time threshold of 3 seconds, the sounding hammer is determined to be in a state of rope accumulation; when =1.8G, and the duration is greater than the bottoming time threshold of 3 seconds, at which point the sounding hammer is determined to be in a bottoming state; when When the escape force threshold is less than 40N, the sounding hammer is considered to have successfully escaped. Indicates the tension of the measuring rope. Indicates the rate of change of the tension in the measuring rope. It is a time variable; This indicates the change in the tension of the measuring rope at the current moment compared to the previous moment;

[0046] The control of whether the AI ​​environmental perception module starts collecting data is as follows: when the flight control module recognizes that the sounding hammer has touched the bottom for the first time, it sends a data collection start signal to the AI ​​environmental perception module, and the module starts collecting environmental data.

[0047] The AI ​​environment perception module includes an environment acquisition unit and a latency constraint unit. The environment acquisition unit is used to collect environmental data of the environment where the sounding hammer is located, and the latency constraint unit is used to control the total latency from the start of data acquisition to the final result being transmitted to the cloud service platform.

[0048] The environmental acquisition unit includes a depth sensor and an attitude sensor, used to sense the underwater depth measurement data of the sounding hammer and the spatial attitude of the sounding rope.

[0049] The constraint expression for the total delay is as follows:

[0050] ;

[0051] in, This represents the total latency from data collection to the final results being available in the cloud; This indicates the time taken for the edge computing module to complete the elevation calculation; This indicates the time taken to transmit the calculated underwater elevation to the cloud service platform via the link. This indicates the maximum allowable delay; this formula is used to control the time from data acquisition to underwater elevation calculation and uploading to the cloud service platform, ensuring data transmission efficiency.

[0052] The winch module is connected to the AI ​​environmental perception module via the measuring rope for correcting the rope's posture.

[0053] The attitude correction of the measuring rope is specifically based on the angle between the measuring rope and the vertical direction. To determine whether to perform posture correction for rope measurement, when... >Maximum permissible tilt angle At that time, the rope posture was corrected.

[0054] Correcting the rope posture includes the following steps:

[0055] Step A1: Based on the included angle Determine the horizontal offset distance Its expression is as follows:

[0056] ;

[0057] in, This indicates the horizontal offset distance between the drone's hovering point and the measuring plumb line. Indicates the length of the measuring rope; Indicates the angle between the measuring rope and the vertical direction; It is a sine function;

[0058] Step A2: Calculate the amount of horizontal redundant offset that needs to be eliminated. Its expression is as follows:

[0059] ;

[0060] in, This indicates the amount of redundant horizontal offset that needs to be eliminated; This indicates the horizontal offset distance between the drone's hovering point and the measuring plumb line. Indicates the length of the measuring rope; Indicates the maximum permissible tilt angle; It is a sine function;

[0061] Through the above series of steps, the inclination angle of the measuring rope is actively constrained within the threshold range at the physical level, which reduces the horizontal component force from the source. This allows the subsequent mathematical model for attitude compensation to run under a small angle condition that is close to vertical, which greatly reduces nonlinear error and significantly improves the reliability of underwater elevation calculation and the ability to maintain centimeter-level accuracy.

[0062] The edge computing module is used to calculate the underwater elevation directly beneath the drone, and its expression is as follows:

[0063] ;

[0064] in, Indicates the underwater elevation directly beneath the drone; Indicates the PTK elevation of the drone; Indicates the effective vertical depth after compensation; The total error is represented by the initial elevation of the sounding hammer's bottom point after subtracting the vertical depth of the measuring rope from the known aerial reference of the UAV. Then, the error is eliminated one by one to obtain the final elevation.

[0065] Effective vertical depth The expression is as follows:

[0066] ;

[0067] in, Indicates the length of the measuring rope; Indicates the angle between the measuring rope and the vertical direction; It is a cosine function;

[0068] Due to the impact of water flow and flight attitude, the measuring rope cannot maintain a perfectly vertical state during actual operation and forms an angle with the vertical direction. ,pass Projecting the inclined measuring rope onto the vertical direction eliminates depth errors introduced by attitude.

[0069] Total error The expression is as follows:

[0070] ;

[0071] in, This indicates the vertical offset error of the RTK antenna phase center relative to the center of gravity of the UAV; This indicates the encoder counting error of the winch; This indicates environmental data acquisition error; Indicates other errors;

[0072] The cloud service platform communicates with the edge computing module to receive the calculated underwater elevation.

[0073] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. An intelligent water mapping system based on edge computing, characterized in that: It includes an AI environmental perception module, a flight control module, a winch module, an edge computing module, and a cloud service platform; The flight control module identifies the current state of the sounding hammer based on the rope tension and controls whether the AI ​​environment perception module starts collecting data. The AI ​​environment perception module includes an environment acquisition unit and a time delay constraint unit. The environment acquisition unit is used to collect environmental data of the environment where the sounding hammer is located, and the time delay constraint unit is used to control the total delay from the start of data acquisition to the transmission of the final result to the cloud service platform. The winch module is connected to the AI ​​environmental perception module via a measuring rope for correcting the rope's posture. The edge computing module is used to calculate the underwater elevation directly beneath the drone; The cloud service platform is communicatively connected to the edge computing module to receive the calculated underwater elevation.

2. The intelligent water mapping system based on edge computing according to claim 1, characterized in that: The flight control module identifies the current state of the sounding hammer based on the rope tension, specifically: when At that time, and Within the set range, the sounding hammer is determined to be in a suspended, lowered state at this time; when ,and If the force is less than the bottoming force threshold and the duration is greater than the bottoming time threshold, the sounding hammer is considered to have made its first bottoming contact. And if the duration is greater than the over-release time threshold, the sounding hammer state is determined to be rope accumulation; when If the duration is greater than the bottoming time threshold, the sounding hammer is considered to be in a bottoming state; when When the depth sounding hammer's condition is below the escape force threshold, it is considered successfully freed. Indicates the tension of the measuring rope. Indicates the rate of change of the tension in the measuring rope. It is a time variable; This indicates the change in the tension of the measuring rope at the current moment compared to the previous moment; The control of whether the AI ​​environment perception module starts collecting data is as follows: when the flight control module recognizes that the sounding hammer has touched the bottom for the first time, it sends a data collection start signal to the AI ​​environment perception module, and the module starts collecting environmental data.

3. The intelligent water mapping system based on edge computing according to claim 1, characterized in that: The environmental acquisition unit includes a depth sensor and an attitude sensor, used to sense the underwater depth measurement data of the sounding hammer and the spatial attitude of the sounding rope.

4. The intelligent water mapping system based on edge computing according to claim 1, characterized in that: The constraint expression for the total delay is as follows: ； in, This represents the total latency from data collection to the final results being available in the cloud; This indicates the time taken for the edge computing module to complete the elevation calculation; This indicates the time taken to transmit the calculated underwater elevation to the cloud service platform via the link. Indicates the maximum allowed delay.

5. The intelligent water mapping system based on edge computing according to claim 1, characterized in that: The attitude correction of the measuring rope specifically involves: based on the angle between the measuring rope and the vertical direction. To determine whether to perform posture correction for rope measurement, when... >Maximum permissible tilt angle At that time, the rope posture was corrected.

6. The intelligent water mapping system based on edge computing according to claim 5, characterized in that: The rope posture is corrected, including the following steps: Step A1: Based on the included angle Determine the horizontal offset distance ; Step A2: Calculate the amount of horizontal redundant offset that needs to be eliminated. Its expression is as follows: ； in, This indicates the amount of redundant horizontal offset that needs to be eliminated; This indicates the horizontal offset distance between the drone's hovering point and the measuring plumb line. Indicates the length of the measuring rope; Indicates the maximum permissible tilt angle; It is a sine function.

7. The intelligent water mapping system based on edge computing according to claim 6, characterized in that: The horizontal offset distance in step A1 The expression is as follows: ； in, This indicates the horizontal offset distance between the drone's hovering point and the measuring plumb line. Indicates the length of the measuring rope; Indicates the angle between the measuring rope and the vertical direction; It is a sine function.

8. The intelligent water mapping system based on edge computing according to claim 1, characterized in that: The expression for the underwater elevation directly beneath the drone is as follows: ； in, Indicates the underwater elevation directly beneath the drone; Indicates the PTK elevation of the drone; Indicates the effective vertical depth after compensation; This represents the total error.

9. The intelligent water mapping system based on edge computing according to claim 8, characterized in that: The effective vertical depth The expression is as follows: ； in, Indicates the length of the measuring rope; Indicates the angle between the measuring rope and the vertical direction; It is a cosine function.

10. The intelligent water mapping system based on edge computing according to claim 8, characterized in that: The total error The expression is as follows: ； in, This indicates the vertical offset error of the RTK antenna phase center relative to the center of gravity of the UAV; This indicates the encoder counting error of the winch; This indicates environmental data acquisition error; Indicates other errors.

Images