Method for determining river flow field distribution and drone equipment

Abstract

The present invention relates to the technical field of river section flow field distribution, and specifically to a method for determining river section flow field distribution and an unmanned aerial vehicle (UAV) device. The method includes obtaining the location information of the UAV device based on a positioning component; obtaining the continuous wave signal sent by the ultrasonic radar component and the reflected wave signal corresponding to the received continuous wave signal; determining the surface flow velocity at a preset position in the preset river section corresponding to the location information based on the continuous wave signal and the reflected wave signal; obtaining the laser radar signal emitted by the laser radar component and the target reflected radar signal corresponding to the received laser radar signal; determining the calculated riverbed topography at the preset position in the preset river section corresponding to the location information based on the laser radar signal and the target reflected radar signal; and determining the three-dimensional flow field distribution corresponding to the preset river section based on the surface flow velocity and the calculated riverbed topography corresponding to each preset position. The method has low labor costs and high efficiency, and does not require manual measurement of data such as water flow velocity and water level corresponding to each position in the preset river section.

Description

Technical Field

[0001] The present invention relates to the technical field of river section flow field distribution, and in particular to a method for determining river section flow field distribution and unmanned aerial vehicle (UAV) equipment. Background Art

[0002] With population growth and economic development, the demand for water resources continues to increase, but this also faces challenges such as water shortages, water pollution, and ecological degradation. Therefore, in-depth research on the flow field distribution of pre-defined river sections is of great significance for addressing the challenges of water resource management and environmental protection.

[0003] In the prior art, measurement points are usually set up in a preset river section, and field measurements are performed using instruments such as flow meters and water level meters to obtain data such as water flow velocity and water level, thereby obtaining the three-dimensional flow field distribution corresponding to the preset river section.

[0004] Therefore, the above method has high labor cost and low efficiency. Summary of the Invention

[0005] In view of this, the present invention provides a method for determining the flow field distribution of a river section and an unmanned aerial vehicle device to solve the problem of how to improve the efficiency of obtaining the three-dimensional flow field distribution corresponding to a preset river section.

[0006] In a first aspect, the present invention provides a method for determining the flow field distribution of a river section, which is applied to a control component in an unmanned aerial vehicle (UAV) device. The UAV device also includes a positioning component, an ultrasonic radar component, and a laser radar component. The control component is communicatively connected with the positioning component, the ultrasonic radar component, and the laser radar component. The method includes:

[0007] Obtain the location information of the drone device based on the positioning component;

[0008] Obtaining the continuous wave signal sent by the ultrasonic radar component and the reflected wave signal corresponding to the received continuous wave signal;

[0009] Determining a surface flow velocity at a preset location in a preset river section corresponding to the location information based on the continuous wave signal and the reflected wave signal;

[0010] Obtain the laser radar signal emitted by the laser radar component and the target reflected radar signal corresponding to the received laser radar signal;

[0011] Determine, based on the laser radar signal and the target reflected radar signal, a calculated riverbed topography at a preset location in a preset river section corresponding to the location information;

[0012] Based on the surface flow velocity corresponding to each preset position and the calculated riverbed topography, the three-dimensional flow field distribution corresponding to the preset river section is determined.

[0013] The method for determining the flow field distribution in a river section provided by the embodiments of the present application uses a positioning component to obtain the location information of a drone device, thereby ensuring the accuracy of the acquired location information. The method also includes obtaining a continuous wave signal transmitted by an ultrasonic radar component and a corresponding reflected wave signal from the received continuous wave signal. Based on the continuous wave signal and the reflected wave signal, the method determines the surface flow velocity at a preset location in the preset river section corresponding to the location information, thereby ensuring the accuracy of the surface flow velocity at the preset location in the preset river section corresponding to the determined location information. The method also includes obtaining a laser radar signal transmitted by a laser radar component and a corresponding target reflected radar signal from the received laser radar signal. Based on the laser radar signal and the target reflected radar signal, the method determines the calculated riverbed topography at the preset location in the preset river section corresponding to the location information, thereby ensuring the accuracy of the calculated riverbed topography at the preset location in the preset river section corresponding to the determined location information. Based on the surface flow velocity and the calculated riverbed topography corresponding to each preset location, the method determines the three-dimensional flow field distribution corresponding to the preset river section, thereby ensuring the accuracy of the determined three-dimensional flow field distribution corresponding to the preset river section. This method is low in labor cost and highly efficient, as it does not require manual measurement of water velocity, water level, and other data corresponding to each location in the preset river section.

[0014] In an optional embodiment, the ultrasonic radar assembly includes multiple sub-radar units, the continuous wave signal is a sub-continuous wave signal corresponding to the multiple sub-radar units, and the reflected wave signal is a sub-reflected wave signal corresponding to the multiple sub-radar units; the preset position includes a sub-preset position corresponding to each sub-radar unit and an overlapping area corresponding to each sub-preset position; the surface flow velocity includes a first sub-surface flow velocity corresponding to each sub-preset position and a second sub-surface flow velocity corresponding to each overlapping area; and determining the surface flow velocity at a preset position in a preset river section corresponding to the position information based on the continuous wave signal and the reflected wave signal includes:

[0015] Calculating a first sub-surface flow velocity at a sub-preset position corresponding to each sub-radar unit based on the sub-continuous wave signal and the sub-reflected wave signal corresponding to each sub-radar unit;

[0016] Get the overlapping area corresponding to each sub-preset position;

[0017] Obtain radar signal-to-noise ratio values ​​of each target sub-radar unit corresponding to the overlapping area;

[0018] Determine the weight information corresponding to each target sub-radar unit according to the radar signal-to-noise ratio value of each target sub-radar unit;

[0019] The weight information corresponding to each target sub-radar unit is multiplied by the first sub-surface flow velocity corresponding to each target sub-radar unit, and then the sum is added and averaged to obtain the second sub-surface flow velocity corresponding to the overlapping area.

[0020] The method for determining the flow field distribution of a river section provided in an embodiment of the present application calculates the first sub-surface flow velocity of the sub-preset position corresponding to each sub-radar unit based on the sub-continuous wave signal and sub-reflected wave signal corresponding to each sub-radar unit, thereby ensuring the accuracy of the calculated first sub-surface flow velocity of each sub-preset position. The overlapping area corresponding to each sub-preset position is obtained; the radar signal-to-noise ratio value of each target sub-radar unit corresponding to the overlapping area is obtained, thereby ensuring the accuracy of the weight information corresponding to each sub-radar unit. The weight information corresponding to each target sub-radar unit is multiplied by the first sub-surface flow velocity corresponding to each target sub-radar unit, and then the weight information is added and averaged to obtain the second sub-surface flow velocity corresponding to the overlapping area, thereby ensuring the accuracy of the obtained second sub-surface flow velocity corresponding to the overlapping area.

[0021] In an optional embodiment, calculating the first sub-surface flow velocity at the sub-preset position corresponding to each sub-radar unit based on the sub-continuous wave signal and the sub-reflected wave signal corresponding to each sub-radar unit includes:

[0022] Calculate the phase difference between the sub-continuous wave signal and the sub-reflected wave signal corresponding to each sub-radar unit;

[0023] The first sub-surface flow velocity at the sub-preset position corresponding to each sub-radar unit is determined according to the phase difference.

[0024] The method for determining the flow field distribution of a river section provided in an embodiment of the present application calculates the phase difference between the sub-continuous wave signal and the sub-reflected wave signal corresponding to each sub-radar unit, ensuring the accuracy of the calculated phase difference between the sub-continuous wave signal and the sub-reflected wave signal corresponding to each sub-radar unit. Based on the phase difference, the first sub-surface flow velocity at the sub-preset location corresponding to each sub-radar unit is determined, ensuring the accuracy of the determined first sub-surface flow velocity at the sub-preset location corresponding to each sub-radar unit.

[0025] In an optional embodiment, obtaining a laser radar signal emitted by a laser radar component and receiving a target reflected radar signal corresponding to the laser radar signal includes:

[0026] Acquire the laser radar signal emitted by the laser radar component;

[0027] receiving at least one backup reflected radar signal corresponding to the laser radar signal;

[0028] Identify each backup reflected radar signal;

[0029] If the backup reflected radar signal meets a preset condition, the backup reflected radar signal is determined as the target reflected radar signal.

[0030] The method for determining the flow field distribution of a river section provided in an embodiment of the present application obtains a laser radar signal emitted by a laser radar component; receives at least one backup reflection radar signal corresponding to the laser radar signal; identifies each backup reflection radar signal, and if the backup reflection radar signal meets a preset condition, determines the backup reflection radar signal as a target reflection radar signal, thereby filtering each backup reflection radar signal and ensuring the accuracy of the determined target reflection radar signal.

[0031] In an optional embodiment, the preset conditions include a preset light intensity condition and a preset time condition; if the backup reflected radar signal meets the preset conditions, determining the backup reflected radar signal as the target reflected radar signal includes:

[0032] Identify the laser radar signal, determine a first light intensity corresponding to the laser radar signal, and determine a transmission time corresponding to the laser radar signal;

[0033] Determining a preset light intensity threshold according to the first light intensity, and determining a preset receiving time threshold according to the emission time;

[0034] Obtaining the second light intensity and reception time corresponding to each backup reflected radar signal;

[0035] For each backup reflected radar signal, comparing the second light intensity with a preset light intensity threshold, and comparing the reception time with a preset reception time threshold;

[0036] If the second light intensity is less than the preset light intensity threshold and the receiving time is later than the preset receiving time threshold, the backup reflected radar signal is determined as the target reflected radar signal.

[0037] The method for determining the flow field distribution of a river section provided in the embodiment of the present application identifies the laser radar signal, determines the first light intensity corresponding to the laser radar signal, and determines the emission time corresponding to the laser radar signal, thereby ensuring the accuracy of the determined first light intensity and emission time. The preset light intensity threshold is determined based on the first light intensity, and the preset receiving time threshold is determined based on the emission time, thereby ensuring the accuracy of the determined preset light intensity threshold and the preset receiving time threshold. The second light intensity and receiving time corresponding to each standby reflection radar signal are obtained; for each standby reflection radar signal, the second light intensity is compared with the preset light intensity threshold, and the receiving time is compared with the preset receiving time threshold, thereby ensuring the accuracy of the comparison result obtained. If the second light intensity is less than the preset light intensity threshold, and the receiving time is later than the preset receiving time threshold, the standby reflection radar signal is determined as the target reflection radar signal, thereby ensuring the accuracy of the determined target reflection radar signal.

[0038] In an optional embodiment, after determining the calculated riverbed topography at a preset location in a preset river section corresponding to the location information based on the laser radar signal and the target reflected radar signal, the method further includes:

[0039] Obtain the actual measured riverbed topography corresponding to multiple reference points in a preset river section;

[0040] Calculating a first similarity between the calculated riverbed topography corresponding to each preset position and the real measured riverbed topography corresponding to each reference point;

[0041] Based on each first similarity, at least one target real measured riverbed topography matching each calculated riverbed topography is calculated;

[0042] For each real measured riverbed topography, calculating a second similarity between the real measured riverbed topography and each target calculated riverbed topography;

[0043] Based on the second similarity, the position information and attitude information of the UAV device are adjusted to ensure the accuracy of each calculated riverbed terrain.

[0044] The method for determining the flow field distribution of a river section provided in an embodiment of the present application obtains the real measured riverbed topography corresponding to multiple reference points in a preset river section; calculates the first similarity between the calculated riverbed topography corresponding to each preset position and the real measured riverbed topography corresponding to each reference point, thereby ensuring the accuracy of each calculated first similarity. Based on each first similarity, at least one target real measured riverbed topography matching each calculated riverbed topography is calculated, thereby ensuring the accuracy of the determined at least one target real measured riverbed topography matching each calculated riverbed topography. For each real measured riverbed topography, a second similarity between the real measured riverbed topography and each target calculated riverbed topography is calculated, thereby ensuring the accuracy of each calculated second similarity. Based on the second similarity, the position information and attitude information of the drone device are adjusted, thereby ensuring the accuracy of the position information and attitude information of the drone device, thereby avoiding the inaccuracy of the calculated calculated riverbed topography due to the inaccuracy of the position information and attitude information of the drone device.

[0045] In an optional embodiment, calculating and obtaining at least one target real measured riverbed topography that matches each calculated riverbed topography based on the first similarity includes:

[0046] Randomly initialize the current position and current velocity of each initial particle;

[0047] Determining a first fitness value of each initial particle based on each first similarity; the first fitness value represents the degree of matching between the initial particle and each actual measured riverbed topography;

[0048] Determine the individual optimal position and the global optimal position corresponding to each initial particle according to the first fitness value;

[0049] According to the current position and current velocity corresponding to each initial particle, the individual optimal position and the global optimal position, each initial particle is updated to generate each updated particle;

[0050] Calculate the second fitness value corresponding to each updated particle;

[0051] At least one target calculated riverbed topography matching each actual measured riverbed topography is determined according to the second fitness value corresponding to each updated particle.

[0052] The method for determining the flow field distribution of a river section provided in an embodiment of the present application randomly initializes the current position and current velocity of each initial particle; based on each first similarity, determines the first fitness value of each initial particle, thereby ensuring the accuracy of the first fitness value of each determined initial particle. Based on the first fitness value, determines the individual optimal position and the global optimal position corresponding to each initial particle, thereby ensuring the accuracy of the individual optimal position and the global optimal position corresponding to each initial particle. Based on the current position and current velocity, the individual optimal position and the global optimal position corresponding to each initial particle, updates each initial particle to generate each updated particle, thereby ensuring the accuracy of each generated updated particle. Calculates the second fitness value corresponding to each updated particle, thereby ensuring the accuracy of the second fitness value corresponding to the calculated updated particle. Based on the second fitness value corresponding to each updated particle, determines at least one target calculated riverbed topography that matches each real measured riverbed topography, thereby ensuring the accuracy of the at least one target real measured riverbed topography that matches each calculated riverbed topography.

[0053] In an optional embodiment, determining the three-dimensional flow field distribution corresponding to the preset river section based on the surface flow velocity and the surface flow velocity corresponding to each preset position includes:

[0054] The surface flow velocity corresponding to each preset position, the calculated riverbed topography, and the position information corresponding to each preset position are input into the preset flow field distribution determination model, and the three-dimensional flow field distribution corresponding to the preset river section is output.

[0055] The method for determining the flow field distribution of a river section provided in an embodiment of the present application inputs the surface flow velocity corresponding to each preset position, the calculated riverbed topography, and the position information corresponding to each preset position into a preset flow field distribution determination model, and outputs the three-dimensional flow field distribution corresponding to the preset river section, thereby ensuring the accuracy of the output three-dimensional flow field distribution corresponding to the preset river section.

[0056] In an optional embodiment, the training method of the preset flow field distribution determination model includes:

[0057] Obtaining a training data set; the training data set includes training surface flow velocity, training riverbed topography, training location information, and training flow field distribution corresponding to the training river at multiple training locations corresponding to the training river, where the training flow field distribution is label information;

[0058] Input the training data set into the initial flow field distribution determination network;

[0059] Based on a preset loss function, a preset optimization algorithm is used to train the initial flow field distribution determination network to generate a preset flow field distribution determination model; wherein the preset loss function includes at least one of the Navier-Stokes equations, velocity boundary conditions, and surface flow velocity boundary conditions.

[0060] The method for determining the flow field distribution of a river section provided in an embodiment of the present application obtains a training data set; inputs the training data set into an initial flow field distribution determination network; based on a preset loss function, a preset optimization algorithm is used to train the initial flow field distribution determination network to generate a preset flow field distribution determination model, thereby ensuring the accuracy of the generated preset flow field distribution determination model and satisfying at least one of the Navier-Stokes equations, velocity boundary conditions, and surface velocity boundary conditions.

[0061] In a second aspect, the present invention provides a drone device comprising: a control component, a positioning component, an ultrasonic radar component, a lidar component, and a computer-readable storage medium. The control component is communicatively connected to the positioning component, the ultrasonic radar component, and the lidar component. The computer-readable storage medium stores computer instructions. The control component executes the method for determining the river section flow field distribution of the first aspect or any corresponding embodiment thereof by executing the computer instructions. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0063] Figure 1 is a schematic structural diagram of a drone device according to an embodiment of the present invention;

[0064] Figure 2 is a schematic flow chart of a method for determining a river section flow field distribution according to an embodiment of the present invention;

[0065] Figure 3 is a flow chart of another method for determining the flow field distribution of a river section according to an embodiment of the present invention;

[0066] Figure 4 is a flow chart of another method for determining the flow field distribution of a river section according to an embodiment of the present invention;

[0067] Figure 5 is a structural block diagram of a device for determining a river section flow field distribution according to an embodiment of the present invention;

[0068] Figure 6 Schematic diagram of the hardware structure of the control component of an embodiment of the present invention. DETAILED DESCRIPTION

[0069] To make the purpose, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative efforts shall fall within the scope of protection of the present invention.

[0070] With population growth and economic development, the demand for water resources continues to increase, but this also faces challenges such as water shortages, water pollution, and ecological degradation. Therefore, in-depth research on the flow field distribution of pre-defined river sections is of great significance for addressing the challenges of water resource management and environmental protection.

[0071] In the prior art, measurement points are usually set up in a preset river section, and field measurements are performed using instruments such as flow meters and water level meters to obtain data such as water flow velocity and water level, thereby obtaining the three-dimensional flow field distribution corresponding to the preset river section.

[0072] Therefore, the above method has high labor cost and low efficiency.

[0073] Based on the above method, an embodiment of the present application provides a method for determining the flow field distribution of a river section. The method uses a positioning component to obtain the location information of a drone device, thereby ensuring the accuracy of the acquired location information. The method also includes obtaining a continuous wave signal transmitted by an ultrasonic radar component and a corresponding reflected wave signal. Based on the continuous wave signal and the reflected wave signal, the method determines the surface flow velocity at a preset location in the preset river section corresponding to the location information, thereby ensuring the accuracy of the surface flow velocity at the preset location in the preset river section corresponding to the determined location information. The method also includes obtaining a laser radar signal transmitted by a laser radar component and a target reflected radar signal corresponding to the received laser radar signal. Based on the laser radar signal and the target reflected radar signal, the method determines the calculated riverbed topography at the preset location in the preset river section corresponding to the location information, thereby ensuring the accuracy of the calculated riverbed topography at the preset location in the preset river section corresponding to the determined location information. Based on the surface flow velocity and the calculated riverbed topography corresponding to each preset location, the method determines the three-dimensional flow field distribution corresponding to the preset river section, thereby ensuring the accuracy of the determined three-dimensional flow field distribution corresponding to the preset river section. The above method has low labor costs and high efficiency, and does not require manual measurement of water velocity, water level, and other data corresponding to each location in the preset river section.

[0074] It should be noted that the method for determining the flow field distribution of a river section provided in the embodiment of the present application is applied to the control component in the UAV equipment. Figure 1 As shown, the UAV device also includes a positioning component, an ultrasonic radar component and a laser radar component, and the control component is communicatively connected with the positioning component, the ultrasonic radar component and the laser radar component.

[0075] According to an embodiment of the present invention, an embodiment of a method for determining the flow field distribution of a river section is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0076] In this embodiment, a method for determining the flow field distribution of a river section is provided, which can be used for the control component in the above-mentioned UAV equipment. Figure 2 FIG. 1 is a flow chart of a method for determining a river flow field distribution according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:

[0077] Step S101: Acquire the location information of the drone device based on the positioning component.

[0078] Optionally, the positioning component in the drone device can be RTK (Real-Time Kinematic, real-time dynamic positioning system), an inertial navigation positioning system, or a GPS positioning system. The embodiments of the present application do not specifically limit the positioning component.

[0079] Among them, the RTK system usually consists of the following parts: 1. Base station: a fixed base station installed in a known location, which receives satellite signals and processes them in real time, and sends differential correction information to the mobile station. 2. Mobile station: installed on mobile devices that need to be positioned, such as surveying instruments, drones, vehicles, etc. The mobile station receives satellite signals and calculates high-precision position coordinates in combination with the differential correction information sent by the base station. 3. Data communication link: used for data transmission between the base station and the mobile station, which can be wireless communication (such as radio, mobile network) or wired communication (such as Ethernet). 4. Positioning software: software running on the mobile station device, used to receive satellite signals, process differential correction information, and calculate position coordinates.

[0080] Then, the control component can obtain the location information of the drone device sent by the positioning component based on the communication connection between the control component and the positioning component.

[0081] Step S102: obtaining a continuous wave signal sent by the ultrasonic radar component and a reflected wave signal corresponding to the received continuous wave signal.

[0082] Specifically, after obtaining the location information of the drone device, the control component can control the ultrasonic radar component to send a continuous wave signal, and then the ultrasonic radar component receives a reflected wave signal corresponding to the continuous wave signal.

[0083] The control component can receive the continuous wave signal sent by the ultrasonic radar component and the reflected wave signal corresponding to the continuous wave signal based on the communication connection between the control component and the ultrasonic radar component.

[0084] Step S103 : determining the surface flow velocity at a preset position in the preset river section corresponding to the position information based on the continuous wave signal and the reflected wave signal.

[0085] Specifically, the control component may calculate the phase difference between the continuous wave signal and the reflected wave signal corresponding to the position information.

[0086] Then, the first sub-surface flow velocity at the sub-preset position corresponding to each sub-radar unit is determined according to the phase difference between the continuous wave signal and the reflected wave signal.

[0087] This step will be described in detail below.

[0088] Step S104: Acquire the laser radar signal emitted by the laser radar component and the target reflected radar signal corresponding to the received laser radar signal.

[0089] Specifically, after obtaining the location information of the drone device, the control component can control the lidar component to transmit a lidar signal. Then, the lidar component receives a target-reflected radar signal corresponding to the lidar signal.

[0090] The control component can receive the lidar signal sent by the lidar component and the target reflected radar signal based on the communication connection with the lidar component.

[0091] Step S105 , determining the calculated riverbed topography at a preset position in a preset river section corresponding to the position information based on the laser radar signal and the target reflected radar signal.

[0092] Specifically, the electronic device can obtain the emission time corresponding to the laser radar signal and the reception time corresponding to the target reflected radar signal, then subtract the emission time corresponding to the laser radar signal from the reception time corresponding to the target reflected radar signal and divide it by 2 to calculate the total time it takes for the laser radar signal to reach the preset position in the preset river section, and then calculate the first time it takes for the laser radar signal to propagate in the air based on the propagation speed of the laser radar signal in the air and the location information of the drone device. Then, subtract the first time from the total time to calculate the second time it takes for the laser radar signal to propagate in the water, and then calculate the water depth corresponding to the preset position based on the second time and the propagation speed of the laser radar signal in the water. Then, based on the water depth corresponding to the preset position, determine the calculated riverbed topography at the preset position in the preset river section corresponding to the position information.

[0093] Step S106 , based on the surface flow velocity corresponding to each preset position and the calculated riverbed topography, the three-dimensional flow field distribution corresponding to the preset river section is determined.

[0094] Specifically, the control component can obtain surface flow velocities and calculated riverbed topography data at each preset location. A coordinate system corresponding to the preset river section is then established to correlate and represent the surface flow velocities and calculated riverbed topography data. Based on the surface flow velocity data at the preset locations, a predefined interpolation method (such as linear interpolation or spline interpolation) is used to perform interpolation calculations across the entire surface of the preset river section to obtain the surface flow velocities for the entire surface of the preset river section. The control component can then construct a riverbed topography model for the preset river section based on the calculated riverbed topography data using a numerical terrain model, discrete point cloud, or other suitable modeling techniques. Based on the surface flow velocities and riverbed topography model for the entire surface of the preset river section, the control component uses fluid mechanics principles and numerical methods (such as the finite volume method and the finite element method) to perform flow field calculations. These calculations can take into account laws such as the continuity of water flow, conservation of momentum, and conservation of energy. The control component visualizes the calculated three-dimensional flow field data to facilitate intuitive observation of the flow field distribution and characteristics. Professional visualization software or tools can be used to present information such as flow velocity, direction, and streamlines.

[0095] This step will be described in detail below.

[0096] The method for determining the flow field distribution in a river section provided by the embodiments of the present application uses a positioning component to obtain the location information of a drone device, thereby ensuring the accuracy of the acquired location information. The method also includes obtaining a continuous wave signal transmitted by an ultrasonic radar component and a corresponding reflected wave signal from the received continuous wave signal. Based on the continuous wave signal and the reflected wave signal, the method determines the surface flow velocity at a preset location in the preset river section corresponding to the location information, thereby ensuring the accuracy of the surface flow velocity at the preset location in the preset river section corresponding to the determined location information. The method also includes obtaining a laser radar signal transmitted by a laser radar component and a corresponding target reflected radar signal from the received laser radar signal. Based on the laser radar signal and the target reflected radar signal, the method determines the calculated riverbed topography at the preset location in the preset river section corresponding to the location information, thereby ensuring the accuracy of the calculated riverbed topography at the preset location in the preset river section corresponding to the determined location information. Based on the surface flow velocity and the calculated riverbed topography corresponding to each preset location, the method determines the three-dimensional flow field distribution corresponding to the preset river section, thereby ensuring the accuracy of the determined three-dimensional flow field distribution corresponding to the preset river section. This method is low in labor cost and highly efficient, as it does not require manual measurement of water velocity, water level, and other data corresponding to each location in the preset river section.

[0097] In this embodiment, a method for determining the flow field distribution of a river section is provided, which can be used for the control component in the above-mentioned UAV equipment. Figure 3 FIG. 1 is a flow chart of a method for determining a river flow field distribution according to an embodiment of the present invention. Figure 3 As shown, the process includes the following steps:

[0098] Step S201: Acquire the location information of the drone device based on the positioning component.

[0099] For details about this step, please refer to the above description of step S101 and will not be repeated here.

[0100] Step S202: Acquire the continuous wave signal sent by the ultrasonic radar component and the reflected wave signal corresponding to the received continuous wave signal.

[0101] For details about this step, please refer to the above description of step S102 and will not be repeated here.

[0102] Step S203 : determining the surface flow velocity at a preset position in the preset river section corresponding to the position information based on the continuous wave signal and the reflected wave signal.

[0103] Specifically, the ultrasonic radar assembly includes multiple sub-radar units, the continuous wave signal is the sub-continuous wave signal corresponding to each of the multiple sub-radar units, and the reflected wave signal is the sub-reflected wave signal corresponding to each of the multiple sub-radar units; the preset position includes the sub-preset position corresponding to each sub-radar unit and the overlapping area corresponding to each sub-preset position; the surface flow velocity includes the first sub-surface flow velocity corresponding to each sub-preset position and the second sub-surface flow velocity corresponding to each overlapping area. The above step S203 may include the following steps:

[0104] Step S2031: Calculate the first sub-surface flow velocity at the sub-preset position corresponding to each sub-radar unit based on the sub-continuous wave signal and the sub-reflected wave signal corresponding to each sub-radar unit.

[0105] Specifically, the above step S2031 may include the following steps:

[0106] Step a1: Calculate the phase difference between the sub-continuous wave signal and the sub-reflected wave signal corresponding to each sub-radar unit.

[0107] Specifically, the control component may calculate the phase difference between the sub-continuous wave signal and the sub-reflected wave signal corresponding to each sub-radar unit.

[0108] For example, the expression of the sub-continuous wave signal can be:

[0109]

[0110] Where s represents the sub-continuous wave signal of frequency modulation within the preset time period, e is the base of the natural logarithmic exponential function, which is used to express periodic fluctuations. j is the imaginary unit, f c is the carrier frequency, k is the slope of the frequency modulation, which defines the rate of change of the signal frequency over time, and t is time.

[0111] The sub-reflected wave signal can be the superposition of signals reflected from multiple scattering sources. The signal of each scattering source can be expressed as:

[0112]

[0113] Among them, A n is the reflection intensity, τ n is the nth signal propagation delay, f d,n It is the Doppler shift caused by the movement of the water surface.

[0114] Then, the control component can perform mixing operations and low-pass filtering operations on the sub-continuous wave signal and the sub-reflected wave signal, wherein the mixing operation involves combining the sub-continuous wave signal and the sub-reflected wave signal to generate a difference frequency signal.

[0115]

[0116] Among them, the control component can first perform conjugate processing on the sub-reflected wave signal, * represents the conjugate complex number. By multiplying the sub-continuous wave signal with the sub-reflected wave signal after conjugate processing, the phase difference between the sub-continuous wave signal s and the sub-reflected wave signal r can be calculated. This phase information is very important in ranging and speed measurement. It can extract the frequency change caused by target movement (such as water flow speed). The phase difference is mainly reflected in the Doppler frequency shift f d,n Therefore, the control component can calculate the Doppler frequency shift f based on the above formula (3): d,n .

[0117] Step a2: determining the first sub-surface flow velocity at the sub-preset position corresponding to each sub-radar unit according to the phase difference.

[0118] Specifically, the control component calculates the first sub-surface flow velocity of the sub-preset position corresponding to each sub-radar unit based on the correspondence between the phase difference and the water flow velocity.

[0119] For example, the Doppler shift f d,n The relationship with water velocity v is:

[0120]

[0121] Where λ is the wavelength. According to the characteristics of Bragg scattering, the wavelength λ must match half the wavelength of the water surface wave. When the wavelength of the radar wave matches half the wavelength of the water surface wave, the reflected signal intensity increases.

[0122] This is because the scattered wavefront "resonates" with the periodic structure of the water surface, enhancing the intensity of the reflected wave. By configuring multiple radar units into an array, each unit can independently scan different areas, thereby achieving flow velocity measurement at multiple points on the surface. The data collected by each radar unit can be integrated and analyzed to form a comprehensive view of water flow velocity, providing more comprehensive water dynamic information. If there are N sub-radar units, the first surface flow velocity of the sub-preset position corresponding to the i-th sub-radar unit is:

[0123]

[0124] Optionally, the electronic device may calculate the flow velocity variance corresponding to each first sub-surface flow velocity according to the following formula (6). Then, the flow velocity variance corresponding to each first sub-surface flow velocity is compared with the flow velocity variance threshold. If the flow velocity variance corresponding to each first sub-surface flow velocity is less than or equal to the flow velocity variance threshold, it is determined that the calculated first surface flow velocity of each sub-preset position is accurate. If the flow velocity variance corresponding to the first sub-surface flow velocity is greater than the flow velocity variance threshold, it is determined that the calculated first surface flow velocity of the sub-preset position is inaccurate, and the electronic device recalculates the first sub-surface flow velocity corresponding to each target sub-radar unit.

[0125]

[0126] in, and are the partial derivatives of the first sub-surface flow velocity corresponding to the i-th target sub-radar unit in the x and y directions (which can be understood as the river direction and the direction perpendicular to the river channel), and The variance of the flow velocity of the first sub-surface corresponding to the i-th target sub-radar unit in the x and y directions. is the velocity variance of the first sub-surface flow velocity corresponding to the i-th target sub-radar unit.

[0127] Step S2032: Obtain the overlapping areas corresponding to the sub-preset positions.

[0128] Specifically, after the control component calculates the first sub-surface flow velocity of the sub-preset position corresponding to each sub-radar unit, the electronic device can obtain the overlapping area corresponding to each sub-preset position.

[0129] Step S2033: Obtain radar signal-to-noise ratio values ​​of each target sub-radar unit corresponding to the overlapping area.

[0130] Specifically, the control component can obtain each target sub-radar unit corresponding to the overlapping area. The control component can then receive radar signal-to-noise ratio values ​​for each target sub-radar unit input by the user or sent by other devices. The electronic device can also obtain the radar signal strength and noise intensity corresponding to each target sub-radar unit and then calculate the radar signal-to-noise ratio value for each target sub-radar unit based on the obtained radar signal strength and noise intensity corresponding to each target sub-radar unit.

[0131] Step S2034: Determine weight information corresponding to each target sub-radar unit according to the radar signal-to-noise ratio value of each target sub-radar unit.

[0132] Specifically, the control component can sort the radar signal-to-noise ratio values ​​of the target sub-radar units from large to small, and then determine the weight information corresponding to each target sub-radar unit according to the sorting of the radar signal-to-noise ratio values ​​corresponding to each target sub-radar unit.

[0133] In step S2035, the weight information corresponding to each target sub-radar unit is multiplied by the first sub-surface flow velocity corresponding to each target sub-radar unit, and then the results are added and averaged to obtain the second sub-surface flow velocity corresponding to the overlapping area.

[0134] Specifically, the electronic device may multiply the weight information corresponding to each target sub-radar unit by the first sub-surface flow velocity corresponding to each target sub-radar unit, and then add and average the results to obtain the second sub-surface flow velocity corresponding to the overlapping area.

[0135] Exemplarily, the control component may calculate the flow velocity of the second sub-surface corresponding to the overlapping area using the following formula:

[0136]

[0137] Among them, w i is the weight information corresponding to the i-th target sub-radar unit, v i is the first sub-surface flow velocity corresponding to the i-th target sub-radar unit.

[0138] Step S204: Acquire the laser radar signal emitted by the laser radar component and the target reflected radar signal corresponding to the received laser radar signal.

[0139] Specifically, the above step S204 may include the following steps:

[0140] Step S2041, obtaining the laser radar signal emitted by the laser radar component.

[0141] Specifically, the control component can receive the lidar signal sent by the lidar component based on the communication connection between the control component and the lidar component.

[0142] Step S2042: Receive at least one backup reflected radar signal corresponding to the laser radar signal.

[0143] Specifically, after the laser radar component transmits a laser radar signal, it will receive at least one backup reflected radar signal corresponding to the laser radar signal.

[0144] Then, the laser radar component transmits each received backup reflected radar signal to the laser radar signal, so that the control component can receive at least one backup reflected radar signal corresponding to the laser radar signal.

[0145] Step S2043: Identify each backup reflected radar signal.

[0146] Specifically, the control component can identify the light intensity and reception time corresponding to each backup reflected radar signal.

[0147] Step S2044: If the backup reflected radar signal meets a preset condition, the backup reflected radar signal is determined as the target reflected radar signal.

[0148] Specifically, the preset conditions include a preset light intensity condition and a preset time condition. The above step S2044 may include the following steps:

[0149] Step b1: Identify the laser radar signal, determine the first light intensity corresponding to the laser radar signal, and determine the emission time corresponding to the laser radar signal.

[0150] Specifically, the control component can process and analyze the lidar signal to extract light intensity information, determine the first light intensity corresponding to the lidar signal, and receive the emission time corresponding to the lidar signal sent by the lidar component.

[0151] Step b2: determining a preset light intensity threshold according to the first light intensity, and determining a preset receiving time threshold according to the emission time.

[0152] Specifically, the control component can multiply the first light intensity by the first preset threshold to calculate the preset light intensity threshold. Optionally, the control component can obtain historical data corresponding to the preset river section input by the user, search the water depth range corresponding to the preset river section from the historical data, and then determine the reduction rate of the light intensity in the water based on the water depth range, and then determine the first preset threshold based on the reduction rate of the light intensity in the water. Among them, the first preset threshold can be 0.6, or 0.5, or other values ​​less than 1. The embodiment of the present application does not specifically limit the preset threshold because the embodiment of the present application does not specifically limit the preset light threshold.

[0153] Specifically, the control component may also determine a first preset duration based on the water depth range. The first preset duration may be 1 second, 2 seconds, or other durations, and is not specifically limited in this embodiment of the present application. The control component may then add the first preset duration to the transmission time to calculate a preset reception time threshold.

[0154] Step b3: Obtain the second light intensity and reception time corresponding to each standby reflected radar signal.

[0155] Specifically, the control component can process and analyze each backup reflected radar signal to extract light intensity information and determine the second light intensity corresponding to each backup reflected radar signal. The control component can also receive the corresponding reception identification of each backup reflected radar signal sent by the laser radar device.

[0156] Step b4: for each standby reflected radar signal, the second light intensity is compared with a preset light intensity threshold, and the receiving time is compared with a preset receiving time threshold.

[0157] Specifically, the control component compares the second light intensity corresponding to each backup reflected radar signal with a preset light intensity threshold, and compares the receiving time corresponding to each backup reflected radar signal with a preset receiving time threshold.

[0158] Step b5: If the second light intensity is less than the preset light intensity threshold and the receiving time is later than the preset receiving time threshold, the backup reflected radar signal is determined as the target reflected radar signal.

[0159] Specifically, if the second light intensity corresponding to the backup reflection radar signal is less than the preset light intensity threshold and the receiving time is later than the preset receiving time threshold, the backup reflection radar signal is determined as the target reflection radar signal, thereby filtering out the backup reflection radar signal reflected back by the laser radar signal reaching the water surface, and the backup reflection radar signal reflected back after the laser radar signal reaches other objects in the water, thereby ensuring that the determined target reflection radar signal is the reflection radar signal reflected back after the laser radar signal reaches the riverbed.

[0160] Step S205 , determining the calculated riverbed topography at a preset position in a preset river section corresponding to the position information based on the laser radar signal and the target reflected radar signal.

[0161] For details about this step, please refer to the above description of step S105 and will not be repeated here.

[0162] Step S206 , based on the surface flow velocity corresponding to each preset position and the calculated riverbed topography, the three-dimensional flow field distribution corresponding to the preset river section is determined.

[0163] For details about this step, please refer to the above description of step S106 and will not be repeated here.

[0164] The method for determining the flow field distribution of a river section provided in an embodiment of the present application calculates the phase difference between the sub-continuous wave signal and the sub-reflected wave signal corresponding to each sub-radar unit, thereby ensuring the accuracy of the calculated phase difference between the sub-continuous wave signal and the sub-reflected wave signal corresponding to each sub-radar unit. Based on the phase difference, the first sub-surface flow velocity of the sub-preset position corresponding to each sub-radar unit is determined, thereby ensuring the accuracy of the first sub-surface flow velocity of the sub-preset position corresponding to each sub-radar unit. The overlapping area corresponding to each sub-preset position is obtained; the radar signal-to-noise ratio value of each target sub-radar unit corresponding to the overlapping area is obtained, thereby ensuring the accuracy of the weight information corresponding to each sub-radar unit. The weight information corresponding to each target sub-radar unit is multiplied by the first sub-surface flow velocity corresponding to each target sub-radar unit, and then the sum is added and averaged to obtain the second sub-surface flow velocity corresponding to the overlapping area, thereby ensuring the accuracy of the obtained second sub-surface flow velocity corresponding to the overlapping area.

[0165] Then, the laser radar signal emitted by the laser radar component is obtained; at least one backup reflection radar signal corresponding to the laser radar signal is received; and each backup reflection radar signal is identified. The laser radar signal is identified, and the first light intensity corresponding to the laser radar signal is determined, and the emission time corresponding to the laser radar signal is determined, thereby ensuring the accuracy of the determined first light intensity and emission time. A preset light intensity threshold is determined based on the first light intensity, and a preset reception time threshold is determined based on the emission time, thereby ensuring the accuracy of the determined preset light intensity threshold and preset reception time threshold. The second light intensity and reception time corresponding to each backup reflection radar signal are obtained; for each backup reflection radar signal, the second light intensity is compared with the preset light intensity threshold, and the reception time is compared with the preset reception time threshold, thereby ensuring the accuracy of the comparison result obtained. If the second light intensity is less than the preset light intensity threshold, and the reception time is later than the preset reception time threshold, the backup reflection radar signal is determined as the target reflection radar signal, thereby ensuring the accuracy of the determined target reflection radar signal.

[0166] In this embodiment, a method for determining the flow field distribution of a river section is provided, which can be used for the control component in the above-mentioned UAV equipment. Figure 4 FIG. 1 is a flow chart of a method for determining a river flow field distribution according to an embodiment of the present invention. Figure 4 As shown, the process includes the following steps:

[0167] Step S301: Acquire the location information of the drone device based on the positioning component.

[0168] For details about this step, please refer to the above description of step S201 and will not be repeated here.

[0169] Step S302: Acquire the continuous wave signal sent by the ultrasonic radar component and the reflected wave signal corresponding to the received continuous wave signal.

[0170] For details about this step, please refer to the above description of step S202 and will not be repeated here.

[0171] Step S303 : determining the surface flow velocity at a preset position in the preset river section corresponding to the position information based on the continuous wave signal and the reflected wave signal.

[0172] For details about this step, please refer to the above description of step S203 and will not be repeated here.

[0173] Step S304: Acquire the laser radar signal emitted by the laser radar component and the target reflected radar signal corresponding to the received laser radar signal.

[0174] For details about this step, please refer to the above description of step S204 and will not be repeated here.

[0175] Step S305 , determining the calculated riverbed topography at a preset position in a preset river section corresponding to the position information based on the laser radar signal and the target reflected radar signal.

[0176] For details about this step, please refer to the above description of step S205 and will not be repeated here.

[0177] Step S306: obtaining the actual measured riverbed topography corresponding to multiple reference points in the preset river section.

[0178] Specifically, the control component can receive the actual measured riverbed topography corresponding to multiple reference points in a preset river section input by the user, or can receive the actual measured riverbed topography corresponding to multiple reference points in the preset river section sent by other devices. The actual measured riverbed topography corresponding to multiple reference points in the preset river section can be obtained by setting measurement points at multiple reference points in the preset river section and conducting field measurements using instruments such as a current meter and a water level gauge.

[0179] Step S307 : calculating a first similarity between the calculated riverbed topography corresponding to each preset position and the actual measured riverbed topography corresponding to each reference point.

[0180] Specifically, the control component may calculate a first similarity between the calculated riverbed topography corresponding to each preset position and the actual measured riverbed topography corresponding to each reference point based on a preset similarity algorithm.

[0181] The preset similarity algorithm may be a Euclidean distance algorithm, a Mahalanobis distance algorithm, a cosine distance algorithm, or the like.

[0182] Illustratively, the embodiment of the present application calculates the first similarity between the calculated riverbed topography corresponding to each preset position and the actual measured riverbed topography corresponding to each reference point based on the following formula according to the Mahalanobis distance algorithm.

[0183]

[0184] Tp i =Rp i +t (9)

[0185] Among them, Y represents the real measured riverbed terrain dataset corresponding to each reference point, P represents the calculated riverbed terrain dataset corresponding to each preset position, and y i is the value of each point in Y, p i is the value of each point in P, R and t are rotation matrices and translation matrices respectively, which are obtained from the yaw angle and other data of the UAV equipment. These two transformations are used to align the theoretical terrain data with the actual terrain data. V represents the covariance matrix of the i-th and j-th items of y and p, is the mean of the real measured riverbed topography dataset corresponding to each reference point, is the mean of the calculated riverbed topography dataset corresponding to each preset location.

[0186] Step S308: Based on each first similarity, at least one target real measured riverbed topography matching each calculated riverbed topography is calculated and obtained.

[0187] Specifically, the above step S308 may include the following steps:

[0188] Step S3081, randomly initialize the current position and current velocity of each initial particle.

[0189] Specifically, the control component may randomly initialize a plurality of initial particles, and initialize the current position and current velocity of each initial particle.

[0190] Step S3082: Determine the first fitness value of each initial particle according to each first similarity.

[0191] The first fitness value represents the matching degree between the initial particles and the actual measured riverbed topography.

[0192] Specifically, the control component may determine the first fitness value of each initial particle based on each first similarity.

[0193] It should be noted that there is a correlation between the particles and the calculated riverbed topography corresponding to each preset position.

[0194] Step S3083: Determine the individual optimal position and the global optimal position corresponding to each initial particle according to the first fitness value.

[0195] Specifically, the control component may determine the individual optimal position corresponding to each initial particle according to the first fitness value corresponding to each initial particle.

[0196] The individual best position is the best position achieved by the particle in the current iteration.

[0197] At the same time, the control component can also determine the global optimal position, which is the best position reached by the entire particle swarm in the current iteration, based on the first fitness value corresponding to each initial particle. The global optimal position is the position with the highest fitness value among all initial particles.

[0198] Step S3084 : updating each initial particle according to the current position and current velocity corresponding to each initial particle, the individual optimal position, and the global optimal position to generate updated particles.

[0199] Specifically, the control component can use the particle swarm optimization algorithm's update formula to update each initial particle based on its current position and velocity, individual optimal position, and global optimal position, generating updated particles. The updated particle positions and velocities are then used for the next iteration.

[0200] Step S3085: Calculate the second fitness value corresponding to each updated particle.

[0201] Specifically, the control component may calculate the similarity between each update particle and each real measured riverbed topography, and determine the calculated similarity between each update particle and each real measured riverbed topography as the second fitness value corresponding to each update particle.

[0202] Step S3086: Determine at least one target calculated riverbed topography that matches each actual measured riverbed topography based on the second fitness value corresponding to each updated particle.

[0203] Specifically, the control component may determine at least one target real measured riverbed topography that matches each calculated riverbed topography according to the second fitness value of each updated particle.

[0204] For example, the control component may select an update particle with a higher second fitness value as a target particle. Based on the position information of the target particles, the control component then determines at least one target calculated riverbed topography that is closest to each target particle. This determines at least one target calculated riverbed topography that matches each actual measured riverbed topography.

[0205] Through continuous iteration of the above steps, the particle swarm optimization algorithm gradually converges to a target, real-world measured riverbed topography that matches each calculated riverbed topography. During this process, the particle swarm continuously adjusts its position and velocity, exploring the solution space to find the optimal match. It's important to note that the specific implementation details may vary depending on the specific requirements of the problem and the characteristics of the data. In actual applications, adjustments and optimizations may be necessary based on actual conditions, such as selecting an appropriate similarity calculation method, adjusting particle swarm parameters, and introducing additional constraints. Furthermore, combining other algorithms or techniques can be considered to improve matching accuracy and efficiency.

[0206] Step S309 : For each actual measured riverbed topography, a second similarity between the actual measured riverbed topography and each target calculated riverbed topography is calculated.

[0207] Specifically, for each real measured riverbed topography, the control component can calculate the sub-second similarity between the real measured riverbed topography and each target calculated riverbed topography, and then average each sub-second similarity to obtain the second similarity between the real measured riverbed topography and each target calculated riverbed topography.

[0208] Step S310: Based on the second similarity, the position information and attitude information of the UAV device are adjusted to ensure the accuracy of each calculated riverbed terrain.

[0209] Specifically, the control component can compare the second similarity with the preset similarity threshold. If the second similarity is less than the preset similarity threshold, the control device can adjust the position information and posture information of the drone device until the second similarity calculated again is greater than or equal to the preset similarity threshold, thereby ensuring the accuracy of each calculated riverbed terrain.

[0210] Step S311 : determining the three-dimensional flow field distribution corresponding to the preset river section based on the surface flow velocity corresponding to each preset position and the calculated riverbed topography.

[0211] Specifically, the above step S311 may include the following steps:

[0212] Step S3111: input the surface flow velocity corresponding to each preset position, the calculated riverbed topography, and the position information corresponding to each preset position into the preset flow field distribution determination model, and output the three-dimensional flow field distribution corresponding to the preset river section.

[0213] Specifically, the control component inputs the surface flow velocity corresponding to each preset position, the calculated riverbed topography, and the position information corresponding to each preset position into the preset flow field distribution determination model, and outputs the three-dimensional flow field distribution corresponding to the preset river section.

[0214] In an optional embodiment of the present application, a training method for a preset flow field distribution determination model may include the following steps:

[0215] Step c1: Obtain a training data set.

[0216] The training data set includes training surface flow velocity, training riverbed topography, training location information and training flow field distribution corresponding to the training river at multiple training locations corresponding to the training river, and the training flow field distribution is label information.

[0217] Specifically, the control component may receive a training data set input by a user, or may receive a training data set sent by other devices.

[0218] Step c2: input the training data set into the initial flow field distribution determination network.

[0219] Specifically, the control component can input the training data set into the initial flow field distribution determination network.

[0220] Step c3: Based on a preset loss function, a preset optimization algorithm is used to train the initial flow field distribution determination network to generate a preset flow field distribution determination model.

[0221] The preset loss function includes at least one of the Navier-Stokes equation, the velocity boundary condition, and the surface flow velocity boundary condition.

[0222] Specifically, the control component can train the initial flow field distribution determination network based on a preset loss function using a preset optimization algorithm to generate a preset flow field distribution determination model.

[0223] Among them, the preset loss function can be as follows:

[0224]

[0225] Among them, w1, w2, and w3 are weight factors used to balance the influence of different physical equations.

[0226] in, The Navier-Stokes equations (NS) are a set of equations of motion that describe the conservation of momentum for viscous, incompressible fluids. They are one of the fundamental equations in fluid mechanics, used to describe the movement and changes of fluids. Here, ρ is the density, u is the velocity field, p is the pressure, μ is the dynamic viscosity of the water, and f is the body force, which is generally driven by gravity due to the flow of water upstream and downstream.

[0227] The first term on the left side of the NS equation represents the inertial force of the fluid, the second term represents the convection term of the fluid, the first term on the right side represents the pressure gradient force, the second term represents the viscous force, and the third term represents the external force. The NS equation has a wide range of applications in fluid mechanics, for example, in fields such as weather forecasting, aerospace, hydraulic engineering, and petrochemical engineering, where it is used to simulate and predict fluid flow, heat transfer, and mass transfer. It is important to note that the NS equation is a nonlinear partial differential equation that is very difficult to solve, and numerical methods are usually required for approximate solutions.

[0228] Where u(x,y,zbed,t)=0, (x,y,zbed) is the riverbed location information, and the riverbed topography is defined as the velocity boundary condition to ensure that the flow velocity is zero at the riverbed contact point.

[0229] in, It is to combine the level set function with the surface velocity boundary condition to ensure that the input realizes the known velocity distribution at φ = 0, so as to ensure that the velocity at the fluid interface, that is, where the level set is zero, conforms to the observed data.

[0230] The preset optimization algorithm may be an Adam optimizer or an L-BFGS prioritizer.

[0231] Furthermore, when training the above-mentioned initial flow field distribution determination network, an Adam optimizer can be selected to optimize the initial flow field distribution determination network, so that the initial flow field distribution determination network can converge quickly and have good generalization ability.

[0232] When the Adam optimizer is used to optimize the initial flow field distribution determination network, a learning rate can also be set for the optimizer. Here, the learning rate range test (LR Range Test) technique can be used to select the optimal learning rate and set it to the optimizer. The learning rate selection process of this test technology is as follows: first, the learning rate is set to a very small value, and then the initial flow field distribution determination network and the training data set are simply iterated several times. After each iteration, the learning rate is increased, and the training loss (loss) is recorded each time. Then, the LR Range Test graph is drawn. Generally, the ideal LR Range Test graph contains three areas: in the first area, the learning rate is too small and the loss remains basically unchanged. In the second area, the loss decreases and converges quickly. In the last area, the learning rate is so large that the loss begins to diverge. In this case, the learning rate corresponding to the lowest point in the LR Range Test graph can be used as the optimal learning rate, and this optimal learning rate is used as the initial learning rate of the Adam optimizer and set to the optimizer.

[0233] The method for determining the flow field distribution of a river section provided in an embodiment of the present application obtains the real measured riverbed topography corresponding to multiple reference points in a preset river section; calculates the first similarity between the calculated riverbed topography corresponding to each preset position and the real measured riverbed topography corresponding to each reference point, thereby ensuring the accuracy of each calculated first similarity. Randomly initialize the current position and current velocity of each initial particle; determine the first fitness value of each initial particle based on each first similarity, thereby ensuring the accuracy of the first fitness value of each determined initial particle. Based on the first fitness value, determine the individual optimal position and global optimal position corresponding to each initial particle, thereby ensuring the accuracy of the individual optimal position and global optimal position corresponding to each determined initial particle. Based on the current position and current velocity, individual optimal position and global optimal position corresponding to each initial particle, update each initial particle to generate each updated particle, thereby ensuring the accuracy of each generated updated particle. Calculate the second fitness value corresponding to each updated particle, thereby ensuring the accuracy of the second fitness value corresponding to the calculated updated particle. At least one target calculated riverbed topography matching each real measured riverbed topography is determined based on the second fitness value corresponding to each updated particle, thereby ensuring the accuracy of the determined at least one target real measured riverbed topography matching each calculated riverbed topography.

[0234] Then, for each actual measured riverbed topography, a second similarity is calculated between the actual measured riverbed topography and each target calculated riverbed topography, ensuring the accuracy of each calculated second similarity. Based on this second similarity, the position and attitude information of the UAV device are adjusted to ensure the accuracy of the UAV device's position and attitude information, thereby avoiding inaccurate calculated riverbed topography caused by inaccurate UAV device position and attitude information.

[0235] The surface flow velocity corresponding to each preset position, the calculated riverbed topography, and the position information corresponding to each preset position are input into the preset flow field distribution determination model, and the three-dimensional flow field distribution corresponding to the preset river section is output, thereby ensuring the accuracy of the output three-dimensional flow field distribution corresponding to the preset river section.

[0236] Among them, the training process of the preset flow field distribution determination model includes: obtaining a training data set; inputting the training data set into the initial flow field distribution determination network; based on a preset loss function, using a preset optimization algorithm to train the initial flow field distribution determination network to generate a preset flow field distribution determination model, thereby ensuring the accuracy of the generated preset flow field distribution determination model and satisfying at least one of the Navier-Stokes equations, velocity boundary conditions, and surface flow velocity boundary conditions.

[0237] In this embodiment, a device for determining the flow field distribution of a river section is also provided. The device is used to implement the above-mentioned embodiments and preferred embodiments, and the details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated.

[0238] This embodiment provides a device for determining the flow field distribution of a river section, which is applied to a control component in a drone device. The drone device also includes a positioning component, an ultrasonic radar component, and a laser radar component. The control component is communicatively connected with the positioning component, the ultrasonic radar component, and the laser radar component. Figure 5 Shown, including:

[0239] The first acquisition module 401 is used to obtain the location information of the UAV device based on the positioning component;

[0240] The second acquisition module 402 is used to acquire the continuous wave signal sent by the ultrasonic radar component and the reflected wave signal corresponding to the received continuous wave signal;

[0241] A first determining module 403 is configured to determine a surface flow velocity at a preset location in a preset river section corresponding to the location information based on the continuous wave signal and the reflected wave signal;

[0242] The third acquisition module 404 is used to acquire the laser radar signal emitted by the laser radar component and the target reflected radar signal corresponding to the received laser radar signal;

[0243] A second determining module 405 is configured to determine a calculated riverbed topography at a preset location in a preset river section corresponding to the location information based on the laser radar signal and the target reflected radar signal;

[0244] The third determination module 406 is configured to determine the three-dimensional flow field distribution corresponding to the preset river section based on the surface flow velocity corresponding to each preset position and the calculated riverbed topography.

[0245] The river section flow field distribution determination X device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0246] The embodiment of the present invention also provides a control component having the above Figure 5 The device for determining the flow field distribution of a river section is shown.

[0247] See also Figure 6 , Figure 6 is a structural diagram of a control component provided by an optional embodiment of the present invention, such as Figure 6 As shown, the control assembly includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components utilize different buses to communicate with each other and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the control assembly, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 6 A processor 10 is taken as an example.

[0248] The processor 10 may be a central processing unit, a network processor, or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic, or any combination thereof.

[0249] The memory 20 stores instructions that can be executed by at least one processor 10, so as to enable at least one processor 10 to execute the method shown in the above embodiment.

[0250] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created based on the use of the control component, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely located relative to the processor 10, and these remote memories may be connected to the control component via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0251] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0252] The control component further includes a communication interface 30 for the control component to communicate with other devices or a communication network.

[0253] An embodiment of the present application also provides a drone device, which includes the above-mentioned control component. The drone device also includes a positioning component, an ultrasonic radar component, a lidar component and a computer-readable storage medium. The control component is communicatively connected with the positioning component, the ultrasonic radar component and the lidar component. Computer instructions are stored on the computer-readable storage medium. The control component executes the computer instructions to execute the river section flow field distribution determination method of any one of the above-mentioned embodiments.

[0254] The embodiment of the present invention also provides a computer-readable storage medium. The above-mentioned method according to the embodiment of the present invention can be implemented in hardware, firmware, or implemented as a computer code that can be recorded in a storage medium, or implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and downloaded through a network and will be stored in a local storage medium, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state drive, etc.; further, the storage medium can also include a combination of the above-mentioned types of memory. It can be understood that a computer, a processor, a microprocessor controller or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor or hardware, the method shown in the above embodiment is implemented.

[0255] A portion of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the form in which the computer program instruction exists in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc. Accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium that can be accessed by the computer.

[0256] Although the embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention. Such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for determining the flow field distribution of a river section, characterized in that: A control component applied to a drone device, wherein the drone device further includes a positioning component, an ultrasonic radar component, and a laser radar component, wherein the control component is communicatively connected with the positioning component, the ultrasonic radar component, and the laser radar component, wherein the ultrasonic radar component includes multiple sub-radar units, wherein: the method includes: Obtain the location information of the drone device based on the positioning component; Acquire the sub-continuous wave signals sent by each sub-radar unit and the sub-reflected wave signals corresponding to each received sub-continuous wave signal; For the sub-reflected wave signals and sub-continuous wave signals corresponding to each sub-radar unit, conjugate processing is performed on the sub-reflected wave signals; Multiplying the sub-continuous wave signal with the sub-reflected wave signal after conjugation processing to obtain the phase difference between the sub-continuous wave signal and the sub-reflected wave signal; determining a first sub-surface flow velocity at a sub-preset position corresponding to each sub-radar unit according to the phase difference; Get the overlapping area corresponding to each sub-preset position; Obtain radar signal-to-noise ratio values ​​of each target sub-radar unit corresponding to the overlapping area; Determine the weight information corresponding to each target sub-radar unit according to the radar signal-to-noise ratio value of each target sub-radar unit; The weight information corresponding to each target sub-radar unit is multiplied by the first sub-surface flow velocity corresponding to each target sub-radar unit, and then the sum is added and averaged to obtain the second sub-surface flow velocity corresponding to the overlapping area; Obtain the laser radar signal emitted by the laser radar component and the target reflected radar signal corresponding to the received laser radar signal; Determine, based on the laser radar signal and the target reflected radar signal, a calculated riverbed topography at a preset location in a preset river section corresponding to the location information; Based on the surface flow velocity corresponding to each preset position and the calculated riverbed topography, the three-dimensional flow field distribution corresponding to the preset river section is determined.

2. The method according to claim 1, characterized in that The obtaining of the laser radar signal emitted by the laser radar component and the receiving of a target reflected radar signal corresponding to the laser radar signal include: Acquire the laser radar signal emitted by the laser radar component; receiving at least one backup reflected radar signal corresponding to the laser radar signal; identifying each of the standby reflected radar signals; If the backup reflected radar signal meets a preset condition, the backup reflected radar signal is determined as the target reflected radar signal.

3. The method according to claim 2, characterized in that The preset conditions include a preset light intensity condition and a preset time condition; if the backup reflected radar signal satisfies the preset conditions, determining the backup reflected radar signal as the target reflected radar signal includes: Identify the laser radar signal, determine a first light intensity corresponding to the laser radar signal, and determine a transmission time corresponding to the laser radar signal; determining a preset light intensity threshold according to the first light intensity, and determining a preset receiving time threshold according to the emission time; Obtaining a second light intensity and a receiving time corresponding to each of the backup reflected radar signals; For each of the standby reflected radar signals, comparing the second light intensity with the preset light intensity threshold, and comparing the reception time with the preset reception time threshold; If the second light intensity is less than the preset light intensity threshold, and the receiving time is later than the preset receiving time threshold, the backup reflected radar signal is determined as the target reflected radar signal.

4. The method according to claim 1, wherein After determining the calculated riverbed topography at the preset position in the preset river section corresponding to the position information based on the laser radar signal and the target reflected radar signal, the method further includes: Obtaining the actual measured riverbed topography corresponding to a plurality of reference points in the preset river section; Calculating a first similarity between the calculated riverbed topography corresponding to each of the preset positions and the actual measured riverbed topography corresponding to each of the reference points; Based on each of the first similarities, at least one target real measured riverbed topography matching each of the calculated riverbed topography is calculated; For each of the real measured riverbed topography, calculating a second similarity between the real measured riverbed topography and each target calculated riverbed topography; Based on the second similarity, the position information and posture information of the UAV device are adjusted to ensure the accuracy of the calculated riverbed terrains.

5. The method according to claim 4, characterized in that The step of calculating, based on the first similarity, at least one target real measured riverbed topography that matches each calculated riverbed topography includes: Randomly initialize the current position and current velocity of each initial particle; determining a first fitness value of each of the initial particles according to each of the first similarities; the first fitness value represents a degree of matching between the initial particle and each of the actual measured riverbed topography; Determining, according to the first fitness value, an individual optimal position and a global optimal position corresponding to each of the initial particles; updating each of the initial particles according to the current position and the current speed corresponding to each of the initial particles, the individual optimal position, and the global optimal position to generate updated particles; Calculating a second fitness value corresponding to each of the updated particles; At least one target calculated riverbed topography matching each of the actual measured riverbed topography is determined according to the second fitness value corresponding to each of the updated particles.

6. The method according to claim 1, characterized in that The determining of the three-dimensional flow field distribution corresponding to the preset river section based on the surface flow velocity and the surface flow velocity corresponding to each preset position includes: The surface flow velocity corresponding to each of the preset positions, the calculated riverbed topography, and the position information corresponding to each of the preset positions are input into a preset flow field distribution determination model, and the three-dimensional flow field distribution corresponding to the preset river section is output.

7. The method according to claim 6, characterized in that The training method of the preset flow field distribution determination model includes: Acquire a training data set; the training data set includes training surface flow velocity, training riverbed topography, training location information, and training flow field distribution corresponding to the training river at multiple training locations corresponding to the training river, wherein the training flow field distribution is label information; Inputting the training data set into an initial flow field distribution determination network; Based on a preset loss function, a preset optimization algorithm is used to train the initial flow field distribution determination network to generate the preset flow field distribution determination model; wherein the preset loss function includes at least one of the Navier-Stokes equations, velocity boundary conditions, and surface flow velocity boundary conditions.

8. A drone device, characterized in that: include: A control component, a positioning component, an ultrasonic radar component, a laser radar component, and a computer-readable storage medium, wherein the control component is communicatively connected to the positioning component, the ultrasonic radar component, and the laser radar component, and the computer-readable storage medium stores computer instructions, and the control component executes the river section flow field distribution determination method according to any one of claims 1 to 7 by executing the computer instructions.

Images