Marine scene unmanned aerial vehicle-to-ship sight distance path probability prediction method

Abstract

The invention discloses a marine scene unmanned aerial vehicle-to-ship line-of-sight path probability prediction method, which comprises the following steps: comprehensively considering the diversity of a marine environment, further subdividing the marine scene into 12 representative marine sub-scenes, and optimizing and improving an LoS probability expression; training to obtain corresponding Dm, Dd and Db parameter values in each group of scenes by using a two-channel convolutional neural network and spider monkey optimization coupling machine learning method; the LoS probabilities in different sub-scenes are calculated by inputting the distance between the unmanned aerial vehicle and the ship. The method comprehensively considers the marine environment characteristics and the motion of the unmanned aerial vehicle and the ship, considers the influence of the flight height of the unmanned aerial vehicle on signal transmission, and improves the prediction accuracy.

Description

Technical Field

[0001] The present invention relates to the field of wireless information transmission, and in particular to a method for predicting the line-of-sight path probability of an unmanned aerial vehicle (UAV) to a ship in an ocean scene, and is particularly suitable for predicting wireless channels of an unmanned aerial vehicle (UAV) to a ship in an ocean scene. Background Art

[0002] For the integrated network of air, land, and sea, drone-assisted communication has received widespread attention as an emerging communication method, especially in the marine field. Drones can achieve rapid communication coverage of marine scenes by carrying miniaturized communication equipment, providing new solutions for marine observation, resource exploration, emergency rescue and other tasks.

[0003] In ocean scenarios, the Line-of-Sight (LoS) path is the main communication link for drone-to-ship communication, and its stability and reliability are crucial to the performance of the communication system. The probability prediction of the LoS path is of great significance for guiding the design and optimization of communication systems and improving the communication quality. Only by accurately predicting the existence of the LoS path can we accurately describe the interference and attenuation of the signal during transmission, thereby providing theoretical support for the design of efficient communication systems. However, in the ocean communication scenario of drones to ships, it is extremely difficult to determine whether there is a LoS path due to multiple factors such as weather conditions, sea surface fluctuations, and the movement of the drone itself. Traditional methods for predicting the probability of LoS paths are mostly based on urban building scenarios and cannot be applied to ocean communication scenarios. Therefore, it is of great practical significance to study and develop a method for predicting the probability of LoS paths between drones and ships that is suitable for ocean scenarios. Summary of the invention

[0004] The purpose of the present invention is to provide a method for predicting the probability of a UAV's line-of-sight path to a ship in an ocean scene, which comprehensively considers the characteristics of the ocean environment, the movement of the UAV and the ship, and the influence of the UAV's flight altitude on signal transmission, thereby improving the accuracy of the prediction.

[0005] In order to achieve the above technical objectives, the technical solution adopted by the present invention is:

[0006] A method for predicting the probability of a UAV-to-ship line-of-sight path in an ocean scene, the method comprising the following steps:

[0007] Step A: Set parameters according to the actual environment, including sea surface wind height h, friction speed v * , latitude ξ, geostrophic wind speed v g and the Coriolis parameter f;

[0008] Step B, according to the sea surface wind height h, friction speed v * , latitude ξ, geostrophic wind speed v gand Coriolis parameter f, calculate the ocean scene wind speed v(h);

[0009] Step C, based on the obtained wind speed v(h), calculate the significant wave height H under the current environment s , and according to the significant wave height H s Look up the table to obtain the corresponding sea conditions;

[0010] Step D, set the speed v of the drone and the ship U and v B , set the flight altitude h of the drone U , under the corresponding sea conditions, according to the speed v of the UAV and the ship U and v B 、The flight altitude of the drone h U Look up the table to obtain the corresponding ocean sub-scene;

[0011] Step E: Obtain the corresponding parameter D in the current environment by looking up the table based on the ocean sub-scene m , D d and D b The value of D m is the breakpoint distance parameter adapted to the marine environment, D d is the attenuation parameter of the marine environment, D b is the balance parameter;

[0012] Step F, input the horizontal distance d between the drone and the ship TR , combined with parameter D m , D d and D b The value of LoS probability P is calculated LoS , evaluate the LoS probability P LoS The rationality of LoS <0.3, return to step D, check and adjust the drone and ship parameters, and recalculate P LoS If P LoS ≥0.3, output the final P LoS value.

[0013] Step B further comprises the following steps:

[0014] Calculate the Coriolis parameter f as:

[0015] f=2ω E sinξ

[0016] Among them, ω E is the angular velocity of the Earth's rotation, about 7.292×10 -5 rad / s, ξ is the latitude; the geostrophic wind speed is:

[0017]

[0018] where ρ is the air density, is the pressure gradient force perpendicular to the isobars;

[0019] Coriolis parameter f and geostrophic wind speed v g Substituting the following formula, we get the wind speed at sea level h:

[0020]

[0021] Among them, v * is the friction speed.

[0022] Step C further comprises the following steps:

[0023] The Pierson-Moskowitz wave spectrum under the current wind speed v is:

[0024]

[0025] Among them, α = 0.0081, β = 0.74, ω is the wave angular velocity, and g is the gravitational acceleration;

[0026] The significant wave height is estimated by the zero-order moment of the wave spectrum:

[0027]

[0028] According to the significant wave height H s The size of the wave can be checked in the table to obtain the corresponding sea conditions; according to the significant wave height H s In order of arrival from small to large, sea conditions are divided into four types: light waves, rough waves, strong waves and huge waves.

[0029] Furthermore, 0<H s ≤2m corresponds to slight waves, 2m<H s ≤6m corresponds to rough waves, 6m<H s ≤8m corresponds to strong waves, H s >8m corresponds to huge waves.

[0030] Furthermore, in step C, 12 ocean sub-scenes are obtained by combining different value ranges of significant wave height, drone altitude, drone speed, and ship speed.

[0031] Step E further comprises:

[0032] A machine learning model that couples a dual-channel convolutional neural network with a spider monkey optimization algorithm is used to learn the motion characteristics of drones and ships in various sea conditions, optimize the parameter settings in the LoS probability prediction model, and optimize the parameter D in different ocean sub-scenarios. m , D d and Db Improve the value of .

[0033] Further, in step F, the LoS probability P is calculated using the following formula: LoS :

[0034]

[0035] Where, d TR The horizontal distance between the drone and the ship entered by the user.

[0036] Compared with the prior art, the present invention has the following beneficial effects:

[0037] First, the ocean scene UAV-to-ship line-of-sight path probability prediction method of the present invention comprehensively considers the characteristics of the ocean environment, the movement of the UAV and the ship, and the influence of the UAV's flight altitude on signal transmission, thereby improving the accuracy of the prediction.

[0038] Second, the ocean scene UAV to ship line-of-sight path probability prediction method of the present invention divides the sea surface scene into 12 typical scenes and gives suitable parameter values. This division not only improves the universality of the prediction method, but also simplifies the user's operation. The user can quickly set parameters and make predictions according to the actual environment, thereby achieving rapid and accurate evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 A schematic diagram of a scene of UAV-to-sea communication of the present invention;

[0040] Figure 2 This is a flow chart of the method for predicting the probability of the line-of-sight path of a UAV in an ocean scene of the present invention;

[0041] Figure 3 The line-of-sight path probability under 12 scenarios given by the present invention varies with the horizontal distance d between the UAV and the ship. TR Schematic diagram of the changing curve. DETAILED DESCRIPTION

[0042] The embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings.

[0043] See also Figure 2 The present invention discloses a method for predicting the probability of a UAV-to-ship line-of-sight path in an ocean scene, and the method comprises the following steps:

[0044] Step 1: Set parameters according to the actual environment, including sea surface wind height h, friction speed v * , latitude ξ, geostrophic wind speed v g and the Coriolis parameter f;

[0045] Step 2: According to the sea surface wind height h and friction speed v * , latitude ξ, geostrophic wind speed v g and Coriolis parameter f, calculate the ocean scene wind speed v(h);

[0046] Step 3: Calculate the significant wave height H under the current environment based on the obtained wind speed v(h) s , and according to the significant wave height H s Look up the table to obtain the corresponding sea conditions;

[0047] Step 4: Set the speed v of the drone and the ship U and v B , set the flight altitude h of the drone U , under the corresponding sea conditions, according to the speed v of the UAV and the ship U and v B 、The flight altitude of the drone h U Look up the table to obtain the corresponding ocean sub-scene;

[0048] Step 5: Obtain the corresponding parameter D in the current environment by looking up the table based on the ocean sub-scene m , D d and D b The value of D m is the breakpoint distance parameter adapted to the marine environment, D d is the attenuation parameter of the marine environment, D b is the balance parameter;

[0049] Step 6: Enter the horizontal distance d between the drone and the ship TR , combined with parameter D m , D d and D b The value of LoS probability P is calculated LoS , evaluate the LoS probability P LoS The rationality of LoS <0.3, return to step D, check and adjust the drone and ship parameters, and recalculate P LoS If P LoS ≥0.3, output the final P LoS value.

[0050] The specific process of step 2 is as follows. First, the Coriolis parameter is calculated as:

[0051] f=2ω E sinξ

[0052] Among them, ω E is the angular velocity of the Earth's rotation, about 7.292×10 -5 rad / s, ξ is the latitude. The geostrophic wind speed is:

[0053]

[0054] Where ρ is the air density, which is generally about 1.225 kg / m 3 , It is the pressure gradient force in the direction perpendicular to the isobars, and its value is shown in Table 1.

[0055] Table 1 Empirical values ​​of pressure gradient force changing with latitude

[0056]

[0057] Coriolis parameter f and geostrophic wind speed v g Substituting into the following formula, we can get the wind speed at sea level h:

[0058]

[0059] Among them, v * Usually 0.2m / s~0.6m / s is taken. This patent recommends taking h=19.5m as the benchmark and selecting 25m / s as the evaluation threshold to determine whether the next operation can be performed.

[0060] Step 3: First, get the Pierson-Moskowitz wave spectrum under the current wind speed:

[0061]

[0062] Among them, α = 0.0081, β = 0.74, ω is the wave angular velocity. Then, the significant wave height is estimated by the zero-order moment of the wave spectrum:

[0063]

[0064] According to the significant wave height H s The size of , select the corresponding sea state from Table 2.

[0065] Table 2 Typical sea conditions

[0066] Sea condition A Slight waves Sea state B rough waves Sea Condition C Strong Waves Sea state D huge waves <![CDATA[0<H s ≤2 m]]> <![CDATA[2m<H s ≤6m]]> <![CDATA[6m<H s ≤8m]]> <![CDATA[H s >8m]]>

[0067] In step 4, the user sets the speed v of the drone and the ship. U and v B , set the flight altitude h of the drone U .h U ≤150m is low altitude, 150m <h U ≤350m is medium altitude, h U >350m is considered high altitude.

[0068] According to environmental factors, the motion of the drone and the ship itself, all conditions are combined and divided into 12 representative ocean sub-scenarios. The corresponding parameter thresholds for each sub-scenario are shown in Table 3. The user determines the corresponding ocean sub-scenario based on the input wave parameters, drone height, and drone and ship speeds.

[0069] Table 3 12 ocean sub-scenes

[0070]

[0071]

[0072] In step 5, the user obtains the corresponding D from Table 4 according to the typical scenario selected above. m , D d and D b The value of m is the breakpoint distance parameter adapted to the marine environment, D d is the attenuation parameter of the marine environment, D b is a balance parameter.

[0073] In order to optimize the above three parameter values, the present invention adopts a machine learning model that couples the Dual Channel Convolutional Neural Network (DCCN) with the Spider Monkey Optimization (SMO) algorithm. By learning the motion characteristics of drones and ships under various sea conditions, the parameter settings in the LoS probability prediction model are optimized.

[0074] Table 4 Improved parameter values ​​in different sub-scenarios

[0075] Scenario <![CDATA[D m ]]> <![CDATA[D d ]]> <![CDATA[D b ]]> A1 20.00 500.00 0.30 A2 25.00 550.00 0.35 A3 30.00 600.00 0.40 B1 35.00 650.00 0.45 B2 39.40 616.50 0.50 B3 30.44 646.37 0.53 C1 35.00 628.44 0.52 C2 40.00 608.87 0.51 C3 45.00 589.04 0.51 D1 50.00 560.27 0.55 D2 55.00 600.00 0.60 D3 60.00 650.00 0.65

[0076] In step 6, the user enters the horizontal distance d between the drone and the ship. TR , according to the parameter values ​​in the above table, the calculation method of LoS probability is:

[0077]

[0078] Finally, judge P LoS Does it satisfy P LoS ≥0.3. Higher P LoS The value means that the drone and the ship can provide a more stable and high-quality communication experience. LoS When the value drops below 0.3, it indicates that under the current environment and technical parameter settings, the probability of the existence of a line-of-sight path is low, and the signal quality is significantly reduced due to multipath interference, signal attenuation and other factors. LoSWhen P < 0.3, it is necessary to re-evaluate and adjust the model parameters to adapt to the current environmental conditions, return to step 4 to check the input parameters and recalculate. LoS ≥0.3 indicates that the calculation process is correct and the final LoS probability is output.

[0079] Examples

[0080] The technical solution of the present invention is described again below through a specific implementation case, and this implementation case includes the following steps:

[0081] Step 1: The user sets the parameters according to the real environment data: sea surface wind height h, friction speed v * , latitude ξ, geostrophic wind speed v g , Coriolis parameter f. Let rad, according to

[0082] f=2ω E sinξ,

[0083] Calculate f = 7.728 × 10 -5 s -1 , where ω E is the angular velocity of the Earth's rotation, about 7.292×10 -5 rad / s. ξ=32° Located in the subtropical latitude, refer to Table 1 to obtain the pressure gradient force hPa / 100km, ρ is the air density, generally about 1.225kg / m 3 .according to

[0084]

[0085] Calculate the geostrophic wind speed v g =10.6m / s.

[0086] In ocean scenes, usually v * The range is 0.2m / s~0.6m / s, here we take v * =0.38m / s, h=19.5m.

[0087] Step 2: Based on the above input parameters: sea surface wind height h = 19.5m, friction speed v * =0.38m / s, latitude ξ=32°, geostrophic wind speed v g =10.6m / s, Coriolis parameter f = 7.728×10 -5 s -1 ,according to

[0088]

[0089] The calculated wind speed in the ocean scene is v(h)=4.86+5.71i, and the wind speed is |v(h)|=7.5m / s, satisfying |v(h)|≤25m / s. The drone can communicate normally, so the probability of entering the ocean LoS can be predicted in this scenario.

[0090] Step 3: Substitute the wind speed into the Pierson-Moskowitz wave spectrum:

[0091]

[0092] Among them, α = 0.0081, β = 0.74, ω is the wave angular velocity, and g is the gravitational acceleration. The significant wave height is estimated by the zero-order moment of the wave spectrum:

[0093]

[0094] Find H s =2.51m. By comparing with Table 2, it can be determined that the sea condition is scenario B.

[0095] Step 4: Set the speed of the drone to v U =15m / s,v B =8m / s, drone height h U = 100m. According to the wave parameters, drone height, and the speed of drone and ship input in step 4 and step 5, the typical scenario is determined. By comparing with Table 3, it can be determined that the scenario is B1 scenario.

[0096] Step 5: Refer to Table 4 and obtain the value of the D parameter in scenario B1: D m =35.00, D d =650, D b =0.45.

[0097] Step 6: Enter the horizontal distance d between the drone and the ship TR =200m, the above D m , D d and D b Substitute the parameter values ​​into the LoS probability formula:

[0098]

[0099] Right now:

[0100]

[0101] Satisfy P LoS ≥0.3, output the result.

[0102] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code. The scheme in the embodiments of the present application can be implemented in various computer languages, for example, object-oriented programming language Java and literal scripting language JavaScript, etc.

[0103] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0104] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0105] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0106] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0107] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for predicting the probability of a UAV’s line-of-sight path to a ship in an ocean scene. It is characterized in that The probability prediction method comprises the following steps: Step A: Set parameters according to the actual environment, including sea surface wind height h, friction speed v * , latitude ξ, geostrophic wind speed v g and the Coriolis parameter f; Step B, according to the sea surface wind height h, friction speed v * , latitude ξ, geostrophic wind speed v g and Coriolis parameter f, calculate the ocean scene wind speed v(h); Step C: Calculate the significant wave height H under the current environment based on the acquired wind speed v(h) s , and according to the significant wave height H s Look up the table to obtain the corresponding sea conditions; Step D, set the speed v of the drone and the ship U and v B , set the flight altitude h of the drone U , under the corresponding sea conditions, according to the speed v of the UAV and the ship U and v B 、The flight altitude of the drone h U Look up the table to obtain the corresponding ocean sub-scene; Step E: Obtain the corresponding parameter D in the current environment by looking up the table based on the ocean sub-scene m , D d and D b The value of D m is the breakpoint distance parameter adapted to the marine environment, D d is the attenuation parameter of the marine environment, D b is the balance parameter; Step F, input the horizontal distance d between the drone and the ship TR , combined with parameter D m , D d and D b The value of LoS probability P is calculated LoS , evaluate the LoS probability P LoS The rationality of LoS <0.3, return to step D, check and adjust the drone and ship parameters, and recalculate P LoS If P LoS ≥0.3, output the final P LoS value.

2. The method for predicting the probability of the line-of-sight path of a UAV in an ocean scene to a ship according to claim 1, It is characterized in that Step B further comprises the following steps: Calculate the Coriolis parameter f as: f=2ω E sinξ Among them, ω E is the angular velocity of the Earth's rotation, about 7.292×10 -5 rad / s, ξ is the latitude; the geostrophic wind speed is: where ρ is the air density, is the pressure gradient force perpendicular to the isobars; Coriolis parameter f and geostrophic wind speed v g Substituting the following formula, we get the wind speed at sea level h: Among them, v * is the friction speed.

3. The method for predicting the probability of the line-of-sight path of a UAV in an ocean scene to a ship according to claim 1, It is characterized in that Step C further comprises the following steps: The Pierson-Moskowitz wave spectrum under the current wind speed v is: Among them, α = 0.0081, β = 0.74, ω is the wave angular velocity, and g is the gravitational acceleration; The significant wave height is estimated by the zero-order moment of the wave spectrum: According to the significant wave height H s The size of the wave can be checked in the table to obtain the corresponding sea conditions; according to the significant wave height H s In order of arrival from small to large, sea conditions are divided into four types: light waves, rough waves, strong waves and huge waves.

4. The method for predicting the probability of the line-of-sight path of a UAV in an ocean scene to a ship according to claim 3, It is characterized in that 0<H s ≤2m corresponds to slight waves, 2m<H s ≤6m corresponds to rough waves, 6m<H s ≤8m corresponds to strong waves, H s >8m corresponds to huge waves.

5. The method for predicting the probability of the line-of-sight path of a UAV in an ocean scene to a ship according to claim 1, It is characterized in that In step C, 12 ocean sub-scenarios are obtained by combining different value ranges of significant wave height, drone altitude, drone speed, and ship speed.

6. The method for predicting the probability of the line-of-sight path of a UAV in an ocean scene to a ship according to claim 1, It is characterized in that Step E further comprises: A machine learning model that couples a dual-channel convolutional neural network with a spider monkey optimization algorithm is used to learn the motion characteristics of drones and ships in various sea conditions, optimize the parameter settings in the LoS probability prediction model, and optimize the parameter D in different ocean sub-scenarios. m , D d and D b Improve the value of .

7. The method for predicting the probability of a UAV-to-ship line-of-sight path in an ocean scene according to claim 1, It is characterized in that In step F, the LoS probability P is calculated using the following formula: LoS : Where, d TR The horizontal distance between the drone and the ship entered by the user.

Images