Mine operation restoration method based on unmanned aerial vehicle and related device

Abstract

The invention provides a mine operation repairing method based on an unmanned aerial vehicle and a related device, and relates to the technical field of mine repairing. Based on factors such as a topographic relief factor, a wind field turbulence intensity factor, an unmanned aerial vehicle interference factor, a throwing angle, a wind direction angle, throwing delay and the like, firstly, an initial drop point of seed settlement is given through a physical model, and deviation caused by complex wind field turbulence, unmanned aerial vehicle interference, irregular topography and the like is corrected in combination with a machine learning algorithm; according to the method, the nonlinear and interaction problems in an actual scene are considered, a quadratic term and a small number of physical meaning interaction items are adopted for feature mapping, correction is conducted through a physical model in combination with a machine learning algorithm, and accurate prediction of the seed settlement drop point can be better achieved.

Description

Technical Field

[0001] This application relates to the field of mine restoration technology, and in particular to a mine restoration method and related apparatus based on unmanned aerial vehicles (UAVs). Background Technology

[0002] With increasing global awareness of ecological and environmental protection, mine ecological restoration has become an important component of sustainable development. Traditional artificial vegetation restoration methods suffer from low efficiency, high costs, and significant safety risks when facing complex mine terrain. Drone precision seeding technology offers a new solution for mine vegetation restoration. However, the complexity of the mining environment poses a significant challenge to the accuracy of drone seeding.

[0003] Mining terrain typically features complex characteristics such as steep slopes, sinkholes, and canyons. These topographical features significantly alter local wind field distribution, creating complex airflow phenomena such as turbulence and eddies. Simultaneously, environmental parameters in the mining environment, such as temperature gradients, air pressure changes, and humidity distribution, also affect seed settling trajectories. Traditional drone seeding systems primarily rely on simplified aerodynamic models, considering only an idealized balance of gravity, buoyancy, and air resistance, making it difficult to accurately predict the actual settling behavior of seeds in complex environments.

[0004] Traditional methods neglect key influencing factors unique to mines, such as topographic relief, turbulence, and drone wake interference. Furthermore, they lack detailed modeling of different seed characteristics (density, shape, moisture content, etc.), leading to significant discrepancies between predictions and actual conditions. Secondly, existing methods cannot effectively handle the disturbance effects of complex mine terrain on wind fields; wind field modeling is overly simplistic and lacks real-time perception and adaptive adjustment capabilities for dynamic environmental changes. Summary of the Invention

[0005] In order to achieve accurate prediction of seed settling point during mine restoration, this application provides a mine restoration method and related device based on unmanned aerial vehicles (UAVs).

[0006] Firstly, the mine repair method based on unmanned aerial vehicles (UAVs) provided in this application adopts the following technical solution: A method for mine restoration based on unmanned aerial vehicles (UAVs), comprising: The seed distribution area is determined based on the planting needs of the mine vegetation, and the take-off point, target distribution point and flight trajectory of the drone are determined based on the received distribution task. A material aerodynamic model is constructed, and a settling velocity prediction and correction are performed based on a support vector regression algorithm with physical constraints. Based on topographic relief factor, wind field turbulence intensity factor, UAV interference factor, release angle, wind direction angle and release delay factor, combined with the predicted settling velocity, the seed release settling point can be predicted. Optimal flight paths are planned based on the drop-in range of each region; The step of predicting the seed placement and settling point based on topographic relief factor, wind turbulence intensity factor, UAV interference factor, placement angle, wind direction angle, and placement delay factor, combined with the predicted settling velocity, includes: Calculate the initial landing point using a physical model; The Ridge regression algorithm is used to intelligently correct biases caused by complex environments. Nonlinearity and interaction effects are addressed by introducing eigenmaps with quadratic terms and physical meaning interaction terms. The final predicted landing point is obtained by combining the physical model's predicted landing point with the machine learning correction.

[0007] Optionally, the step of constructing a material aerodynamic model and correcting the settling velocity prediction based on a support vector regression algorithm with physical constraints includes: A preliminary estimate of the settling velocity was obtained based on a traditional aerodynamic model; Construct a multidimensional feature vector containing seed characteristic parameters, environmental parameters, and mine-specific parameters; The settling velocity prediction model was modified using a support vector regression algorithm with physical constraints. The seed characteristic parameters mentioned above include seed density, equivalent diameter, sphericity, and moisture content; The environmental parameters include air density, aerodynamic viscosity, ambient temperature, atmospheric pressure, specific humidity, and average ambient wind speed. The specific parameters for the mine include topographic relief factor, wind field turbulence intensity factor, and UAV interference factor.

[0008] Optionally, the terrain undulation factor is calculated in the following manner: Calculate the local terrain slope angle and curvature based on UAV lidar point cloud data; The terrain undulation factor is calculated based on the slope angle and curvature. The calculation formula is as follows: Where θ(x,y) is the slope angle and κ(x,y) is the curvature. , These are empirical weighting coefficients.

[0009] Optionally, the wind field turbulence intensity factor is obtained in the following way: Local wind speed time series were obtained by using a drone equipped with a wind speed sensor. Wind field simulation under complex terrain based on CFD simulation results; The turbulence intensity factor was calculated by combining data from the on-site meteorological monitoring station.

[0010] Optionally, the UAV interference factor is calculated in the following way: The UAV interference factor is constructed based on flight altitude, flight speed, and propeller parameters; The calculation formula is: ; in The propeller downwash speed, The drop height is ε, which is a small constant to avoid a denominator of 0.

[0011] Optionally, the step of planning the optimal flight path based on the deployable range of each region includes: Based on the drone's deployment angle θ and azimuth angle γ, determine the range within which the drone can achieve precise deployment in each area; Based on the deployment range of multiple areas, a path optimization algorithm is used to plan the optimal flight path for drone planting and restoration. It can sense changes in the dynamic environment of the mine in real time and adaptively adjust the flight path and seeding strategy.

[0012] Secondly, this application provides a mine operation repair system based on unmanned aerial vehicles (UAVs), comprising: The area determination module is used to determine the seed distribution area based on the planting needs of mine vegetation, and to determine the take-off point, target distribution point and flight trajectory of the UAV based on the received distribution task. The correction module is used to construct a material aerodynamic model and correct the sedimentation velocity prediction based on a support vector regression algorithm with physical constraints. The prediction module is used to predict the seed placement point based on topographic relief factor, wind field turbulence intensity factor, UAV interference factor, placement angle, wind direction angle and placement delay factor, combined with the predicted settling velocity. The output module is used to plan the optimal flight path based on the drop-in range of each region.

[0013] Thirdly, this application provides a computer device, the device comprising: a memory and a processor, wherein the processor, when executing computer instructions stored in the memory, performs the method described above.

[0014] Fourthly, this application provides a computer-readable storage medium including instructions that, when executed on a computer, cause the computer to perform the method described above.

[0015] In summary, this application, based on factors such as terrain undulation factor, wind field turbulence intensity factor, UAV interference factor, deployment angle, wind direction angle, and deployment delay, first uses a physical model to give the initial landing point of the seed. Then, it combines machine learning algorithms to correct the deviations caused by complex wind field turbulence, UAV interference, and irregular terrain. It also considers the nonlinearity and interaction problems in the actual scenario, and uses quadratic terms and a small number of physically meaningful interaction terms for feature mapping. By combining the physical model with machine learning algorithms for correction, it can better achieve accurate prediction of the seed landing point. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the computer device structure of the hardware operating environment involved in the embodiments of this application; Figure 2 This is a flowchart illustrating the first embodiment of the mine repair method based on unmanned aerial vehicles (UAVs) of this application; Figure 3 This is a structural block diagram of the first embodiment of the mine operation repair system based on unmanned aerial vehicles (UAVs) of this application. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0018] Reference Figure 1 , Figure 1 This is a schematic diagram of the computer device structure of the hardware operating environment involved in the embodiments of this application.

[0019] like Figure 1As shown, the computer device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen or an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wireless-Fidelity (Wi-Fi) interface). The memory 1005 may be high-speed random access memory (RAM) or stable non-volatile memory (NVM), such as a disk drive. The memory 1005 may also optionally be a storage device independent of the aforementioned processor 1001.

[0020] Those skilled in the art will understand that Figure 1 The structure shown does not constitute a limitation on the computer device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0021] like Figure 1 As shown, the memory 1005, which serves as a storage medium, may include an operating system, a network communication module, a user interface module, and a mine operation repair program based on unmanned aerial vehicles (UAVs).

[0022] exist Figure 1 In the computer device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in this application can be set in the computer device, and the computer device calls the UAV-based mine operation repair program stored in the memory 1005 through the processor 1001, and executes the UAV-based mine operation repair method provided in the embodiment of this application.

[0023] This application provides a method for mine repair based on unmanned aerial vehicles (UAVs), referring to... Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of the mine operation repair method based on unmanned aerial vehicles (UAVs) of this application.

[0024] In this embodiment, the mine repair method based on drones includes the following steps: Step S10: Determine the seed delivery area based on the planting needs of the mine vegetation, and determine the take-off point, target delivery point and flight trajectory of the UAV based on the received delivery task.

[0025] It should be noted that the core technical approach in this embodiment is as follows: 1. Mission planning: Determine the drop area, takeoff point, target point, and flight path; 2. Settlement velocity prediction: An aerodynamic physical model is established, and a physical constraint support vector regression algorithm (PR-SVG) is used to correct the settlement velocity prediction. 3. Landing Point Prediction: Based on topographic relief factors, wind turbulence intensity factors, UAV interference factors, deployment angle, wind direction angle, and deployment delay factors, combined with the settlement velocity predicted in the previous stage, the landing point of seed deployment is predicted. Specifically, a physical model is used to calculate the initial landing point, and Ridge regression is used to correct for deviations caused by complex environments. 4. Route optimization: Plan the optimal flight path based on the available deployment range of each region.

[0026] Step S20: Construct a material aerodynamic model and use a support vector regression algorithm based on physical constraints to predict and correct the settling velocity.

[0027] It should be noted that the steps of constructing a material aerodynamic model and correcting the settling velocity prediction based on a physically constrained support vector regression algorithm include: obtaining a preliminary settling velocity estimate based on a traditional aerodynamic model; constructing a multidimensional feature vector containing seed characteristic parameters, environmental parameters, and mine-specific parameters; and correcting the settling velocity prediction model using a physically constrained support vector regression algorithm. The seed characteristic parameters include seed density, equivalent diameter, sphericity, and moisture content; the environmental parameters include air density, aerodynamic viscosity, ambient temperature, atmospheric pressure, specific humidity, and average ambient wind speed; and the mine-specific parameters include topographic relief factor, wind field turbulence intensity factor, and UAV interference factor.

[0028] It should be noted that the preliminary settlement velocity estimate is derived from the traditional aerodynamic model to improve the accuracy of subsequent predictions.

[0029] The settling velocity of seeds as they fall through the air. It is mainly determined by three forces: gravity, buoyancy, and air resistance. At the terminal velocity (i.e., when the settling velocity stabilizes), these three forces are in equilibrium. in, , , These are gravity, buoyancy, and air resistance, respectively.

[0030] The formula for gravity is: The formula for buoyancy is: in, For seed quality; This represents the seed volume; Seed density; air density; This is the acceleration due to gravity.

[0031] The formula for air resistance is: in, The drag coefficient is related to the seed shape and Reynolds number; The projected area of ​​the seed in the direction of airflow; This represents the settling velocity.

[0032] Therefore, when the terminal settling velocity is reached At that time, the forces are balanced as follows: The settlement velocity was obtained as follows: Due to the complex nonlinear environment and varying seed characteristics in mines, physical models struggle to accurately predict settlement velocity. By constructing a physically constrained support vector regression algorithm (PR-SVG), the settlement velocity prediction model is modified to better adapt to actual conditions and improve prediction accuracy.

[0033] The input feature vector is: in, These are seed-related parameters, namely seed density, seed equivalent diameter, seed sphericity, and seed moisture content; These are environmental parameters, namely air density, aerodynamic viscosity, ambient temperature, atmospheric pressure, specific humidity, and average ambient wind speed. These are specific parameters for the mine, namely, topographic relief factor, wind field turbulence intensity factor, and UAV interference factor.

[0034] The terrain undulation factor, calculated from local slope and curvature, characterizes the impact of complex mine terrain on wind field disturbance. Mines typically have complex terrain (steep slopes, subsidence pits, etc.), and these undulations alter the distribution of the local wind field. Wind accelerates on slopes and forms eddies in depressions, thus affecting the sedimentation trajectory of seeds. Therefore, the local terrain slope angle is first calculated based on UAV lidar point clouds: in, It is a function of terrain height. Therefore, the terrain relief factor can be defined: in, The slope angle is the angle of inclination; the steeper the slope, the greater the wind speed disturbance. The curvature represents a positive value indicating a convexity and a negative value indicating a concaveness, reflecting the dispersion / convergence of airflow. , The empirical weights can be calibrated through wind tunnel experiments or numerical simulations.

[0035] In mining canyons or slope areas, airflow is often accompanied by turbulence, and this pulsation causes fluctuations in the actual settling velocity of seeds. (Turbulence intensity factor) Turbulence intensity measures the ratio of localized wind speed fluctuations to average wind speed, reflecting air instability. It is defined as: in, Let be the instantaneous wind speed at the i-th time point; Average wind speed; The number of sampling points is used in practical applications. Data sources include local wind speed time series obtained by wind speed sensors mounted on UAVs, CFD simulation results (wind field simulation under complex terrain), and on-site meteorological monitoring stations.

[0036] The drone's propellers generate a wake effect, which alters the airflow environment immediately after seed release, affecting initial settling conditions. A drone interference factor is constructed considering flight altitude, flight speed, and propeller parameters. in The propeller downwash speed, For the deployment height, ε is a small constant to avoid a denominator of 0, which can be represented by an empirical model: in, This represents the total thrust of the propeller blades; Where is the blade radius, The rotor disk area; This refers to air density.

[0037] Based on the above feature vectors, SVR is used to predict the correction factor: in, As a correction factor; , For Lagrange multipliers; For kernel functions; This is a bias term.

[0038] The final settlement velocity is obtained: .

[0039] Step S30: Based on the terrain undulation factor, wind field turbulence intensity factor, UAV interference factor, release angle, wind direction angle and release delay factor, combined with the predicted settling velocity, the seed release settling point is predicted.

[0040] In practice, the seed placement point is predicted by combining factors such as terrain undulation, wind turbulence intensity, drone interference, placement angle, wind direction angle, and placement delay with the settlement velocity predicted in the previous stage. (This part provides an initial landing point through a physical model, and uses machine learning algorithms to correct deviations caused by complex wind turbulence, drone interference, and irregular terrain.)

[0041] The seed settling trajectory is determined by particle kinematics and is influenced by factors such as terrain undulation, wind turbulence intensity, drone interference, release angle, and release delay. Therefore, after considering factors such as wind speed, terrain influence, and drone interference, the basic physical model prediction formula is as follows: in, The seed landing location predicted by the physical model. Its calculation formula; This refers to the estimated landing time. For a three-dimensional wind speed field, These are the three wind speed components of the wind speed field; The angle from which the drone is deployed; The wind direction angle is the angle between the direction of seed release and the direction of the relative incoming flow. The release delay is the time delay between the drone executing the release command and the actual release of the seeds. The remaining available features predicted by the physical model work together to calculate the initial landing location of the seed.

[0042] At the landing point predicted by the physical model Based on this, a regularized linear model (Ridge regression) is used to incorporate terrain undulation factors, wind field turbulence intensity factors, UAV interference factors, deployment angle, and deployment delay factors into the machine learning-based corrected prediction. .

[0043] The basic input for the Ridge regression model prediction is: in, The angle of projection is relative to the horizontal downward direction; The wind direction angle.

[0044] To balance nonlinearity and interaction, a quadratic term plus a small number of physically meaningful interaction terms are used for feature mapping: Where 1 represents the bias; By controlling for wind and direction factors, this method encodes the wind magnitude and direction information together into features, enabling the model to not only perceive how strong the wind is, but also which way it is blowing. By combining the topographic relief factor with the wind direction angle, we can represent how the terrain enhances or weakens the effect of the wind along the wind direction. This indicates the coupling effect between the downwash airflow and the delivery angle. If the delivery angle is exactly aligned with the downwash direction, the downwash effect is the greatest. If the angles are different, the downwash effect is weakened.

[0045] It should be noted that the wind field turbulence intensity factor is obtained in the following ways: local wind speed time series are obtained by using a wind speed sensor mounted on a UAV; wind field simulation under complex terrain is performed based on CFD simulation results; and turbulence intensity factor is calculated by combining data from on-site meteorological monitoring stations.

[0046] In the feature space after the quadratic and interactive expansion, the correction amount for Ridge regression prediction is: in, The expanded feature vector (containing linear terms, quadratic terms, and some physical interaction terms); This is the regression weight matrix.

[0047] For the i-th experiment, the physical model predicts the landing point as follows: The actual observed landing point was .

[0048] The correction label is: At the same time, each sample corresponds to a set of input features. This constitutes a matrix. The true correction vectors of all N samples were collected as supervision signals for Ridge regression.

[0049] To avoid overfitting, an L2 regularization term is introduced, and the objective function is: in, >0 represents the regularization coefficient; For the Frobenius norm, take all The sum of the squared elements is then taken as the total L2 weight penalty.

[0050] Ridge regression has an analytical solution, and the weight matrix can be written as: in, ; ; It is the identity matrix used to implement regularization for Ridge regression.

[0051] Based on the physical impact point, the final predicted impact point is: .

[0052] It should be noted that the steps for predicting the seed placement and settling point based on terrain undulation factor, wind field turbulence intensity factor, UAV interference factor, placement angle, wind direction angle, and placement delay factor, combined with the predicted settling velocity, include: calculating the initial landing point position using a physical model; intelligently correcting deviations caused by complex environments using the Ridge regression algorithm; handling nonlinearity and interaction effects by introducing a feature mapping of quadratic terms and physical meaning interaction terms; and obtaining the final predicted landing point by combining the landing point predicted by the physical model and the machine learning correction amount.

[0053] Step S40: Plan the optimal flight path based on the drop range of each area.

[0054] It is understood that the step of planning the optimal flight path based on the delivery range of each area includes: determining the range in which the drone can accurately deliver the drone in each area based on the drone's delivery angle θ and direction angle γ; planning the optimal flight path for drone planting and restoration using a path optimization algorithm based on the delivery range of multiple areas; and adaptively adjusting the flight path and seeding strategy based on real-time sensing of dynamic environmental changes in the mine.

[0055] It should be noted that, in this embodiment, the following was ultimately achieved through the above methods: 1. The aerodynamic model output is used as the input and constraint for SVR to avoid the prediction results from going astray. At the same time, specific features of the mine (terrain undulation, turbulence intensity, and drone wake interference) are introduced to improve the model's adaptability to complex environments. This upgrades the prediction model from "pure machine learning" to a prediction method of "physical constraints + scene enhancement + adaptive weighting", which is significantly innovative.

[0056] 2. In the seed settling location prediction section, this proposal, based on factors such as terrain undulation factor, wind field turbulence intensity factor, UAV interference factor, release angle, wind direction angle, and release delay, first uses a physical model to give the preliminary seed settling location. Then, it combines machine learning algorithms to correct deviations caused by complex wind field turbulence, UAV interference, irregular terrain, etc., and considers nonlinearity and interaction issues in the actual scenario. It uses quadratic terms plus a small number of physically meaningful interaction terms for feature mapping. By combining the physical model with machine learning algorithms for correction, it can better achieve accurate prediction of seed settling location.

[0057] This embodiment, based on factors such as terrain undulation factor, wind field turbulence intensity factor, UAV interference factor, deployment angle, wind direction angle, and deployment delay, first uses a physical model to give the initial landing point of the seed. Then, it combines machine learning algorithms to correct the deviations caused by complex wind field turbulence, UAV interference, irregular terrain, etc., and considers the nonlinearity and interaction problems in the actual scenario. It uses quadratic terms and a small number of physically meaningful interaction terms for feature mapping. By combining the physical model with machine learning algorithms for correction, it can better achieve accurate prediction of the seed landing point.

[0058] Furthermore, embodiments of this application also propose a computer-readable storage medium storing a program for mine operation repair based on unmanned aerial vehicles (UAVs). When the UAV-based mine operation repair program is executed by a processor, it implements the steps of the UAV-based mine operation repair method described above.

[0059] Reference Figure 3 , Figure 3 This is a structural block diagram of the first embodiment of the mine operation repair system based on unmanned aerial vehicles (UAVs) of this application.

[0060] like Figure 3 As shown, the UAV-based mine operation repair system proposed in this application includes: The area determination module 10 is used to determine the seed delivery area based on the planting needs of mine vegetation, and to determine the take-off point, target delivery point and flight trajectory of the UAV based on the received delivery task. Correction module 20 is used to construct a material aerodynamic model and correct the settling velocity prediction based on a support vector regression algorithm with physical constraints. The prediction module 30 is used to predict the seed placement point based on topographic relief factor, wind field turbulence intensity factor, UAV interference factor, placement angle, wind direction angle and placement delay factor, combined with the predicted settling velocity. Output module 40 is used to plan the optimal flight path based on the drop range of each region.

[0061] It should be understood that the above are merely illustrative examples and do not constitute any limitation on the technical solution of this application. In specific applications, those skilled in the art can make settings as needed, and this application does not impose any restrictions on this.

[0062] This embodiment, based on factors such as terrain undulation factor, wind field turbulence intensity factor, UAV interference factor, deployment angle, wind direction angle, and deployment delay, first uses a physical model to give the initial landing point of the seed. Then, it combines machine learning algorithms to correct the deviations caused by complex wind field turbulence, UAV interference, irregular terrain, etc., and considers the nonlinearity and interaction problems in the actual scenario. It uses quadratic terms and a small number of physically meaningful interaction terms for feature mapping. By combining the physical model with machine learning algorithms for correction, it can better achieve accurate prediction of the seed landing point.

[0063] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of this application. In practical applications, those skilled in the art can select some or all of it to achieve the purpose of this embodiment according to actual needs, and no restrictions are imposed here.

[0064] In addition, for technical details not described in detail in this embodiment, please refer to the method for mine operation repair based on UAV provided in any embodiment of this application, which will not be repeated here.

[0065] Furthermore, it should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0066] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0067] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as read-only memory (ROM) / RAM, magnetic disk, optical disk), and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods of the various embodiments of this application. The above are only preferred embodiments of this application and do not limit the patent scope of this application. All equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A method for repairing a mine operation based on a drone, characterized by, The method comprises the following steps: determining the seed drop area according to the mine vegetation planting requirements, determining the take-off point, target drop point and flight trajectory of the unmanned aerial vehicle based on the received drop task; constructing a material aerodynamic model, and correcting the settling velocity prediction based on a support vector regression algorithm with physical constraints; based on the terrain undulation factor, wind field turbulence intensity factor, unmanned aerial vehicle interference factor, drop angle, wind direction angle and drop delay factor, combined with the predicted settling velocity, the seed drop settling point is predicted; planning the optimal flight path based on the range of each region that can be dropped; wherein the step of predicting the seed drop settling point based on the terrain undulation factor, wind field turbulence intensity factor, unmanned aerial vehicle interference factor, drop angle, wind direction angle and drop delay factor, combined with the predicted settling velocity, comprises: using a physical model to calculate the preliminary drop point position; using a Ridge regression algorithm to intelligently correct the deviation caused by complex environments; processing nonlinearity and interaction effects through the introduction of quadratic terms and physical meaning interaction terms; combining the physical model to predict the drop point and the machine learning correction amount to obtain the final predicted drop point.

2. The method of claim 1, wherein, The step of constructing a material aerodynamic model and correcting the settling velocity prediction based on a support vector regression algorithm with physical constraints comprises: obtaining a preliminary settling velocity estimate based on a traditional aerodynamic model; constructing a multi-dimensional feature vector containing seed characteristic parameters, environmental parameters and mine specific parameters; correcting the settling velocity prediction model using a support vector regression algorithm with physical constraints; wherein the seed characteristic parameters include seed density, equivalent diameter, sphericity and moisture content; the environmental parameters include air density, aerodynamic viscosity, environmental temperature, atmospheric pressure, air relative humidity and environmental average wind speed; the mine specific parameters include the terrain undulation factor, the wind field turbulence intensity factor and the unmanned aerial vehicle interference factor.

3. The method of claim 2, wherein, The terrain undulation factor is calculated by: calculating the local terrain slope angle and curvature based on the unmanned aerial vehicle laser radar point cloud data; The terrain fluctuation factor is calculated according to the slope angle and the curvature, and the calculation formula is: where θ(x, y) is the slope angle, κ(x, y) is the curvature, , is an empirical weight coefficient.

4. The method of claim 2, wherein, The wind field turbulence intensity factor is obtained by: obtaining a local wind speed time series by the unmanned aerial vehicle carrying a wind speed sensor; simulating the wind field under complex terrain based on CFD simulation results; combining the data from the on-site meteorological monitoring station to calculate the turbulence intensity factor.

5. The method of claim 1, wherein, The unmanned aerial vehicle interference factor is calculated by: constructing the unmanned aerial vehicle interference factor based on the flight height, flight speed and blade parameters; The calculation formula is: ; wherein is the propeller wash speed, is the drop height, and ε is a small constant to avoid division by zero.

6. The method of claim 1, wherein, The step of planning the optimal flight path based on the range of each region that can be dropped comprises: judging the range of each region that the unmanned aerial vehicle can achieve accurate drop based on the drop angle θ and the direction angle γ of the unmanned aerial vehicle; planning the optimal flight path of the unmanned aerial vehicle planting and repairing according to the drop range of multiple regions using a path optimization algorithm; real-time sensing of mine dynamic environment changes, and self-adaptive adjustment of flight path and seeding strategy.

7. An unmanned aerial vehicle based mine operation remediation system, characterized in that, The method of claim 1 comprises: a region determination module for determining the seed drop area according to the mine vegetation planting requirements, and determining the take-off point, target drop point and flight trajectory of the unmanned aerial vehicle based on the received drop task; The correction module is configured to build a material aerodynamic model and correct the settling velocity prediction based on a support vector regression algorithm with physical constraints; The prediction module is configured to predict the seed dropping settling point based on a terrain undulation factor, a wind field turbulence intensity factor, a UAV interference factor, a dropping angle, a wind direction angle and a dropping delay factor, and in combination with the predicted settling velocity. The output module is configured to plan an optimal flight path based on the range of each region where the seeds can be dropped.

8. A computer device, comprising: The device comprises a memory and a processor, and the processor executes the method according to any one of claims 1 to 6 when running computer instructions stored in the memory.

9. A computer-readable storage medium, characterized in that, The instructions, when running on a computer, cause the computer to execute the method according to any one of claims 1 to 6.

Images