Near space unmanned aerial vehicle delivery monitoring method, device and equipment and storage medium

Abstract

The invention discloses a near space unmanned aerial vehicle delivery monitoring method, device and equipment and a storage medium, and the method comprises the steps: determining a target global environment model through local environment data collected by each sensor node, and further optimizing a predicted delivery trajectory and a predicted delivery drop point, determining an optimized delivery trajectory and an optimized delivery drop point; error analysis is carried out according to the actual drop point position, the actual putting track, the optimized putting track and the optimized putting drop point, and putting errors are determined; and adjusting the state of the unmanned aerial vehicle according to the launching error and the current flight state until the launching task in the near space is finished. In this way, the launching precision of the unmanned aerial vehicle in a near space complex environment is remarkably improved; the actual drop point position and the delivery track are monitored in real time, closed-loop control is formed in combination with error analysis and flight state feedback, the problem of delivery deviation accumulation is effectively solved, and high-precision and high-robustness autonomous delivery task execution is achieved.

Description

Technical Field

[0001] The present application relates to the field of drone technology, and in particular to a method, apparatus, device, and storage medium for monitoring the deployment of near-space drones. Background Art

[0002] Existing drone delivery technologies typically rely on preset trajectories and static environmental parameters, lacking the ability to monitor and compensate for dynamic environmental disturbances such as sudden changes in high-altitude wind fields and pressure gradients. This results in significant deviations between the actual landing point and the expected location, particularly in near-space environments. Furthermore, traditional methods lack a global environmental model based on multi-sensor data fusion, making it impossible to dynamically correct trajectory errors. Furthermore, they lack closed-loop monitoring and feedback mechanisms for the delivery process, resulting in poor drone delivery accuracy in near-space environments. Summary of the Invention

[0003] The main purpose of this application is to provide a near-space drone delivery monitoring method, device, equipment and storage medium, aiming to solve the technical problem of reduced delivery accuracy caused by insufficient real-time monitoring and inability to perform dynamic trajectory correction in a timely manner in existing drone delivery technology.

[0004] To achieve the above objectives, the present application proposes a near-space drone deployment monitoring method, which includes:

[0005] When the drone meets the delivery conditions, control the drone to perform the delivery task according to the predicted delivery trajectory and predicted delivery point;

[0006] Real-time monitoring of local environmental data collected by the drone through multiple sensor nodes during the actual deployment process, and determining a target global environmental model based on the local environmental data collected by each sensor node;

[0007] Optimizing the predicted delivery trajectory and the predicted delivery point through the target global environment model to determine the optimized delivery trajectory and the optimized delivery point;

[0008] Real-time monitoring of the actual landing point and actual delivery trajectory of the drone during the actual delivery process;

[0009] Perform error analysis based on the actual landing point, the actual delivery trajectory, the optimized delivery trajectory, and the optimized delivery landing point to determine the delivery error of the drone during the delivery process;

[0010] The state of the drone is adjusted according to the delivery error of the drone during the delivery process and the current flight state of the drone until the delivery mission in the near space is completed.

[0011] In one embodiment, when the drone meets the delivery conditions, the step of controlling the drone to perform the delivery task according to the predicted delivery trajectory and predicted delivery point includes:

[0012] When the UAV meets the launch conditions, obtaining the initial operating conditions and initial environmental parameters of the UAV;

[0013] Constructing a UAV motion model of the UAV moving in near space by using the initial operating conditions and the initial environmental parameters;

[0014] Performing a virtual simulation of the delivery process according to the UAV motion model to determine a predicted delivery trajectory and a predicted delivery point of the UAV during the delivery process;

[0015] The drone is controlled to perform the delivery task according to the predicted delivery trajectory and predicted delivery landing point.

[0016] In one embodiment, the step of determining the target global environment model using the local environment data collected by each sensor node includes:

[0017] The fluctuation rate of the local environment data collected by each sensor node is calculated to determine the local environment fluctuation rate of the area where each sensor node is located;

[0018] The initial global environment model is constructed based on the local environment data collected by each sensor node. The calculation formula of the initial global environment model is as follows:

[0019]

[0020] in, is the initial global environment model, M is the number of sensor nodes, x i The local environment data of the i-th sensor node, ||pp i || is the position of the i-th sensor node p i The Euclidean distance, α i is the distance attenuation factor;

[0021] The initial global environment model is modified according to the local environment fluctuation rate of the area where each sensor node is located to determine the target global environment model, wherein the calculation formula of the target global environment model is as follows:

[0022]

[0023] in, is the target global environment model, the comprehensive weight L is the target space length, is the local environment volatility of the i-th sensor node.

[0024] In one embodiment, the step of calculating the fluctuation rate of the local environment data collected by each sensor node to determine the fluctuation rate of the local environment in the area where each sensor node is located includes:

[0025] The volatility is calculated based on the local environmental data collected by each sensor node to determine the differential volatility corresponding to each sensor node. The calculation formula for the differential volatility of the i-th sensor node is as follows:

[0026]

[0027] in, is the differential volatility corresponding to the i-th sensor node, N is the number of sampling points in the local environment data collected by the i-th sensor node, γ is the forgetting factor, k is the index of the time series corresponding to each data point in the local environment data, x i (t k ) is the value of the i-th sensor at time t k The sampling value of

[0028] The standard deviation of the sliding window corresponding to each sensor node is calculated based on the differential volatility corresponding to each sensor node, and the calculation formula of the differential volatility of the i-th sensor node is as follows:

[0029]

[0030] Among them, σ 2，i is the standard deviation of the sliding window corresponding to the i-th sensor node, W is the window length corresponding to the i-th sensor node when collecting local environmental data, β is the attenuation factor, μ i ,W is the weighted mean within the window, n is the index corresponding to the current time point in the local environment data;

[0031] The initial local volatility corresponding to each sensor node is determined by calculating the mean value based on the sliding window standard deviation corresponding to each sensor node and the differential volatility corresponding to each sensor node;

[0032] The initial local fluctuation rate corresponding to each sensor node is normalized to obtain the local environmental fluctuation rate of the area where each sensor node is located.

[0033] In one embodiment, the step of performing error analysis based on the actual landing point position, the actual delivery trajectory, the optimized delivery trajectory, and the optimized delivery landing point to determine the delivery error of the drone during the delivery process includes:

[0034] Calculating the landing point error based on the actual landing point position and the optimized delivery landing point to determine the three-dimensional spatial error of the UAV during the delivery process;

[0035] Calculating a trajectory error based on the actual delivery trajectory and the optimized delivery trajectory to determine the trajectory error of the UAV during the delivery process;

[0036] A weighted calculation is performed based on the three-dimensional space error and the trajectory error to determine the delivery error of the UAV during the delivery process.

[0037] In one embodiment, before the step of controlling the drone to perform the delivery task according to the predicted delivery trajectory and predicted delivery point when the drone meets the delivery conditions, the step further includes:

[0038] Training a machine learning model using a historical fault dataset of the drone to determine a fault diagnosis model for the drone;

[0039] Collecting current status data of each component of the drone, and inputting the current status data into the fault diagnosis model to determine the status fault result of each component;

[0040] When the status failure result of each component is a preset qualified result, it is determined that the drone meets the delivery conditions.

[0041] In one embodiment, after the step of adjusting the state of the drone according to the delivery error of the drone during the delivery process and the current flight state of the drone until the delivery mission in near-space is completed, the step further includes:

[0042] Obtaining the object weight, object delivery acceleration, and delivery position deviation of the delivered object during the delivery process of the drone;

[0043] Performing nondestructive evaluation based on the weight of the object and the acceleration of the object delivery to determine the delivery state energy of the delivery object;

[0044] The delivery performance of the UAV is monitored according to the delivery position deviation of the delivery object and the delivery state energy of the delivery object to determine the delivery performance result of the UAV.

[0045] In addition, to achieve the above-mentioned purpose, the present application also proposes a near-space UAV delivery monitoring device, the near-space UAV delivery monitoring device comprising:

[0046] A control module is used to control the drone to perform the delivery task according to the predicted delivery trajectory and predicted delivery point when the drone meets the delivery conditions;

[0047] A processing module is used to monitor in real time the local environment data collected by the UAV through multiple sensor nodes during the actual delivery process, and determine the target global environment model based on the local environment data collected by each sensor node;

[0048] An optimization module, configured to optimize the predicted delivery trajectory and the predicted delivery point using the target global environment model, and determine an optimized delivery trajectory and an optimized delivery point;

[0049] A monitoring module is used to monitor in real time the actual landing position and actual delivery trajectory of the drone during the actual delivery process;

[0050] An analysis module is configured to perform error analysis based on the actual landing point, the actual delivery trajectory, the optimized delivery trajectory, and the optimized delivery landing point to determine a delivery error of the drone during the delivery process;

[0051] The adjustment module is used to adjust the state of the drone according to the delivery error of the drone during the delivery process and the current flight state of the drone until the delivery mission in the near space is completed.

[0052] In addition, to achieve the above-mentioned purpose, the present application also proposes a near-space drone delivery monitoring device, which includes: a memory, a processor, and a computer program stored on the memory and runnable on the processor, and the computer program is configured to implement the steps of the near-space drone delivery monitoring method as described above.

[0053] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the near-space drone deployment monitoring method as described above are implemented.

[0054] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the near-space drone deployment monitoring method as described above.

[0055] The present application controls the drone to perform the delivery task according to the predicted delivery trajectory and predicted delivery landing point when the drone meets the delivery conditions; monitors the local environment data collected by the drone through multiple sensor nodes in real time during the actual delivery process, and determines the target global environment model through the local environment data collected by each sensor node; optimizes the predicted delivery trajectory and predicted delivery landing point through the target global environment model to determine the optimized delivery trajectory and optimized delivery landing point; monitors the actual landing point position and the actual delivery trajectory of the drone in real time during the actual delivery process; performs error analysis based on the actual landing point position, the actual delivery trajectory, the optimized delivery trajectory and the optimized delivery landing point to determine the delivery error of the drone during the delivery process; and adjusts the state of the drone based on the delivery error of the drone during the delivery process and the current flight state of the drone until the delivery task in near space is completed. Through the above method, a dynamically updated target global environment model is constructed by real-time collection of local environmental data from multiple sensor nodes, and the delivery trajectory and landing point distribution are optimized online based on the model, which significantly improves the delivery accuracy of UAVs in complex environments in near-space. By real-time monitoring of the actual landing point position and delivery trajectory, combined with error analysis and flight status feedback to form a closed-loop control, the problem of delivery deviation accumulation caused by dynamic environmental changes in traditional methods is effectively solved, and high-precision and robust autonomous delivery mission execution is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0057] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0058] Figure 1 A flowchart illustrating a first embodiment of a method for monitoring the deployment of a near-space drone is provided in this application;

[0059] Figure 2 A flowchart illustrating a second embodiment of the method for monitoring the deployment of a near-space drone is provided in this application;

[0060] Figure 3 This is a schematic diagram of the module structure of the near-space UAV deployment monitoring device according to an embodiment of the present application;

[0061] Figure 4Schematic diagram of the equipment structure of the hardware operating environment involved in the near-space drone deployment monitoring method in the embodiment of the present application.

[0062] The purpose, features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0063] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not intended to limit the present application.

[0064] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0065] The main solution of the embodiment of the present application is: when the drone meets the delivery conditions, the drone is controlled to perform the delivery task according to the predicted delivery trajectory and the predicted delivery landing point; the local environment data collected by the drone through multiple sensor nodes during the actual delivery process is monitored in real time, and the target global environment model is determined through the local environment data collected by each sensor node; the predicted delivery trajectory and the predicted delivery landing point are optimized through the target global environment model to determine the optimized delivery trajectory and the optimized delivery landing point; the actual landing point position and the actual delivery trajectory of the drone during the actual delivery process are monitored in real time; error analysis is performed based on the actual landing point position, the actual delivery trajectory, the optimized delivery trajectory and the optimized delivery landing point to determine the delivery error of the drone during the delivery process; the state of the drone is adjusted based on the delivery error of the drone during the delivery process and the current flight state of the drone until the delivery mission in near space is completed.

[0066] Because existing drone delivery technologies typically rely on preset trajectories and static environmental parameters, they lack the ability to monitor and compensate for dynamic environmental disturbances such as sudden changes in high-altitude wind fields and pressure gradients in real time. This results in significant deviations between the actual landing point and the expected location, particularly in near-space environments. Furthermore, traditional methods lack a global environmental model based on multi-sensor data fusion, making it impossible to dynamically correct trajectory errors. Furthermore, they lack closed-loop monitoring and feedback mechanisms for the delivery process, resulting in poor drone delivery accuracy in near-space environments.

[0067] This application provides a solution that constructs a dynamically updated target global environment model by real-time collection of local environmental data from multiple sensor nodes, and optimizes the delivery trajectory and landing point distribution online based on the model, significantly improving the delivery accuracy of drones in complex environments in near-space. By real-time monitoring of the actual landing point position and delivery trajectory, combined with error analysis and flight status feedback to form a closed-loop control, it effectively solves the problem of delivery deviation accumulation caused by dynamic environmental changes in traditional methods, and realizes high-precision and robust autonomous delivery task execution.

[0068] It should be noted that the execution entity of this embodiment can be a computing service device with data processing, network communication, and program execution capabilities, such as a tablet computer, personal computer, or mobile phone, or a near-space drone delivery monitoring device capable of performing the aforementioned functions. Below, this embodiment and the following embodiments will be described using a near-space drone delivery monitoring device as an example execution entity.

[0069] Based on this, the embodiment of the present application provides a method for monitoring the placement of a near-space drone, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the near-space UAV deployment monitoring method of the present application.

[0070] In this embodiment, the near-space drone delivery monitoring method includes steps S10 to S60:

[0071] Step S10: When the UAV meets the delivery conditions, the UAV is controlled to perform the delivery task according to the predicted delivery trajectory and predicted delivery landing point.

[0072] It should be noted that when all components of the drone are functioning normally, it means that the drone is capable of performing a delivery mission in near-space, and at this point it is determined that the drone meets the delivery conditions. The predicted delivery trajectory is an ideal delivery route based on a series of physical models and environmental data. This route takes into account factors such as the starting position, target position, expected wind speed, temperature gradient, etc., and uses numerical simulation to predict the optimal flight path of the drone so that it can accurately reach the designated delivery location. The predicted delivery point refers to the calculation of the final landing position of the delivery object to be delivered based on the predicted delivery trajectory and cargo characteristics (weight, shape, parachute type, etc.).

[0073] It can be understood that the drone is controlled to fly according to the predicted delivery trajectory, and the delivery mechanism is triggered to release the delivery object at the predicted delivery landing point.

[0074] In a feasible implementation, step S10 may include steps A11 to A14:

[0075] Step A11: When the UAV meets the launch conditions, the initial operating conditions and initial environmental parameters of the UAV are obtained.

[0076] It should be noted that the initial operating conditions include but are not limited to the initial position r0(x0,y0,z0) of the drone, the initial velocity v0(v x0 ,v y0 ,v z0), mass m and initial launch angle θ, etc.; initial environmental parameters include but are not limited to sea level air density ρ0, gravity acceleration g, wind speed w=(w x ,w y ,w z ), temperature gradient, etc.

[0077] Step A12: Constructing a UAV motion model of the UAV moving in near space based on the initial operating conditions and the initial environmental parameters.

[0078] It should be noted that based on Newton's second law, combined with initial operating conditions and initial environmental parameters, a UAV motion model can be constructed for UAVs moving in near-space. Considering the influence of factors such as resistance and gravity, the UAV motion model is as follows: Horizontal direction (x-axis): Vertical direction (y-axis): Height direction (z-axis) Among them, C d is the drag coefficient, A is the frontal area, is the air density that changes with altitude, H is the standard altitude, v(v x ,v y ,v z ) is the velocity vector of the UAV, w=(w x ,w y ,w z ) is the wind speed vector, |vw| is the relative velocity magnitude.

[0079] Step A13: Performing a virtual simulation of the delivery process according to the UAV motion model to determine the predicted delivery trajectory and predicted delivery point of the UAV during the delivery process.

[0080] It should be noted that by using numerical methods (such as the fourth-order Runge-Kutta method) to solve the UAV motion model of the UAV in near space, the position coordinates r(t) = (x(t), y(t), z(t)) and the velocity v(t) = (v x (t),v y (t),v z (t)). By integrating the above motion equation, the predicted trajectory of the UAV in the air is obtained. When the height z(t) of the UAV is close to the ground, that is, z(t)≈0, the position (x f ,y f ,z f ) is the predicted delivery point.

[0081] Step A14: Control the UAV to perform the delivery task according to the predicted delivery trajectory and predicted delivery landing point.

[0082] In a feasible implementation manner, steps B11 to B13 may be further included before step S10:

[0083] Step B11: Train a machine learning model using the historical fault data set of the UAV to determine a fault diagnosis model for the UAV.

[0084] It should be noted that the historical fault data set includes but is not limited to historical fault time, fault type (such as motor failure, sensor failure, etc.), component location, and environmental factors when the fault occurs (such as temperature, humidity, wind speed, etc.). Then, these raw data are converted into a format that can be used to train the machine learning model. The conversion process includes but is not limited to pre-processing steps such as data cleaning, feature extraction and selection of the historical fault data set. Finally, a suitable machine learning algorithm is selected to train the model, and the model performance is evaluated through methods such as cross-validation to form a fault diagnosis model that can ultimately be used for drone fault detection and diagnosis. In this embodiment, the machine learning algorithm includes but is not limited to any one of a decision tree, a random forest, a support vector machine, and a neural network.

[0085] Step B12: collecting current status data of each component of the drone, and inputting the current status data into the fault diagnosis model to determine the status fault result of each component.

[0086] It should be noted that before executing the delivery mission, the drone must be started and the current status data of each component (such as state parameters such as voltage, current, and temperature) must be continuously collected during the operation of the drone. The current status data of each component is input into the fault diagnosis model, which determines whether each component has a fault, thereby obtaining a status fault result for each component. In this embodiment, the status fault result includes one of the following: a fault exists, a fault does not exist, and an impending fault.

[0087] Step B13: When the status failure result of each component is a preset qualified result, it is determined that the drone meets the delivery conditions.

[0088] It should be noted that when the status failure result of each component is that there is no fault, it means that the status failure result of each component is a preset qualified result. At this time, the drone can perform the delivery mission in near space, and it is determined that the drone meets the delivery conditions.

[0089] Step S20: real-time monitoring of local environmental data collected by the UAV through multiple sensor nodes during the actual delivery process, and determining a target global environmental model through the local environmental data collected by each sensor node.

[0090] It should be noted that when the drone is performing a delivery mission, local environmental data, including but not limited to wind speed, wind direction, temperature, humidity, and air pressure, are continuously collected through multiple sensor nodes deployed at different locations (such as weather stations, ground radars, etc.).

[0091] It can be understood that based on the local environmental data provided by each sensor node, mathematical modeling techniques (such as interpolation, statistical models, or machine learning algorithms) are used to construct a global environmental model that reflects the environmental conditions of the entire deployment area. This model is used to describe the comprehensive environmental state of the drone's operating area. This model can provide more comprehensive and accurate environmental predictions than a single sensor node, helping to improve deployment accuracy.

[0092] Step S30: Optimizing the predicted delivery trajectory and the predicted delivery point through the target global environment model to determine the optimized delivery trajectory and the optimized delivery point.

[0093] It should be noted that the optimal delivery trajectory and optimal delivery point are recalculated using the latest environmental information in the target global environmental model. In this embodiment, the trajectory after optimizing the predicted delivery trajectory using the target global environmental model is the optimized delivery trajectory; the point after optimizing the predicted delivery point using the target global environmental model is the optimized delivery point.

[0094] Step S40: real-time monitoring of the actual landing position and actual delivery trajectory of the UAV during the actual delivery process.

[0095] It should be noted that during a drone delivery mission, multi-source sensors are continuously used to monitor the drone's actual flight path from takeoff to release of the delivery object, as well as the actual geographic location of the delivery object after landing. In this embodiment, the multi-source sensors include but are not limited to GPS positioning systems, inertial measurement units (IMUs), and visual odometry. The actual landing point refers to the actual geographic location of the delivery object after landing, and the actual delivery trajectory refers to the actual flight path of the drone from takeoff to release of the delivery object.

[0096] Step S50: performing error analysis based on the actual landing point position, the actual delivery trajectory, the optimized delivery trajectory, and the optimized delivery landing point to determine the delivery error of the UAV during the delivery process.

[0097] It should be noted that the difference between the actual landing point and the optimized landing point is compared, and the difference between the actual delivery trajectory and the optimized delivery trajectory is compared, and the two are combined to obtain the delivery error of the drone during the delivery process.

[0098] In a feasible implementation, step S50 may include steps C11 to C13:

[0099] Step C11: Calculating the landing point error based on the actual landing point position and the optimized delivery landing point to determine the three-dimensional spatial error of the UAV during the delivery process.

[0100] It should be noted that based on the actual landing point position (x d ,y d ,z d ) and optimize delivery points (x f ,y f ,z f )Calculate the horizontal plane error, horizontal plane error And further calculate the height error E2 = |z d -z f |, calculate the error based on the horizontal plane error and height error to determine the three-dimensional space error

[0101] Step C12: Calculating a trajectory error based on the actual delivery trajectory and the optimized delivery trajectory to determine the trajectory error of the UAV during the delivery process.

[0102] It should be noted that the calculation of the actual delivery trajectory T d (t) and optimized delivery trajectory T f (t) Euclidean distance E at each time point d =||T d (t)-T f (t)||, based on the actual delivery trajectory T d (t) and optimized delivery trajectory T f (t) Euclidean distance E at each time point d =||T d (t)-T f (t)||Calculate the average trajectory error and use the average trajectory error as the trajectory error E4 of the UAV during the delivery process.

[0103] Step C13: performing weighted calculation based on the three-dimensional space error and the trajectory error to determine the delivery error of the UAV during the delivery process.

[0104] It should be noted that the landing point error and trajectory error are assigned corresponding weights, and the sum of the two is 1. The specific allocation method can be set according to actual needs. According to the weights w1 and w2 corresponding to the landing point error and trajectory error respectively, and combined with the three-dimensional space error and trajectory error, a weighted calculation is performed to obtain the delivery error E of the drone during the delivery process. z =w1E3+w2E4.

[0105] Step S60: adjusting the state of the drone according to the delivery error of the drone during the delivery process and the current flight state of the drone until the delivery mission in the near space is completed.

[0106] It should be noted that the current flight state includes but is not limited to the current three-dimensional coordinates, speed, attitude and other related data of the UAV. The current flight state or mission strategy of the UAV is dynamically corrected based on the feedback of the delivery error. The PID controller gain K is used to calculate the current flight state or mission strategy of the UAV. p ,K i ,K d Adaptive adjustment, for example, increasing the proportional gain K when encountering a large deviation p To quickly correct the error; when there is a cumulative error, appropriately increase the integral gain K i Based on the PID controller's output, the drone's flight state is fine-tuned to ensure it follows the optimal delivery path as closely as possible, minimizing the final delivery error. The delivery mission is considered complete only after the drone successfully completes all scheduled delivery operations and confirms that the cargo has safely and accurately arrived at the target location.

[0107] In a feasible implementation, step S60 may include steps D11 to D13:

[0108] Step D11: Obtaining the object weight, object delivery acceleration, and delivery position deviation of the delivered object during the delivery process of the drone.

[0109] It should be noted that the placement position deviation of the delivery object refers to the actual landing position (x d ,y d ,z d ) and optimize delivery points (x f ,y f ,z f ) between the three-dimensional space error. By installing an inertial measurement unit (IMU) in the delivery object, the landing impact acceleration of the delivery object when it is released by the drone can be collected. In this embodiment, the object delivery acceleration refers to the landing impact acceleration a when the delivery object is released by the drone. c .

[0110] Step D12: performing a non-destructive evaluation based on the weight of the object and the acceleration of the object delivery to determine the delivery state energy of the delivery object.

[0111] It should be noted that the weight m of the object to be delivered is d and the object launch acceleration a c Can calculate the impact energy of the object when it is released Wherein Δt is the impact duration. In this embodiment, the impact energy when the delivery object is released is used as the delivery state energy of the delivery object, which is used to reflect whether the delivery object is damaged.

[0112] Step D13: monitoring the delivery performance of the UAV according to the delivery position deviation of the delivery object and the delivery state energy of the delivery object to determine the delivery performance result of the UAV.

[0113] It should be noted that the corresponding weights are assigned to the delivery position deviation and delivery state energy, and the sum of the two is 1. The specific distribution method can be set according to actual needs. According to the weights w3 and w4 corresponding to the delivery position deviation and delivery state energy respectively, and combined with the delivery position deviation and delivery state energy, a weighted calculation is performed to obtain the delivery performance index P of the drone during the delivery process = w3E3 + w4E c In this embodiment, delivery performance is divided into multiple levels, each corresponding to a different delivery index range, for example, qualified (P ≤ 0.5), warning (0.5 < P ≤ 0.8), and unqualified (P > 0.8). Based on the delivery performance indicators of the drone during the delivery process and the delivery index range corresponding to each delivery performance level, the delivery performance level of the drone is determined, and the final delivery performance result is obtained based on the delivery performance level.

[0114] This embodiment controls the drone to perform the delivery mission according to the predicted delivery trajectory and predicted delivery point when the drone meets the delivery conditions; monitors the local environment data collected by the drone through multiple sensor nodes in real time during the actual delivery process, and determines a target global environment model through the local environment data collected by each sensor node; optimizes the predicted delivery trajectory and predicted delivery point through the target global environment model to determine the optimized delivery trajectory and optimized delivery point; monitors the actual delivery point position and the actual delivery trajectory of the drone in real time during the actual delivery process; performs error analysis based on the actual delivery point position, the actual delivery trajectory, the optimized delivery trajectory and the optimized delivery point to determine the delivery error of the drone during the delivery process; and adjusts the state of the drone based on the delivery error during the delivery process and the current flight state of the drone until the delivery mission in near space is completed. Through the above method, a dynamically updated target global environment model is constructed by real-time collection of local environmental data from multiple sensor nodes, and the delivery trajectory and landing point distribution are optimized online based on the model, which significantly improves the delivery accuracy of UAVs in complex environments in near-space. By real-time monitoring of the actual landing point position and delivery trajectory, combined with error analysis and flight status feedback to form a closed-loop control, the problem of delivery deviation accumulation caused by dynamic environmental changes in traditional methods is effectively solved, and high-precision and robust autonomous delivery mission execution is achieved.

[0115] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above embodiment 1 can be referred to the above introduction and will not be described in detail later. Figure 2 In the near-space UAV deployment monitoring method, step S20 further includes steps S201 to S203:

[0116] Step S201: performing fluctuation calculation on the local environment data collected by each sensor node to determine the local environment fluctuation rate of the area where each sensor node is located.

[0117] It should be noted that the local environmental data collected by each sensor node is used to calculate the degree of change of environmental parameters in the area where each sensor node is located, which is used to identify the instability of the environment and predict possible change trends, thereby obtaining the local environmental volatility of the area where each sensor node is located.

[0118] In a feasible implementation, step S21 may include steps E11 to E14:

[0119] Step E11: Calculate the fluctuation rate based on the local environmental data collected by each sensor node to determine the differential fluctuation rate corresponding to each sensor node. The calculation formula for the differential fluctuation rate of the i-th sensor node is as follows:

[0120]

[0121] in, is the differential volatility corresponding to the i-th sensor node, N is the number of sampling points in the local environment data collected by the i-th sensor node, γ is the forgetting factor, k is the index of the time series corresponding to each data point in the local environment data (k = 1, 2, ..., N), x i (t k ) is the value of the i-th sensor at time t k The sampling value of .

[0122] It should be noted that the local environmental data collected by each sensor node is used to calculate the local environmental fluctuation rate in the area where each sensor node is located. This is used to measure the intensity of data changes between adjacent time points. To reduce noise sensitivity, this embodiment introduces a forgetting factor γ∈(0,1]) to control the decay rate of data weight. The more recent the data, the higher the weight.

[0123] Step E12: Calculate the standard deviation based on the differential volatility corresponding to each sensor node to determine the sliding window standard deviation corresponding to each sensor node. The calculation formula for the differential volatility of the i-th sensor node is as follows:

[0124]

[0125] Among them, σ 2，i is the standard deviation of the sliding window corresponding to the i-th sensor node, W is the window length corresponding to the i-th sensor node when collecting local environmental data, β is the attenuation factor, μ i ,W is the weighted mean within the window, and n is the index corresponding to the current time point in the local environment data.

[0126] It should be noted that the standard deviation of each sensor node within the time window length W is calculated based on the differential volatility corresponding to each sensor node to measure the degree of data dispersion, thereby obtaining the sliding window standard deviation corresponding to each sensor node. In this embodiment, an attenuation factor β∈(0,1] is introduced to adjust the weights of different time points within the window. By introducing exponentially decaying weights, the influence of the data within the window decreases over time, avoiding the "mutation" problem of fixed windows.

[0127] Step E13: performing mean calculation based on the sliding window standard deviation corresponding to each sensor node and the differential volatility corresponding to each sensor node to determine the initial local volatility corresponding to each sensor node.

[0128] It should be noted that the weighted harmonic mean method is used to combine the sliding window standard deviation corresponding to each sensor node and the differential volatility corresponding to each sensor node to obtain the initial local volatility corresponding to each sensor node, avoiding the dominance of a single indicator in the result. In this embodiment, the calculation formula for the initial local volatility of the i-th sensor node is as follows: A linear weighted combination or other methods may also be used to calculate the initial local fluctuation rate corresponding to each sensor node, which is not limited in this embodiment.

[0129] In step E14, normalizing the initial local fluctuation rate corresponding to each sensor node is performed to obtain the local environmental fluctuation rate of the area where each sensor node is located.

[0130] It should be noted that the initial local fluctuation rate corresponding to each sensor node is normalized and the result is mapped to the interval [0,1] to obtain the local environmental fluctuation rate of the area where each sensor node is located. In this embodiment, the local environmental fluctuation rate of the area where the i-th sensor node is located is

[0131] Step S202: construct an initial global environment model based on the local environment data collected by each sensor node, wherein the calculation formula of the initial global environment model is as follows:

[0132]

[0133] in, is the initial global environment model, M is the number of sensor nodes, xi The local environment data of the i-th sensor node, ||pp i || is the position of the i-th sensor node p i The Euclidean distance, α i is the distance attenuation factor.

[0134] It should be noted that the initial global environment model is constructed using the local environment data collected by each sensor node. Introducing the distance attenuation factor α when building the model i =α0+log(1+d i ), where α0 is a pre-set basic attenuation factor, such as 2; d i is the density of neighboring nodes around the i-th sensor node (the number of nodes per unit area). In this embodiment, in the sparse area (d i Small) to reduce the attenuation strength (α i small), expand the scope of influence; in dense areas (d i Large) enhances attenuation to avoid overfitting.

[0135] Step S203: Modify the initial global environment model according to the local environment fluctuation rate of the area where each sensor node is located to determine the target global environment model, wherein the calculation formula of the target global environment model is as follows:

[0136]

[0137] in, is the target global environment model, the comprehensive weight L is the target space length, is the local environment volatility of the i-th sensor node.

[0138] It should be noted that the initial global environment model is modified by using the local environment volatility of the area where each sensor node is located, and the volatility and spatial correlation are integrated to determine the target global environment model. In this embodiment, the target space length L refers to the spatial correlation length, which controls the sensor's influence range. The closer 1) or the farther (||pp i The weight of sensors with ||≥L) is significantly suppressed, doubly ensuring the reliability of the model.

[0139] This embodiment calculates the volatility of the local environmental data collected by each sensor node to determine the local environmental volatility of the area where each sensor node is located. An initial global environmental model is constructed based on the local environmental data collected by each sensor node. This initial global environmental model is then modified based on the local environmental volatility of the area where each sensor node is located to determine a target global environmental model. This approach enables the target global environmental model to better describe the comprehensive environmental state of the drone's operating area, laying the foundation for subsequent deployment monitoring.

[0140] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the near-space drone deployment monitoring method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0141] This application also provides a near-space drone deployment monitoring device, please refer to Figure 3 The near-space UAV deployment monitoring device includes:

[0142] The control module 10 is used to control the drone to perform the delivery task according to the predicted delivery trajectory and predicted delivery point when the drone meets the delivery conditions;

[0143] The processing module 20 is used to monitor in real time the local environment data collected by the UAV through multiple sensor nodes during the actual delivery process, and determine the target global environment model based on the local environment data collected by each sensor node;

[0144] An optimization module 30 is configured to optimize the predicted delivery trajectory and the predicted delivery point using the target global environment model to determine an optimized delivery trajectory and an optimized delivery point;

[0145] A monitoring module 40 is used to monitor in real time the actual landing position and actual delivery trajectory of the drone during the actual delivery process;

[0146] An analysis module 50 is configured to perform error analysis based on the actual landing point, the actual delivery trajectory, the optimized delivery trajectory, and the optimized delivery landing point to determine a delivery error of the drone during the delivery process;

[0147] The adjustment module 60 is used to adjust the state of the drone according to the delivery error of the drone during the delivery process and the current flight state of the drone until the delivery mission in the near space is completed.

[0148] Optionally, the control module 10 is further configured to:

[0149] When the UAV meets the launch conditions, obtaining the initial operating conditions and initial environmental parameters of the UAV;

[0150] Constructing a UAV motion model of the UAV moving in near space by using the initial operating conditions and the initial environmental parameters;

[0151] Performing a virtual simulation of the delivery process according to the UAV motion model to determine a predicted delivery trajectory and a predicted delivery point of the UAV during the delivery process;

[0152] The drone is controlled to perform the delivery task according to the predicted delivery trajectory and predicted delivery landing point.

[0153] Optionally, the processing module 20 is further configured to:

[0154] The fluctuation rate of the local environment data collected by each sensor node is calculated to determine the local environment fluctuation rate of the area where each sensor node is located;

[0155] The initial global environment model is constructed based on the local environment data collected by each sensor node. The calculation formula of the initial global environment model is as follows:

[0156]

[0157] in, is the initial global environment model, M is the number of sensor nodes, x i The local environment data of the i-th sensor node, ||pp i || is the position of the i-th sensor node p i The Euclidean distance, α i is the distance attenuation factor;

[0158] The initial global environment model is modified according to the local environment fluctuation rate of the area where each sensor node is located to determine the target global environment model, wherein the calculation formula of the target global environment model is as follows:

[0159]

[0160] in, is the target global environment model, the comprehensive weight L is the target space length, is the local environment volatility of the i-th sensor node.

[0161] Optionally, the processing module 20 is further configured to:

[0162] The volatility is calculated based on the local environmental data collected by each sensor node to determine the differential volatility corresponding to each sensor node. The calculation formula for the differential volatility of the i-th sensor node is as follows:

[0163]

[0164] in, is the differential volatility corresponding to the i-th sensor node, N is the number of sampling points in the local environment data collected by the i-th sensor node, γ is the forgetting factor, k is the index of the time series corresponding to each data point in the local environment data, x i (t k ) is the value of the i-th sensor at time t k The sampling value of

[0165] The standard deviation of the sliding window corresponding to each sensor node is calculated based on the differential volatility corresponding to each sensor node, and the calculation formula of the differential volatility of the i-th sensor node is as follows:

[0166]

[0167] Among them, σ 2，i is the standard deviation of the sliding window corresponding to the i-th sensor node, W is the window length corresponding to the i-th sensor node when collecting local environmental data, β is the attenuation factor, μ i ,W is the weighted mean within the window, n is the index corresponding to the current time point in the local environment data;

[0168] The initial local volatility corresponding to each sensor node is determined by calculating the mean value based on the sliding window standard deviation corresponding to each sensor node and the differential volatility corresponding to each sensor node;

[0169] The initial local fluctuation rate corresponding to each sensor node is normalized to obtain the local environmental fluctuation rate of the area where each sensor node is located.

[0170] Optionally, the analysis module 50 is further configured to:

[0171] Calculating the landing point error based on the actual landing point position and the optimized delivery landing point to determine the three-dimensional spatial error of the UAV during the delivery process;

[0172] Calculating a trajectory error based on the actual delivery trajectory and the optimized delivery trajectory to determine the trajectory error of the UAV during the delivery process;

[0173] A weighted calculation is performed based on the three-dimensional space error and the trajectory error to determine the delivery error of the UAV during the delivery process.

[0174] Optionally, the control module 10 is further configured to:

[0175] Training a machine learning model using a historical fault dataset of the drone to determine a fault diagnosis model for the drone;

[0176] Collecting current status data of each component of the drone, and inputting the current status data into the fault diagnosis model to determine the status fault result of each component;

[0177] When the status failure result of each component is a preset qualified result, it is determined that the drone meets the delivery conditions.

[0178] Optionally, the adjustment module 60 is further configured to:

[0179] Obtaining the object weight, object delivery acceleration, and delivery position deviation of the delivered object during the delivery process of the drone;

[0180] Performing nondestructive evaluation based on the weight of the object and the acceleration of the object delivery to determine the delivery state energy of the delivery object;

[0181] The delivery performance of the UAV is monitored according to the delivery position deviation of the delivery object and the delivery state energy of the delivery object to determine the delivery performance result of the UAV.

[0182] The near-space drone delivery monitoring device provided by this application adopts the near-space drone delivery monitoring method of the above-mentioned embodiment, which can solve the technical problem of reduced delivery accuracy caused by the existing drone delivery technology due to insufficient real-time monitoring and the inability to perform dynamic trajectory correction in a timely manner. Compared with the existing technology, the beneficial effects of the near-space drone delivery monitoring device provided by this application are the same as the beneficial effects of the near-space drone delivery monitoring method provided by the above-mentioned embodiment, and the other technical features of the near-space drone delivery monitoring device are the same as the features disclosed in the above-mentioned embodiment method, which will not be repeated here.

[0183] The present application provides a near-space drone delivery monitoring device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the near-space drone delivery monitoring method of the above-mentioned embodiment one.

[0184] Reference below Figure 4, which shows a schematic structural diagram of a near-space drone delivery monitoring device suitable for implementing an embodiment of the present application. The near-space drone delivery monitoring device in the embodiment of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (e.g., vehicle-mounted navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 4 The near-space drone deployment monitoring device shown is merely an example and should not limit the functionality and scope of use of the embodiments of the present application.

[0185] like Figure 4 As shown, the near-space drone delivery monitoring device may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM: Read Only Memory) 1002 or the program loaded from the storage device 1003 to the random access memory (RAM: Random Access Memory) 1004. Various programs and data required for the operation of the near-space drone delivery monitoring device are also stored in RAM1004. The processing device 1001, ROM1002 and RAM1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input device 1007 including, for example, a touch screen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output device 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage device 1003 including, for example, a magnetic tape, hard disk, etc.; and communication device 1009. Communication device 1009 can allow the near-space drone delivery monitoring device to communicate wirelessly or wired with other devices to exchange data. Although the figure shows a near-space drone delivery monitoring device with various systems, it should be understood that it is not required to implement or have all of the systems shown. More or fewer systems may be implemented or have instead.

[0186] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0187] The near-space drone delivery monitoring device provided by this application utilizes the near-space drone delivery monitoring method described in the aforementioned embodiment, and can address the technical issue of existing drone delivery technologies, which suffer from reduced delivery accuracy due to insufficient real-time monitoring and the inability to perform timely dynamic trajectory correction. Compared to the prior art, the beneficial effects of the near-space drone delivery monitoring device provided by this application are the same as those of the near-space drone delivery monitoring method described in the aforementioned embodiment, and the other technical features of the near-space drone delivery monitoring device are the same as those disclosed in the method of the previous embodiment, and are not further elaborated here.

[0188] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0189] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0190] The present application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, and the computer-readable program instructions are used to execute the near-space drone delivery monitoring method in the above-mentioned embodiment.

[0191] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0192] The above-mentioned computer-readable storage medium can be included in the near-space drone delivery monitoring device; or it can exist independently without being assembled into the near-space drone delivery monitoring device.

[0193] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the near-space drone delivery monitoring device, the near-space drone delivery monitoring device enables: when the drone meets the delivery conditions, to control the drone to perform the delivery task according to the predicted delivery trajectory and predicted delivery landing point; to monitor in real time the local environmental data collected by the drone through multiple sensor nodes during the actual delivery process, and to determine the target global environmental model through the local environmental data collected by each sensor node; to optimize the predicted delivery trajectory and predicted delivery landing point through the target global environmental model to determine the optimized delivery trajectory and optimized delivery landing point; to monitor in real time the actual landing point position and actual delivery trajectory of the drone during the actual delivery process; to perform error analysis based on the actual landing point position, the actual delivery trajectory, the optimized delivery trajectory and the optimized delivery landing point to determine the delivery error of the drone during the delivery process; to adjust the state of the drone based on the delivery error of the drone during the delivery process and the current flight state of the drone until the delivery mission in near space is completed.

[0194] The computer program code for performing the operations of the present application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0195] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0196] The modules described in the embodiments of the present application may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.

[0197] The readable storage medium provided in this application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., a computer program) for executing the above-mentioned near-space drone delivery monitoring method. This computer-readable storage medium can solve the technical problem of reduced delivery accuracy caused by the inadequate real-time monitoring and inability to perform timely dynamic trajectory correction in existing drone delivery technologies. Compared with the existing technology, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the near-space drone delivery monitoring method provided in the above-mentioned embodiment, and will not be elaborated here.

[0198] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the above-mentioned near-space drone deployment monitoring method.

[0199] The computer program product provided in this application can address the technical issues with existing drone delivery technologies, which suffer from reduced delivery accuracy due to insufficient real-time monitoring and the inability to perform timely dynamic trajectory correction. Compared to existing technologies, the beneficial effects of the computer program product provided in this application are similar to those of the near-space drone delivery monitoring method provided in the aforementioned embodiments, and are not further elaborated here.

[0200] The above description is only part of the embodiments of the present application and does not limit the patent scope of the present application. All equivalent structural transformations made by using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A method for monitoring the release of a near-space drone, characterized in that: The method comprises: When the drone meets the delivery conditions, the drone is controlled to perform the delivery task according to the predicted delivery trajectory and predicted delivery point; Real-time monitoring of local environmental data collected by the drone through multiple sensor nodes during the actual deployment process, and determining a target global environmental model based on the local environmental data collected by each sensor node; Optimizing the predicted delivery trajectory and the predicted delivery point through the target global environment model to determine the optimized delivery trajectory and the optimized delivery point; Real-time monitoring of the actual landing point and actual delivery trajectory of the drone during the actual delivery process; Perform error analysis based on the actual landing point, the actual delivery trajectory, the optimized delivery trajectory, and the optimized delivery landing point to determine the delivery error of the drone during the delivery process; The state of the drone is adjusted according to the delivery error of the drone during the delivery process and the current flight state of the drone until the delivery mission in the near space is completed.

2. The method according to claim 1, wherein When the drone meets the delivery conditions, the step of controlling the drone to perform the delivery task according to the predicted delivery trajectory and the predicted delivery landing point includes: When the UAV meets the launch conditions, obtaining the initial operating conditions and initial environmental parameters of the UAV; Constructing a UAV motion model of the UAV moving in near space by using the initial operating conditions and the initial environmental parameters; Performing a virtual simulation of the delivery process according to the UAV motion model to determine a predicted delivery trajectory and a predicted delivery point of the UAV during the delivery process; The drone is controlled to perform the delivery task according to the predicted delivery trajectory and predicted delivery landing point.

3. The method according to claim 1, wherein The step of determining the target global environment model through the local environment data collected by each sensor node includes: The fluctuation rate of the local environment data collected by each sensor node is calculated to determine the local environment fluctuation rate of the area where each sensor node is located; The initial global environment model is constructed based on the local environment data collected by each sensor node. The calculation formula of the initial global environment model is as follows: in, is the initial global environment model, M is the number of sensor nodes, x i The local environment data of the i-th sensor node, ||pp i || is the position of the i-th sensor node p i The Euclidean distance, α i is the distance attenuation factor; The initial global environment model is modified according to the local environment fluctuation rate of the area where each sensor node is located to determine the target global environment model, wherein the calculation formula of the target global environment model is as follows: in, is the target global environment model, the comprehensive weight L is the target space length, is the local environment volatility of the i-th sensor node.

4. The method according to claim 3, wherein The step of calculating the fluctuation rate of the local environment data collected by each sensor node to determine the fluctuation rate of the local environment in the area where each sensor node is located includes: The volatility is calculated based on the local environmental data collected by each sensor node to determine the differential volatility corresponding to each sensor node. The calculation formula for the differential volatility of the i-th sensor node is as follows: in, is the differential volatility corresponding to the i-th sensor node, N is the number of sampling points in the local environment data collected by the i-th sensor node, γ is the forgetting factor, k is the index of the time series corresponding to each data point in the local environment data, x i (t k ) is the value of the i-th sensor at time t k The sampling value of The standard deviation of the sliding window corresponding to each sensor node is calculated based on the differential volatility corresponding to each sensor node, and the calculation formula of the differential volatility of the i-th sensor node is as follows: Among them, σ 2，i is the standard deviation of the sliding window corresponding to the i-th sensor node, W is the window length corresponding to the i-th sensor node when collecting local environmental data, β is the attenuation factor, μ i ,W is the weighted mean within the window, n is the index corresponding to the current time point in the local environment data; The initial local volatility corresponding to each sensor node is determined by calculating the mean value based on the sliding window standard deviation corresponding to each sensor node and the differential volatility corresponding to each sensor node; The initial local fluctuation rate corresponding to each sensor node is normalized to obtain the local environmental fluctuation rate of the area where each sensor node is located.

5. The method according to claim 1, wherein The step of performing error analysis based on the actual landing point position, the actual delivery trajectory, the optimized delivery trajectory, and the optimized delivery landing point to determine the delivery error of the drone during the delivery process includes: Calculating the landing point error based on the actual landing point position and the optimized delivery landing point to determine the three-dimensional spatial error of the UAV during the delivery process; Calculating a trajectory error based on the actual delivery trajectory and the optimized delivery trajectory to determine the trajectory error of the UAV during the delivery process; A weighted calculation is performed based on the three-dimensional space error and the trajectory error to determine the delivery error of the UAV during the delivery process.

6. The method according to any one of claims 1 to 5, characterized in that Before the step of controlling the drone to perform the delivery task according to the predicted delivery trajectory and predicted delivery point when the drone meets the delivery conditions, the method further includes: Training a machine learning model using a historical fault dataset of the drone to determine a fault diagnosis model for the drone; Collecting current status data of each component of the drone, and inputting the current status data into the fault diagnosis model to determine the status fault result of each component; When the status failure result of each component is a preset qualified result, it is determined that the drone meets the delivery conditions.

7. The method according to any one of claims 1 to 5, characterized in that After the step of adjusting the state of the drone according to the delivery error of the drone during the delivery process and the current flight state of the drone until the delivery mission in the near-space is completed, the method further includes: Obtaining the object weight, object delivery acceleration, and delivery position deviation of the delivered object during the delivery process of the drone; Performing nondestructive evaluation based on the weight of the object and the acceleration of the object delivery to determine the delivery state energy of the delivery object; The delivery performance of the UAV is monitored according to the delivery position deviation of the delivery object and the delivery state energy of the delivery object to determine the delivery performance result of the UAV.

8. A near-space drone deployment monitoring device, characterized in that: The near-space UAV deployment monitoring device includes: A control module is used to control the drone to perform the delivery task according to the predicted delivery trajectory and predicted delivery point when the drone meets the delivery conditions; A processing module is used to monitor in real time the local environment data collected by the UAV through multiple sensor nodes during the actual delivery process, and determine the target global environment model based on the local environment data collected by each sensor node; An optimization module, configured to optimize the predicted delivery trajectory and the predicted delivery point using the target global environment model, and determine an optimized delivery trajectory and an optimized delivery point; A monitoring module is used to monitor in real time the actual landing position and actual delivery trajectory of the drone during the actual delivery process; An analysis module is configured to perform error analysis based on the actual landing point, the actual delivery trajectory, the optimized delivery trajectory, and the optimized delivery landing point to determine a delivery error of the drone during the delivery process; The adjustment module is used to adjust the state of the drone according to the delivery error of the drone during the delivery process and the current flight state of the drone until the delivery mission in the near space is completed.

9. A near-space drone deployment monitoring device, characterized in that: The device includes: a memory, a processor, and a near-space UAV delivery monitoring program stored in the memory and executable on the processor, wherein the near-space UAV delivery monitoring program is configured to implement the steps of the near-space UAV delivery monitoring method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores a near-space UAV delivery monitoring program, which, when executed by the processor, implements the steps of the near-space UAV delivery monitoring method according to any one of claims 1 to 7.

Images