Unmanned aerial vehicle application control method and system

Abstract

The unmanned aerial vehicle pesticide application control method and system provided by the application belong to the field of agricultural technology, and comprise the following steps: acquiring position information of an unmanned aerial vehicle and operation parameters of the unmanned aerial vehicle for target land spraying operation; inputting the operation parameters into a droplet deposition prediction model of the unmanned aerial vehicle to acquire predicted droplet density output by the droplet deposition prediction model; and based on the position information, comparing and analyzing the predicted droplet density with a pesticide application prescription map of the target land to determine a parameter adjustment amount of the unmanned aerial vehicle, which is used for adjusting the operation parameters. The unmanned aerial vehicle pesticide application control method and system provided by the application predict the droplet density in the pesticide application process by using the operation parameters of the unmanned aerial vehicle, compare the prediction with the prescription map, and thus adjust the operation parameters in real time according to the pesticide application quality in the unmanned aerial vehicle pesticide application process, improve the utilization rate of the pesticide, ensure the pesticide application quality, and realize precise pesticide application.

Description

Technical Field

[0001] This invention relates to the field of agricultural technology, and in particular to a method and system for controlling pesticide application by unmanned aerial vehicles (UAVs). Background Technology

[0002] Drone spraying has become one of the most commonly used methods in agricultural machinery operations due to its advantages such as high efficiency, low cost, and wide terrain adaptability. Currently, the accuracy of drone spraying directly affects pesticide utilization, and the most important factor influencing the accuracy of drone spraying is the decision-making and implementation methods for spraying.

[0003] In recent years, one research direction in drug application decision-making is to use deep learning-based image and spectral information fusion technology to design drug application auxiliary decision-making systems and provide data support for drone-based drug application prescriptions.

[0004] However, the drone application method described above cannot guarantee the quality of application. Summary of the Invention

[0005] The drone spraying control method and system provided by this invention are used to solve the defects of existing technologies that cannot guarantee the quality of spraying. During the drone spraying process, the operating parameters can be adjusted in real time according to the quality of spraying, thereby improving the utilization rate of the drug, ensuring the quality of spraying, and achieving precise spraying.

[0006] This invention provides a method for controlling pesticide application by an unmanned aerial vehicle (UAV), comprising:

[0007] The location information of the drone and the operation parameters of the drone spraying the target plot are obtained, including flight speed and spraying flow rate;

[0008] The operation parameters are input into the droplet deposition prediction model of the UAV to obtain the predicted droplet density output by the droplet deposition prediction model; the predicted droplet density is calculated by the droplet deposition prediction model based on the operation parameters to determine the droplet density and dosage.

[0009] Based on the location information, the predicted droplet density is compared and analyzed with the pesticide application prescription map of the target plot to determine the parameter adjustment amount of the UAV, which is used to adjust the operation parameters.

[0010] According to a drone spraying control method provided by the present invention, before inputting the operation parameters into the drone's droplet deposition prediction model and obtaining the predicted droplet density output by the droplet deposition prediction model, the method further includes:

[0011] The number of droplet point clouds and the amount of droplet deposition in multiple sample regions of the UAV under different sample operation parameters are obtained; the sample operation parameters include: sample flight speed and sample drug application rate.

[0012] The droplet deposition prediction model is constructed based on the number of droplet point clouds and the amount of droplet deposition in each sample region according to the operation parameters of each sample.

[0013] According to the present invention, a drone spraying control method is provided, wherein the droplet deposition prediction model is constructed based on the number of droplet point clouds and the amount of droplet deposition in each sample area for each sample operation parameter, including:

[0014] Based on the number of droplet points and the amount of droplet deposition in each sample area under multiple sample operation parameters of the UAV, the linear relationship between the number of droplet points and the amount of droplet deposition in the UAV operation, as well as the deposition relationship between the amount of droplet deposition and the flight speed and the application rate, are determined.

[0015] Based on the linear relationship and the deposition relationship, the quantitative relationship between the flight speed, the application rate, and the number of droplet points is determined;

[0016] Based on the aforementioned quantitative relationships and the area of ​​the sample region, the density relationship between flight speed, application rate, and droplet density is determined.

[0017] Based on the density relationship, the droplet deposition prediction model is constructed.

[0018] According to a drone spraying control method provided by the present invention, the spraying prescription map is obtained based on the following steps:

[0019] Acquire a hyperspectral image of the target site;

[0020] Based on the hyperspectral image, the extent and severity of pests and diseases in the target plot are determined.

[0021] Based on the extent and severity of the pests and diseases, a pesticide application prescription map is determined for the target plot; the pesticide application prescription map includes the distribution of pesticide application requirements within the target plot.

[0022] According to a drone spraying control method provided by the present invention, the step of comparing and analyzing the predicted droplet density with the spraying prescription map of the target plot based on the location information to determine the parameter adjustment amount of the drone includes:

[0023] The required dosage of the drug corresponding to the location information is determined in the drug application prescription diagram;

[0024] The predicted droplet density is compared and analyzed with the required dosage to generate a dosage error.

[0025] The parameter adjustment amount is determined based on the dosage error.

[0026] The present invention also provides a drone spraying control system, including a drone, a drone real-time tracking platform, a digital radio, and an industrial control computer;

[0027] The drone is used for spraying operations;

[0028] The real-time tracking platform for the unmanned aerial vehicle is equipped with multiple lidar sensors.

[0029] The lidar is used to collect droplet point cloud data during the spraying operation of the UAV, and the droplet point cloud data is used to construct a droplet deposition prediction model.

[0030] The drone is equipped with a GPS antenna, which is used to collect the drone's location information and transmit the location information to the industrial control computer via the digital radio.

[0031] The multiple lidars transmit the fog droplet point cloud data to the industrial control computer via the digital radio.

[0032] The industrial control computer is equipped with a processor; it also includes a memory and a program or instruction stored in the memory and executable on the processor. When the program or instruction is executed by the processor, it performs any of the above-described drone spraying control methods.

[0033] The present invention also provides an industrial control computer, comprising:

[0034] The acquisition module is used to acquire the location information of the UAV and the operation parameters of the UAV spraying the target plot. The operation parameters include: flight speed and spraying flow rate.

[0035] The input module is used to input the operation parameters into the droplet deposition prediction model of the UAV and obtain the predicted droplet density output by the droplet deposition prediction model; the predicted droplet density is calculated by the droplet deposition prediction model based on the operation parameters to determine the droplet density and dosage.

[0036] The analysis module is used to compare and analyze the predicted droplet density with the pesticide application prescription map of the target plot based on the location information, so as to determine the parameter adjustment amount of the UAV, which is used to adjust the operation parameters.

[0037] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the drone spraying control method described above.

[0038] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the drone spraying control method as described above.

[0039] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the drone spraying control method as described above.

[0040] The drone spraying control method and system provided by this invention uses drone operation parameters to predict the droplet density during the spraying process and compares the predicted amount with the prescription map. In this way, the operation parameters are adjusted in real time according to the spraying quality during the drone spraying process, thereby improving the utilization rate of the drug, ensuring the spraying quality, and realizing precise spraying. Attached Figure Description

[0041] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0042] Figure 1 This is one of the flowcharts of the drone spraying control method provided by the present invention;

[0043] Figure 2 This is a schematic diagram of the structure of the drone spraying control system provided by the present invention;

[0044] Figure 3 This is a schematic diagram of the distribution of fog droplet point clouds provided by the present invention;

[0045] Figure 4 This is a schematic diagram of coordinate system transformation provided by the present invention;

[0046] Figure 5 This is a schematic diagram of the droplet deposition amount provided by the present invention;

[0047] Figure 6 This is a schematic diagram of the prescription diagram provided by the present invention;

[0048] Figure 7 This is the second flowchart of the drone spraying control method provided by the present invention;

[0049] Figure 8 This is a schematic diagram of the industrial control computer provided by the present invention;

[0050] Figure 9 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0051] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0052] Currently, precision pesticide application decisions for pests and diseases are primarily influenced by five factors: crop information acquisition, nozzle selection, variable-rate application control, aircraft flight attitude control, and application quality monitoring. The application decision-making process mainly utilizes technologies such as image processing, deep learning, artificial neural networks, and spectral analysis to acquire crop information, analyze this information, and construct a pesticide prescription map. Then, considering the impact of nozzle selection, pesticide control system parameter settings, and the influence of the aircraft's flight attitude and gas washing field on pesticide deposition quality, application quality monitoring methods are used to evaluate the application decision-making system and refine the application decisions, thus constructing the final application decision-making system. However, this application decision-making system can only be used after adjusting the plant protection machinery's operating parameters following the initial application, allowing for a subsequent application.

[0053] Building a nozzle selection decision system from the perspective of nozzle selection requires a large number of experiments and nozzle selection based on the specific situation of crop diseases and pests. However, in the actual operation environment, the accuracy of pesticide application is also related to the changes in the wind field when the pesticide liquid leaves the nozzle and is atomized into droplets. Therefore, relying solely on the nozzle selection decision system cannot meet the requirements of drone application for precise control of diseases and pests.

[0054] The following is combined with Figures 1-9 This invention describes the drone spraying control method and system provided by embodiments of the present invention.

[0055] The drone spraying control method provided in this invention can be executed by an electronic device or software, functional modules, or functional entities within an electronic device capable of implementing the drone spraying control method. In this invention, the electronic device includes, but is not limited to, an industrial control computer. It should be noted that the aforementioned execution entity does not constitute a limitation on this invention.

[0056] Figure 1 This is one of the flowcharts illustrating the drone spraying control method provided by the present invention, such as... Figure 1As shown, including but not limited to the following steps:

[0057] First, in step S1, the location information of the UAV and the operation parameters of the UAV spraying the target plot are obtained. The operation parameters include: flight speed and spraying flow rate.

[0058] The drone can be an agricultural drone with pesticide application capabilities.

[0059] During the spraying operation of the drone on the target plot, the industrial control computer will monitor the drone's operating parameters in real time. These operating parameters may include the drone's flight speed and the spraying flow rate.

[0060] The target plot is the area to be sprayed. For example, if wheat is planted in the target plot, drones are needed to spray the wheat canopy.

[0061] The industrial control computer is equipped with software such as SOPAS, EXCEL, and MATLAB to assist in data analysis.

[0062] Optionally, before inputting the operational parameters into the UAV's droplet deposition prediction model and obtaining the predicted droplet density output by the droplet deposition prediction model, the method further includes:

[0063] The number of droplet point clouds and the amount of droplet deposition in multiple sample regions of the UAV under different sample operation parameters are obtained; the sample operation parameters include: sample flight speed and sample drug application rate.

[0064] The droplet deposition prediction model is constructed based on the number of droplet point clouds and the amount of droplet deposition in each sample region according to the operation parameters of each sample.

[0065] Figure 2 This is a schematic diagram of the structure of the drone spraying control system provided by the present invention, as shown below. Figure 2 As shown, it includes:

[0066] Drones, drone real-time tracking platforms, digital radios, and industrial control computers; drone operators can intervene in the drone's pesticide application process through the industrial control computer.

[0067] The drone is equipped with a GPS antenna to collect its location information;

[0068] Digital radios include receivers and transmitters to enable communication with drones and drone real-time tracking platforms;

[0069] The UAV real-time tracking platform has a cuboid frame. Using the platform's initial position as a reference, the X-axis is perpendicular to the guide rails and lies in the same plane as the two guide rails. The Y-axis runs along the guide rails, and the Z-axis is perpendicular to the plane containing the two guide rails, constructing an XYZ Cartesian coordinate system. The cuboid frame is equipped with 101 LiDAR sensors and distance sensors. The distance sensors are located on the LiDARs, which can move along the Z-axis. The LiDAR's height can be adjusted in real-time according to the crop canopy height, determined by the actual operating conditions. While the drone real-time tracking platform moves on the track, LiDAR is used to collect sample droplet point clouds during the drone's application of pesticides to the crop canopy; distance sensors are used to collect the distance between the drone real-time tracking platform and the drone, ensuring that all 101 LiDARs are at the same vertical height, and that the distance sensors ensure that the LiDARs and the drone always maintain a distance of d meters at different flight speeds, achieving real-time tracking and detection functions, reflecting the spatial changes of droplets throughout the entire flight path, and ensuring real-time monitoring and adjustment of drone pesticide application parameters in the later stages.

[0070] Monitoring droplet deposition quality, pesticide application decisions, and precise control of pesticide application are key aspects of variable-rate spraying (VRF) for wheat. During the application process, the wind field generated by the downrotor of the drone has a significant impact on pesticide deposition. The LiDAR detector model TIM351-2134001 can be selected, with a scanning angle of 270 degrees, a measurement range of 0.05 meters to 10 meters, and parameters set to 15 Hz.

[0071] 101 LiDAR detectors are fixedly mounted on the drone real-time tracking platform. Each LiDAR is 0.6 meters away from the crop canopy in the Z-axis direction, and each LiDAR has a distance sensor above it to ensure that the center of the LiDAR scanning is 0.6m away from the drone in the Z-axis direction. The drone's flight speed is v, the spray flow rate is q, and the flight altitude is 1.2m. The flight altitude is specifically the distance between the nozzle and the crop canopy.

[0072] Optionally, the step of constructing the droplet deposition prediction model based on the number of droplet point clouds and the amount of droplet deposition in each sample region for each sample operation parameter includes:

[0073] Based on the number of droplet points and the amount of droplet deposition in each sample area under multiple sample operation parameters of the UAV, the linear relationship between the number of droplet points and the amount of droplet deposition in the UAV operation, as well as the deposition relationship between the amount of droplet deposition and the flight speed and the application rate, are determined.

[0074] Based on the linear relationship and the deposition relationship, the quantitative relationship between the flight speed, the application rate, and the number of droplet points is determined;

[0075] Based on the aforementioned quantitative relationships and the area of ​​the sample region, the density relationship between flight speed, application rate, and droplet density is determined.

[0076] Based on the density relationship, the droplet deposition prediction model is constructed.

[0077] Figure 3 This is a schematic diagram of the distribution of fog droplet point clouds provided by the present invention, as shown below. Figure 3 As shown, experiments were conducted by UAVs at different flight speeds v and application rates q to construct an application decision database model. This model can analyze the actual distribution range, deposition amount, and deposition density of droplet point clouds based on the distribution range, deposition amount, and deposition density of droplets. Since there is a linear relationship between traditional measurements and LiDAR scanning, the deposition density is the density distribution of droplets deposited on the XOY plane. Based on the droplet deposition prediction model, not only can the parameters such as the droplet deposition amount and deposition density within each small square of 5×5m be predicted, but also the flight speed and application rate of the UAV application operation can be predicted accordingly.

[0078] In actual operation, a specific pesticide application decision database is generated by combining the pesticide application prescription map of crop diseases and pests, with each small grid area being 5×5m, and combining the point cloud droplet deposition range and deposition density distribution map. The data of real-time monitoring of droplets by LiDAR is compared with the pesticide application decision database. If there is a deviation from the pesticide application decision database, the drone's flight speed and pesticide application rate are adjusted in real time to ensure the most accurate pesticide application.

[0079] In the pesticide application prescription map, the distribution data of pesticide application requirements are determined based on the actual application needs of each part of the target plot. The point density is linearly correlated with the application amount; areas with higher point density are areas with more severe pests and diseases, and correspondingly require larger application amounts. In addition, the application amount can be flexibly adjusted according to the type of pesticide and its actual effects.

[0080] To investigate the distribution of droplet points in different regions of space, 101 (i = 1, 2, ..., 101) single-threaded LiDARs can be used to simultaneously scan the point cloud data of the area between the nozzle below the UAV and the crop canopy (1.2 meters high) in a direction parallel to the YOZ plane. The spacing between the scanning planes of each LiDAR is 0.05m to ensure that the point cloud within a 5m wide spray width can be completely scanned, thus constructing a three-dimensional distribution of droplet points.

[0081] All point clouds acquired by LiDAR scans from 1 to 101 were divided into 5×5×1.2 (m) rectangular intervals along the Y-axis at 5-meter intervals. The scanning time t for each rectangular interval was:

[0082]

[0083] Under the same operating parameters, the LiDAR scanning time t for droplet point clouds is selected as:

[0084] t2-t1=t (2)

[0085] Where t1 is the start scanning time of any cuboid interval; t2 is the end scanning time of any cuboid interval.

[0086] Figure 4 This is a schematic diagram of coordinate system transformation provided by the present invention, as shown below. Figure 4 As shown, a three-dimensional polar coordinate system is established with the starting position of each LiDAR as the origin. The polar coordinates of the i-th LiDAR plotting point are (α... i r i The calculation formula is as follows:

[0087]

[0088] Among them, RangeValue i (j) represents the j-th data point from the i-th LiDAR; scaleFactor is the scaling factor; startAngle i angularResolution is the starting scan angle of the i-th LiDAR; angularResolution is the scan angle resolution.

[0089] During the time interval t1 to t2, the spatial coordinates of the LiDAR-scanned droplet point cloud will be transformed from polar coordinates to Cartesian coordinates. The origin of the Cartesian coordinate system is also the starting position of each LiDAR. For example, the Cartesian coordinates (y, z) of point R are:

[0090]

[0091] Where α represents the elevation angle at which the LiDAR detector scans particles; r represents the radial distance from the observation point to the LiDAR detector; and i represents the i-th LiDAR.

[0092] From formula (2), we know that the cumulative operation time within the 5×5×1.2 (unit: m) cuboid interval is t, and the number of droplet points in a single LiDAR scan is P. i (i = 1, 2, ..., 101), then during the drone spraying process with the nth set of operational parameters, the number of sample droplet point clouds P along the entire flight path of the drone. n The calculation is as follows:

[0093]

[0094] The above method can calculate the number of droplets in the point cloud in the crop interval between the UAV and the crop canopy throughout the entire flight path. The data measured by this method can reproduce the deposition and change process of droplets during UAV application, providing a visual and quantitative analysis method for studying the deposition quality of pesticide application.

[0095] The area directly beneath the drone's spraying area along a single flight path was divided into several 5×5×1.2 meter squares, and the deposition volume was collected using 5×70 meter coated paper below the flight path. At different flight speeds (v) and spraying rates (q), LiDAR scanning was used to acquire corresponding spatial point clouds. These point clouds were then divided into 5×5×1.2 meter cuboid sections, and the spatial point clouds within these cuboid sections were converted into droplet deposition data for a 5×5 meter square on the XOY plane.

[0096] Figure 5 This is a schematic diagram of the droplet deposition amount provided by the present invention, as shown below. Figure 5 As shown, a 5×5 meter sheet of coated paper is placed directly below the flight path. A correlation model is then developed between the number of points and the deposition density corresponding to each 5×5 meter planar point cloud map and the deposition amount and density of the 5×5 meter sheet of coated paper. This yields a database of application models for operational parameters—deposition amount, deposition density, deposition range, and planar point cloud maps.

[0097] Assuming no natural wind, and identical temperature and humidity conditions, with the UAV flying at an altitude H above the crop canopy, at a flight speed v0, and with a pesticide application rate q0, the number of droplet points in the spatial fog cloud under the influence of the rotor wind field, as obtained by real-time LiDAR scanning, is P0, and the corresponding droplet deposition amount on coated paper is Q0. Under different pesticide application parameters: v0, v1, ..., v n and q0, q1, ..., q n .

[0098] v under different operating parameters n q n The number of sample fog droplet point clouds corresponding to a 5×5 meter XOY plane grid is P. n The corresponding sample droplet deposition amount is Q. n The number of sample fog droplet point clouds P under each set of operational parameters n With sample droplet deposition amount Q n There is a linear correlation between them:

[0099]

[0100] Where P is the number of fog droplet point clouds; Q is the amount of fog droplet deposition; K is the correlation coefficient; and Z0 is a constant.

[0101] Under different flight velocities v and application rates q, the depositional relationship between droplet deposition Q and v and q can be obtained as follows:

[0102] Q = cq + dv + G (7)

[0103] Where c and d represent coefficients; G represents a constant.

[0104] Combining (6) and (7), we can obtain the quantitative relationship between flight speed, drug application rate, and the number of droplet points:

[0105] P = K(cq + dv + G) - Z0 (8)

[0106] The number of droplet points P is the number of droplet points in a 5×5m XOY plane grid. Therefore, a 5×5m area within the XOY plane is used to calculate the droplet density. The density relationship between flight speed, application rate, and droplet density is as follows:

[0107]

[0108] Using formula (9) as the droplet deposition prediction model for UAVs, after inputting the UAV's flight speed and pesticide application rate, the droplet deposition prediction model will calculate the corresponding predicted droplet density. The UAV model and the droplet deposition prediction model are in one-to-one correspondence.

[0109] According to the UAV pesticide application control method provided by the present invention, by extracting the relationship between the operation parameters and droplet density during the UAV pesticide application process, the variation law of droplets in the actual deposition process can be restored to the greatest extent. Furthermore, the spatial distribution and deposition density of droplets under the action of different UAV rotor wind fields can be intuitively displayed in a visual form, which lays the foundation for constructing pesticide application operation parameters and provides data support for decision-making and implementation of UAV pesticide application flight attitude adjustment and pesticide application flow control.

[0110] Further, in step S2, the operation parameters are input into the droplet deposition prediction model of the UAV to obtain the predicted droplet density output by the droplet deposition prediction model; the predicted droplet density is calculated by the droplet deposition prediction model based on the operation parameters to determine the droplet density and dosage.

[0111] The drone's flight speed and the spraying flow rate are input into the drone's droplet deposition prediction model. The droplet deposition prediction model calculates the mathematical relationship between the flight speed and the spraying flow rate to obtain the predicted droplet density corresponding to the current flight speed and spraying flow rate. That is, the droplet density of the drone during the ground spraying process using these operating parameters is the predicted droplet density.

[0112] Further, in step S3, based on the location information, the predicted droplet density is compared and analyzed with the pesticide application prescription map of the target plot to determine the parameter adjustment amount of the UAV, which is used to adjust the operation parameters.

[0113] The predicted droplet density is compared with the droplet density that should be applied at the current position in the application prescription map. If the two are inconsistent, the parameters of the UAV need to be adjusted. The parameter adjustment amount of the UAV is calculated and the operation parameters of the UAV are adjusted according to the parameter adjustment amount. If the two are consistent, the parameter adjustment amount is 0 and the UAV remains in its current state.

[0114] The drone spraying control method provided by this invention uses drone operation parameters to predict the droplet density during the spraying process and compares the predicted amount with the prescription map. In this way, the operation parameters are adjusted in real time according to the spraying quality during the drone spraying process, thereby improving the utilization rate of the drug, ensuring the spraying quality, and realizing precise spraying.

[0115] Optionally, the application prescription map is obtained based on the following steps:

[0116] Acquire a hyperspectral image of the target site;

[0117] Based on the hyperspectral image, the extent and severity of pests and diseases in the target plot are determined.

[0118] Based on the extent and severity of the pests and diseases, a pesticide application prescription map is determined for the target plot; the pesticide application prescription map includes the distribution of pesticide application requirements within the target plot.

[0119] Before applying pesticides to the target plot, hyperspectral images of the target plot are collected. Then, based on the hyperspectral images, pest and disease diagnosis is performed on the crops within the target plot to determine the range and severity of pest and disease occurrence. Based on the severity, the amount of pesticide to be applied at that location is determined. Furthermore, based on the offset error of droplets during the deposition process caused by the wind field of the UAV's rotor, a pesticide prescription map considering the expected offset of the entire target plot is obtained. This reduces droplet offset from the target, improves pesticide utilization, and enables precise control of UAV pesticide application to the target area.

[0120] Figure 6 This is a schematic diagram of the prescription diagram provided by the present invention, such as... Figure 6 As shown, the dot density is linearly related to the amount of pesticide applied. Areas with higher dot density are areas with more severe pests and diseases, and the corresponding amount of pesticide applied is greater.

[0121] This invention conducts multiple experiments on UAVs at different flight speeds and constructs a droplet deposition prediction model. In actual UAV operations, the pesticide application strategy can be adjusted in real time based on the droplet deposition prediction model to ensure that the pesticide atomization droplets deviate from the target to the minimum and maximize the pesticide utilization rate.

[0122] Optionally, the step of comparing and analyzing the predicted droplet density with the pesticide application prescription map of the target plot based on the location information to determine the parameter adjustment amount of the UAV includes:

[0123] The required dosage of the drug corresponding to the location information is determined in the drug application prescription diagram;

[0124] The predicted droplet density is compared and analyzed with the required dosage to generate a dosage error.

[0125] The parameter adjustment amount is determined based on the dosage error.

[0126] The required dosage and specific application coordinates can be determined from the application prescription map. Combined with the droplet density output by the droplet deposition prediction model, a dosage error-parameter adjustment application decision database is constructed. In actual operation, the droplet density output by the droplet deposition prediction model is matched and compared with the application prescription map in real time. If there is an application deviation, the application decision database is used to directly match the operation parameters for precise adjustment of application.

[0127] Specifically, the required amount of pesticide at the current location of the drone is determined in the pesticide application prescription map, and the amount of pesticide can be based on the droplet density;

[0128] The difference between the droplet density output by the droplet deposition prediction model and the required dosage is used to obtain the dosage error. If the dosage error is positive, the dosage exceeds the expectation, and the parameter adjustment can be the increase in the UAV's flight speed or the decrease in the dosage flow rate. If the dosage error is negative, the dosage is lower than the expectation, and the parameter adjustment can be the decrease in the UAV's flight speed or the increase in the dosage flow rate.

[0129] In addition, the quality of pesticide application by drones can be evaluated. The droplet density output by the droplet deposition prediction model during the entire application process can be analyzed to obtain the actual droplet deposition map. The actual droplet deposition map can be compared and analyzed with the pesticide prescription map to obtain the overall dosage error between the two. The final evaluation result of the pesticide application quality can be obtained based on the dosage error.

[0130] According to the drone spraying control method provided by the present invention, spraying deviation is reduced by jointly adjusting the drone's flight speed and spraying flow rate, a drone spraying decision implementation database is constructed, and the drone can complete precise spraying operations for different crops.

[0131] Figure 7 This is the second flowchart of the drone spraying control method provided by the present invention, as shown below. Figure 7 As shown, it includes:

[0132] In the construction phase of the droplet deposition prediction model, multiple sets of UAV operational parameters were experimented with, including the UAV's flight speed v and spray rate q, and LiDAR point cloud and deposition amount (P) were obtained. n With Q n (Linear correlation); Collect the deposition amount and density of small planar grids, and then obtain the quantitative relationship between flight speed, application rate and droplet point cloud number: P=K(cq+dv+G)-Z0, to construct a visual deposition range model, i.e. It also obtains the pesticide application prescription map of the target plot, which includes the pesticide application amount requirement and the pesticide application coordinate area;

[0133] During the drone application phase, the drone's operational parameters are acquired and input into the droplet deposition prediction model to obtain the predicted droplet density.

[0134] The predicted droplet density is compared with the pesticide application requirement at the current location of the drone to obtain the pesticide application error. Based on the pesticide application error, the corresponding parameter adjustment amount is matched in the pesticide application decision database.

[0135] In addition, LiDAR scanning is used in actual real-time operations to obtain deposition parameters, which are then compared with the drug application decision database to determine whether they are consistent with expectations, thus enabling real-time control.

[0136] The UAV pesticide application control method provided by this invention visualizes the entire process of pesticide droplet deposition during single-flight operation and provides a data support model for UAV pesticide application. It utilizes LiDAR to track and acquire the spatial distribution, deposition range, and deposition density of the atomized droplets in real time. The pesticide deposition prediction model provides data support for precise pesticide application, and the LiDAR real-time detection and tracking are matched and checked against the prescription map and deposition model. This enables real-time monitoring and control of UAV pesticide application.

[0137] The drone pesticide application control system provided by the present invention is described below. The drone pesticide application control system described below can be referred to in correspondence with the drone pesticide application control method described above.

[0138] The present invention also provides a drone spraying control system, including a drone, a drone real-time tracking platform, a digital radio, and an industrial control computer;

[0139] The drone is used for spraying operations;

[0140] The real-time tracking platform for the unmanned aerial vehicle is equipped with multiple lidar sensors.

[0141] The lidar is used to collect droplet point cloud data during the spraying operation of the UAV, and the droplet point cloud data is used to construct a droplet deposition prediction model.

[0142] The drone is equipped with a GPS antenna, which is used to collect the drone's location information and transmit the location information to the industrial control computer via the digital radio.

[0143] The multiple lidars transmit the fog droplet point cloud data to the industrial control computer via the digital radio.

[0144] The industrial control computer is equipped with a processor; it also includes a memory and a program or instruction stored in the memory and executable on the processor. When the program or instruction is executed by the processor, it performs the drone spraying control method as described in any of the above embodiments.

[0145] LiDAR is responsible for real-time monitoring of the actual deposition area of ​​the spray droplets and the changing patterns of the deposition process.

[0146] The drone-based pesticide application control system provided by this invention predicts the droplet density during the application process using drone operating parameters and compares the predicted value with the prescription map. This allows for real-time adjustment of operating parameters based on application quality during drone application, improving drug utilization, ensuring application quality, and achieving precise application. The industrial control computer provided by this invention is described below, and its description corresponds to the drone-based pesticide application control method described above.

[0147] Figure 8 This is a structural schematic diagram of the industrial control computer provided by the present invention, as shown below. Figure 8 As shown, it includes:

[0148] The acquisition module 801 is used to acquire the location information of the UAV and the operation parameters of the UAV spraying the target plot. The operation parameters include: flight speed and spraying flow rate.

[0149] The input module 802 is used to input the operation parameters into the droplet deposition prediction model of the UAV and obtain the predicted droplet density output by the droplet deposition prediction model; the predicted droplet density is obtained by the droplet deposition prediction model from the operation parameters to calculate the droplet density and dosage.

[0150] The analysis module 803 is used to compare and analyze the predicted droplet density with the pesticide application prescription map of the target plot based on the location information, so as to determine the parameter adjustment amount of the UAV, and the parameter adjustment amount is used to adjust the operation parameters.

[0151] During the operation of the industrial control computer, the acquisition module 801 acquires the location information of the UAV and the operation parameters of the UAV spraying the target plot, including flight speed and spraying flow rate; the input module 802 inputs the operation parameters into the UAV's droplet deposition prediction model to obtain the predicted droplet density output by the droplet deposition prediction model; the predicted droplet density is calculated by the droplet deposition prediction model based on the operation parameters; the analysis module 803 compares and analyzes the predicted droplet density with the spraying prescription map of the target plot based on the location information to determine the parameter adjustment amount of the UAV, which is used to adjust the operation parameters.

[0152] According to the industrial control computer provided by the present invention, the droplet density during the application process is predicted using the operation parameters of the UAV, and the predicted amount is compared with the prescription map. Thus, during the application process of the UAV, the operation parameters are adjusted in real time according to the application quality, thereby improving the utilization rate of the drug, ensuring the application quality, and realizing precise application.

[0153] Figure 9 This is a schematic diagram of the structure of the electronic device provided by the present invention, such as... Figure 9 As shown, the electronic device may include a processor 910, a communication interface 920, a memory 930, and a communication bus 940, wherein the processor 910, the communication interface 920, and the memory 930 communicate with each other via the communication bus 940. The processor 910 can call logical instructions in the memory 930 to execute a drone spraying control method. This method includes: acquiring the drone's location information and the drone's spraying operation parameters for the target plot, the operation parameters including flight speed and spraying flow rate; inputting the operation parameters into the drone's droplet deposition prediction model to obtain the predicted droplet density output by the droplet deposition prediction model; the predicted droplet density is calculated by the droplet deposition prediction model based on the operation parameters using droplet density spraying rate; and based on the location information, comparing and analyzing the predicted droplet density with the spraying prescription map of the target plot to determine the drone's parameter adjustment amount, the parameter adjustment amount being used to adjust the operation parameters.

[0154] Furthermore, the logical instructions in the aforementioned memory 930 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0155] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the drone spraying control method provided by the above methods. The method includes: acquiring the location information of the drone and the operation parameters of the drone spraying the target plot, the operation parameters including: flight speed and spraying flow rate; inputting the operation parameters into the drone's droplet deposition prediction model to obtain the predicted droplet density output by the droplet deposition prediction model; the predicted droplet density is calculated by the droplet deposition prediction model based on the operation parameters; and based on the location information, comparing and analyzing the predicted droplet density with the spraying prescription map of the target plot to determine the parameter adjustment amount of the drone, the parameter adjustment amount being used to adjust the operation parameters.

[0156] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the UAV spraying control method provided by the above methods. The method includes: acquiring the location information of the UAV and the operation parameters of the UAV spraying a target plot, the operation parameters including: flight speed and spraying flow rate; inputting the operation parameters into a droplet deposition prediction model of the UAV to obtain a predicted droplet density output by the droplet deposition prediction model; the predicted droplet density is obtained by the droplet deposition prediction model calculating the droplet density and spraying amount based on the operation parameters; and, based on the location information, comparing and analyzing the predicted droplet density with a spraying prescription map of the target plot to determine the parameter adjustment amount of the UAV, the parameter adjustment amount being used to adjust the operation parameters.

[0157] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0158] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, 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 can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0159] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for controlling pesticide application by an unmanned aerial vehicle (UAV), characterized in that, include: The location information of the drone and the operation parameters of the drone spraying the target plot are obtained, including flight speed and spraying flow rate; The operation parameters are input into the droplet deposition prediction model of the UAV to obtain the predicted droplet density output by the droplet deposition prediction model; the predicted droplet density is calculated by the droplet deposition prediction model based on the operation parameters to determine the droplet density and dosage. The pesticide application rate requirement corresponding to the location information is determined in the pesticide application prescription map of the target plot; the pesticide application prescription map of the target plot is obtained based on the following steps: acquiring a hyperspectral image of the target plot; determining the range and severity of pests and diseases in the target plot based on the hyperspectral image; determining the pesticide application prescription map of the target plot based on the range and severity of pests and diseases; the pesticide application prescription map includes the distribution of the pesticide application rate requirement within the target plot; The predicted droplet density is compared and analyzed with the required dosage to generate a dosage error. Based on the dosage error, the parameter adjustment amount of the UAV is determined, and the parameter adjustment amount is used to adjust the operation parameters.

2. The drone spraying control method according to claim 1, characterized in that, Before inputting the operational parameters into the UAV's droplet deposition prediction model and obtaining the predicted droplet density output by the droplet deposition prediction model, the method further includes: The number of droplet point clouds and the amount of droplet deposition in multiple sample regions of the UAV under different sample operation parameters are obtained; the sample operation parameters include: sample flight speed and sample drug application rate. The droplet deposition prediction model is constructed based on the number of droplet point clouds and the amount of droplet deposition in each sample region according to the operation parameters of each sample.

3. The drone spraying control method according to claim 2, characterized in that, The droplet deposition prediction model is constructed based on the number of droplet point clouds and the amount of droplet deposition in each sample region according to the operational parameters of each sample, including: Based on the number of droplet points and the amount of droplet deposition in each sample area under multiple sample operation parameters of the UAV, the linear relationship between the number of droplet points and the amount of droplet deposition in the UAV operation, as well as the deposition relationship between the amount of droplet deposition and the flight speed and the application rate, are determined. Based on the linear relationship and the deposition relationship, the quantitative relationship between the flight speed, the application rate, and the number of droplet points is determined; Based on the aforementioned quantitative relationships and the area of ​​the sample region, the density relationship between flight speed, application rate, and droplet density is determined. Based on the density relationship, the droplet deposition prediction model is constructed.

4. A drone-based pesticide application control system, characterized in that, This includes drones, drone real-time tracking platforms, digital radios, and industrial control computers; The drone is used for spraying operations; The real-time tracking platform for the unmanned aerial vehicle is equipped with multiple lidar sensors. The lidar is used to collect droplet point cloud data during the spraying operation of the UAV, and the droplet point cloud data is used to construct a droplet deposition prediction model. The drone is equipped with a GPS antenna, which is used to collect the drone's location information and transmit the location information to the industrial control computer via the digital radio. The multiple lidars transmit the fog droplet point cloud data to the industrial control computer via the digital radio. The industrial control computer is equipped with a processor; it also includes a memory and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction is executed by the processor to perform the drone spraying control method as described in any one of claims 1-3.

5. An industrial control computer, characterized in that, include: The acquisition module is used to acquire the location information of the UAV and the operation parameters of the UAV spraying the target plot. The operation parameters include: flight speed and spraying flow rate. The input module is used to input the operation parameters into the droplet deposition prediction model of the UAV and obtain the predicted droplet density output by the droplet deposition prediction model; the predicted droplet density is calculated by the droplet deposition prediction model based on the operation parameters to determine the droplet density and dosage. An analysis module is used to determine the pesticide application rate requirement corresponding to the location information in the pesticide application prescription map of the target plot; the pesticide application prescription map of the target plot is obtained based on the following steps: acquiring a hyperspectral image of the target plot; determining the range and severity of pests and diseases in the target plot based on the hyperspectral image; determining the pesticide application prescription map of the target plot based on the range and severity of pests and diseases; the pesticide application prescription map includes the distribution of pesticide application rate requirements within the target plot; The analysis module is also used to compare and analyze the predicted droplet density with the required dosage to generate a dosage error. The analysis module is also used to determine the parameter adjustment amount of the UAV based on the dosage error, and the parameter adjustment amount is used to adjust the operation parameters.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the drone drug delivery control method as described in any one of claims 1-3.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the drone drug application control method as described in any one of claims 1-3.

8. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the drone drug application control method as described in any one of claims 1-3.

Images