Precise spraying method of plant protection unmanned aerial vehicle for litchi orchard

Abstract

The invention relates to a plant protection unmanned aerial vehicle accurate spraying method for a litchi orchard, and belongs to the technical field of unmanned aerial vehicle spraying. And carrying out evaluation analysis on the fogdrop charged charges sprayed by the spraying equipment of the current plant protection unmanned aerial vehicle based on the fogdrop charge characteristic prediction result to obtain an evaluation analysis result, and finally generating a first control strategy or a second control strategy based on the evaluation analysis result. And dynamically adjusting the operation working parameter data of the plant protection unmanned aerial vehicle spraying equipment based on the first control strategy or the second control strategy. According to the method, analysis is carried out by combining the operation working parameter data of the plant protection unmanned aerial vehicle spraying equipment and the charged quantity of the fog drops under the environment parameters, scene analysis can be carried out on the spraying condition of the plant protection unmanned aerial vehicle in the lychee garden area according to the charged quantity of the fog drops, and then the spraying precision of the plant protection unmanned aerial vehicle for the spraying task is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of drone spraying, and in particular to a precision spraying method of a plant protection drone used in a litchi orchard. Background Art

[0002] As a good fruit in Lingnan, litchi has high nutritional and economic value and is given the title of "King of Fruits". However, since litchi grows in tropical and subtropical areas with high temperature and high humidity all year round, diseases and pests are frequent, which seriously affects the quality and yield of litchi. Therefore, strengthening the effective chemical control of litchi diseases and pests is of great significance to the production and high yield of litchi. In my country, the main methods of pesticide spraying include manual, ground machinery and aerial spraying. The control of pests and diseases in orchards in hot areas still mainly relies on manual spraying operations such as backpack sprayers, pedal sprayers and motorized high-pressure spray guns. However, manual spraying has low efficiency, the spray quality is difficult to guarantee, and it is impossible to achieve fast and full coverage of plant protection spraying operations in a short time, which may delay the best time for prevention and control. In addition, due to the shortage of labor in orchards and the older average age of the labor force, it is urgent to develop efficient pesticide application technology with high degree of automation, time-saving and labor-saving. However, ground mechanical spraying has high cost, low pesticide utilization rate, and is difficult to operate in complex terrains such as mountains and hills. Plant protection drones have high operating efficiency and good maneuverability. They can effectively avoid the shortcomings of manual and ground mechanical spraying. They can become a new technology for large-scale rapid prevention and control of fruit tree diseases and pests, helping fruit farmers to save costs and increase efficiency. However, electrostatic droplets are easily affected by the environment, which will lead to poor deposition effects and reduce the spray accuracy in litchi orchards. Summary of the invention

[0003] The present invention overcomes the shortcomings of the prior art and provides a precise spraying method for plant protection drones in litchi orchards.

[0004] To achieve the above object, the technical solution adopted by the present invention is:

[0005] The first aspect of the present invention provides a precision spraying method for a plant protection drone used in a litchi orchard, comprising the following steps:

[0006] Obtaining operating parameter data of a plant protection UAV spray device, and constructing a droplet charge characteristic prediction model based on a generative adversarial network and the operating parameter data of the plant protection UAV spray device;

[0007] Acquire environmental characteristic data in a litchi orchard, and obtain a droplet charge characteristic prediction result by using the droplet charge characteristic prediction model in combination with the environmental characteristic data in the litchi orchard;

[0008] Based on the droplet charge characteristic prediction result, the charge of the droplets sprayed by the current plant protection UAV spray equipment is evaluated and analyzed to obtain the evaluation and analysis result;

[0009] A first control strategy or a second control strategy is generated based on the evaluation and analysis result, and the operating parameter data of the plant protection UAV spray equipment is dynamically adjusted based on the first control strategy or the second control strategy.

[0010] Furthermore, in this method, a prediction model for the charge characteristics of droplets is constructed based on the generative adversarial network and the operating parameter data of the plant protection UAV spray equipment, specifically:

[0011] A prediction model for the charge characteristics of droplets is constructed based on a generative adversarial network, and electric field strength characteristic data of the plant protection UAV spray equipment is obtained according to the operating parameter data of the plant protection UAV spray equipment;

[0012] Based on the electric field strength characteristic data of the plant protection UAV spray equipment, an estimate is made to obtain the charge characteristic data of the droplets when the plant protection UAV spray equipment is working, and according to the charge characteristic data of the droplets when the plant protection UAV spray equipment is working, a droplet charge characteristic data set is constructed under different operating parameter data;

[0013] Inputting the droplet charge characteristic data set under different operating parameter data into the droplet charge characteristic prediction model, and setting a number of environmental parameters, and using the several environmental parameters as constraint conditions;

[0014] The droplet charge characteristic prediction model is trained based on the constraint conditions to obtain a droplet charge characteristic prediction model that meets expectations.

[0015] Furthermore, in this method, environmental characteristic data in the litchi orchard are obtained, and the droplet charge characteristic prediction result is obtained by the droplet charge characteristic prediction model in combination with the environmental characteristic data in the litchi orchard, specifically:

[0016] Acquire environmental characteristic data in a litchi orchard and real-time operating parameter data of a plant protection UAV spray device, and input the real-time operating parameter data of the plant protection UAV spray device and the environmental characteristic data in the litchi orchard into the droplet charge characteristic prediction model;

[0017] Generate an initial droplet charge characteristic prediction result based on the real-time operating parameter data of the plant protection UAV spray equipment through a generator, and input the initial droplet charge characteristic prediction result into a discriminator for judgment;

[0018] If the discriminator accepts the initial droplet charge feature prediction result, the initial droplet charge feature prediction result is used as the final prediction result, and the final prediction result is output as the droplet charge feature prediction result;

[0019] If the discriminator does not accept the initial droplet charge feature prediction result, the next droplet charge feature prediction result is generated until the discriminator accepts the current droplet charge feature prediction result and outputs the final prediction result as the droplet charge feature prediction result.

[0020] Furthermore, in this method, based on the prediction result of the droplet charge characteristics, the charge of the droplets sprayed by the current plant protection UAV spray equipment is evaluated and analyzed to obtain the evaluation and analysis results, specifically:

[0021] Setting a droplet charge characteristic data threshold, counting the droplet charge characteristic prediction results, obtaining the distribution characteristics of the droplet charge characteristic prediction results in space, and constructing a droplet charge spatial distribution map according to the distribution characteristics of the droplet charge characteristic prediction results in space;

[0022] Counting the proportion of the charge of the droplets in the droplet charge spatial distribution diagram that is lower than the droplet charge characteristic data threshold, and determining whether the proportion of the charge of the droplets in the droplet charge spatial distribution diagram that is lower than the droplet charge characteristic data threshold is greater than a preset proportion data threshold;

[0023] When the proportion of the charge amount of the droplets in the droplet charge spatial distribution diagram that is lower than the droplet charge characteristic data threshold is greater than a preset proportion data threshold, an abnormal spray evaluation result is generated;

[0024] When the charge amount of the droplets in the droplet charge spatial distribution diagram is lower than the droplet charge characteristic data threshold and the proportion of the data is not greater than the preset proportion data threshold, a normal spray evaluation result is generated, and an evaluation analysis result is generated based on the abnormal spray evaluation result or the normal spray evaluation result.

[0025] Furthermore, in this method, a first control strategy or a second control strategy is generated based on the evaluation and analysis result, specifically:

[0026] When the evaluation and analysis result is an abnormal spray evaluation result, a first control strategy is generated, and when the evaluation and analysis result is a normal spray evaluation result, a second control strategy is generated;

[0027] The first control strategy or the second control strategy is output as an output result.

[0028] Furthermore, in this method, the operating parameter data of the plant protection UAV spray equipment is dynamically adjusted based on the first control strategy or the second control strategy, specifically including:

[0029] When the second control strategy is used, the control is performed according to the operating parameter data of the current plant protection UAV spray equipment;

[0030] When the first control strategy is adopted, a genetic algorithm is introduced, a genetic algebra is set based on the genetic algorithm, and inheritance is performed based on the genetic algebra to reset the operating parameter data of the plant protection UAV spray equipment;

[0031] Obtain the percentage data of the charge amount of the droplets corresponding to the reset operation parameter data of the plant protection UAV spray equipment being lower than the droplet charge characteristic data threshold value, and when the percentage data is not greater than the preset percentage data threshold value, the inheritance ends, and the reset operation parameter data of the plant protection UAV spray equipment is output;

[0032] When the proportion data is not greater than the preset proportion data threshold, inheritance continues until the proportion data is no greater than the preset proportion data threshold, outputs the reset operating parameter data of the plant protection UAV spray equipment, and controls according to the reset operating parameter data of the plant protection UAV spray equipment.

[0033] The second aspect of the present invention provides a plant protection drone precision spraying system for litchi orchards, comprising a memory and a processor, wherein the memory includes a plant protection drone precision spraying method program for litchi orchards, and when the plant protection drone precision spraying method program for litchi orchards is executed by the processor, any step of the plant protection drone precision spraying method for litchi orchards is implemented.

[0034] The third aspect of the present invention provides a computer-readable storage medium, including a program for a plant protection drone precision spraying method for a litchi orchard. When the program for the plant protection drone precision spraying method for a litchi orchard is executed by a processor, any step of the plant protection drone precision spraying method for a litchi orchard is implemented.

[0035] The present invention solves the defects existing in the background technology and has the following beneficial effects:

[0036] The present invention obtains the operation parameter data of the plant protection UAV spray equipment, constructs a droplet charge characteristic prediction model based on the generative adversarial network and the operation parameter data of the plant protection UAV spray equipment, and then obtains the environmental characteristic data in the litchi orchard, and obtains the droplet charge characteristic prediction result through the droplet charge characteristic prediction model in combination with the environmental characteristic data in the litchi orchard, thereby evaluating and analyzing the charge of the droplets sprayed by the current plant protection UAV spray equipment based on the droplet charge characteristic prediction result, obtaining the evaluation and analysis result, and finally generating the first control strategy or the second control strategy based on the evaluation and analysis result, and dynamically adjusting the operation parameter data of the plant protection UAV spray equipment based on the first control strategy or the second control strategy. The present invention analyzes the charge amount of the droplets under the combination of the operation parameter data of the plant protection UAV spray equipment and the environmental parameters, and can perform scenario analysis on the spraying situation of the plant protection UAV in the litchi orchard according to the charge amount of the droplets, thereby improving the spraying accuracy of the plant protection UAV in the spray task. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, drawings of other embodiments can be obtained based on these drawings without paying creative work.

[0038] Figure 1 The overall flow chart of the precision spraying method of plant protection drones used in litchi orchards is shown;

[0039] Figure 2 The system block diagram of the plant protection drone precision spraying system for litchi orchards is shown. DETAILED DESCRIPTION

[0040] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0041] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0042] like Figure 1 As shown, the first aspect of the present invention provides a precision spraying method for plant protection drones in litchi orchards, comprising the following steps:

[0043] S102: Acquire the operating parameter data of the plant protection UAV spray equipment, and build a droplet charge characteristic prediction model based on the generative adversarial network and the operating parameter data of the plant protection UAV spray equipment;

[0044] Exemplarily, the operating parameter data of the spray equipment of the plant protection UAV includes the flight speed and flight altitude of the plant protection UAV, the electric field strength data of the spray equipment, the spraying speed of the spray equipment, the rotation speed of the spray equipment and other data.

[0045] S104: Acquire environmental characteristic data in the litchi orchard, and obtain a droplet charge characteristic prediction result by using a droplet charge characteristic prediction model in combination with the environmental characteristic data in the litchi orchard;

[0046] S106: Based on the prediction result of the droplet charge characteristics, the charge of the droplets sprayed by the current plant protection UAV spray equipment is evaluated and analyzed to obtain the evaluation and analysis result;

[0047] S108: Generate a first control strategy or a second control strategy based on the evaluation and analysis results, and dynamically adjust the operating parameter data of the plant protection UAV spray equipment based on the first control strategy or the second control strategy.

[0048] It should be noted that the present invention combines the operating parameter data of the plant protection UAV spray equipment and the charge of the droplets under environmental parameters for analysis, and can conduct scenario analysis on the spraying conditions of the plant protection UAV in the litchi orchard according to the charge of the droplets, thereby improving the spraying accuracy of the plant protection UAV in the spray task.

[0049] Furthermore, in this method, the operating parameter data of the plant protection UAV spray equipment is obtained, and a droplet charge characteristic prediction model is constructed based on the generative adversarial network and the operating parameter data of the plant protection UAV spray equipment, specifically:

[0050] A prediction model for the charge characteristics of droplets is constructed based on the generative adversarial network, and the electric field strength characteristic data of the plant protection UAV spray equipment is obtained based on the operating parameter data of the plant protection UAV spray equipment;

[0051] Based on the electric field strength characteristic data of the plant protection UAV spray equipment, the charge characteristic data of the droplets of the plant protection UAV spray equipment when it is working is estimated, and the charge characteristic data of the droplets under different operating parameter data is constructed according to the charge characteristic data of the droplets of the plant protection UAV spray equipment when it is working;

[0052] Inputting the droplet charge characteristic data set under different operating parameter data into the droplet charge characteristic prediction model, and setting a number of environmental parameters as constraint conditions;

[0053] The droplet charge characteristic prediction model is trained based on the constraint conditions to obtain the droplet charge characteristic prediction model that meets the expectations.

[0054] It should be noted that the temperature, humidity, and electric field strength of the spray equipment will affect the charge of the droplets. If the electric field strength remains unchanged, the charge of the droplets will decrease under highly humid and high temperature conditions. The loss of charge will cause the droplets to shift during application, which will affect the accuracy of spraying. By fusing generative adversarial neural networks to construct a droplet charge feature prediction model, the charge of the droplets sprayed by the plant protection drone spray equipment can be predicted.

[0055] Furthermore, in this method, environmental characteristic data in the litchi orchard are obtained, and the droplet charge characteristic prediction result is obtained by using the droplet charge characteristic prediction model in combination with the environmental characteristic data in the litchi orchard, specifically:

[0056] Obtain environmental characteristic data in the litchi orchard and real-time operating parameter data of the plant protection UAV spray equipment, and input the real-time operating parameter data of the plant protection UAV spray equipment and environmental characteristic data in the litchi orchard into the droplet charge characteristic prediction model;

[0057] The generator generates the initial droplet charge characteristic prediction result based on the real-time operating parameter data of the plant protection UAV spray equipment, and inputs the initial droplet charge characteristic prediction result into the discriminator for judgment;

[0058] If the initial droplet charge feature prediction result is accepted in the discriminator, the initial droplet charge feature prediction result is used as the final prediction result, and the final prediction result is output as the droplet charge feature prediction result;

[0059] If the discriminator does not accept the initial droplet charge feature prediction result, the next droplet charge feature prediction result is generated until the discriminator accepts the current droplet charge feature prediction result and outputs the final prediction result as the droplet charge feature prediction result.

[0060] It should be noted that due to the differences in temperature and humidity in the litchi orchard, there will be certain differences in the charge of the droplets sprayed by the spray equipment. This method can predict the charge of the droplets of each plant protection drone when spraying in each litchi orchard.

[0061] Furthermore, in this method, the charge of the droplets sprayed by the current plant protection UAV spray equipment is evaluated and analyzed based on the prediction results of the droplet charge characteristics, and the evaluation and analysis results are obtained, specifically:

[0062] Setting a threshold value of droplet charge characteristic data, counting droplet charge characteristic prediction results, obtaining the distribution characteristics of the droplet charge characteristic prediction results in space, and constructing a droplet charge spatial distribution map according to the distribution characteristics of the droplet charge characteristic prediction results in space;

[0063] Exemplarily, the distribution characteristics of the predicted results of the droplet charge characteristics in space are the distribution characteristics of the charge on the droplets within the spraying range of the drone (such as circular areas, fan-shaped areas, etc.), thus forming a droplet charge spatial distribution map. The droplet charge spatial distribution map can estimate the charge distribution of droplets in different inner areas such as circular areas and fan-shaped areas (similar to the planetary orbit map in the solar system, where the blank area between planets represents the charge). Since there may be differences in temperature and humidity in each location, droplets at different locations will have different charges.

[0064] Counting the proportion of droplets whose charge amount is lower than the droplet charge characteristic data threshold in the droplet charge spatial distribution diagram, and determining whether the proportion of droplets whose charge amount is lower than the droplet charge characteristic data threshold in the droplet charge spatial distribution diagram is greater than a preset proportion data threshold;

[0065] When the proportion of the charge amount of the droplets in the droplet charge spatial distribution diagram that is lower than the droplet charge characteristic data threshold is greater than the preset proportion data threshold, an abnormal spray evaluation result is generated;

[0066] When the proportion of the charge amount of droplets in the droplet charge spatial distribution diagram that is lower than the droplet charge characteristic data threshold is not greater than the preset proportion data threshold, a normal spray evaluation result is generated, and an evaluation analysis result is generated based on the abnormal spray evaluation result or the normal spray evaluation result.

[0067] It should be noted that this method can be used to evaluate the distribution of the electric charge of droplets sprayed by the plant protection UAV spray equipment in space.

[0068] Furthermore, in this method, the first control strategy or the second control strategy is generated based on the evaluation and analysis results, specifically:

[0069] When the evaluation and analysis result is an abnormal spray evaluation result, a first control strategy is generated, and when the evaluation and analysis result is a normal spray evaluation result, a second control strategy is generated;

[0070] The first control strategy or the second control strategy is output as an output result.

[0071] Furthermore, in this method, the operating parameter data of the plant protection UAV spray equipment is dynamically adjusted based on the first control strategy or the second control strategy, specifically including:

[0072] When the second control strategy is used, the control is performed according to the operating parameter data of the current plant protection UAV spray equipment;

[0073] When the first control strategy is used, a genetic algorithm is introduced, a genetic algebra is set based on the genetic algorithm, and inheritance is performed based on the genetic algebra to reset the operating parameter data of the plant protection UAV spray equipment;

[0074] Obtain the percentage data of the charge of the droplets corresponding to the reset of the operating parameter data of the plant protection UAV spray equipment being lower than the droplet charge characteristic data threshold. When the percentage data is not greater than the preset percentage data threshold, the inheritance ends and the reset of the operating parameter data of the plant protection UAV spray equipment is output;

[0075] When the proportion data is not greater than the preset proportion data threshold, inheritance continues until the proportion data is no greater than the preset proportion data threshold, outputs the reset operating parameter data of the plant protection UAV spray equipment, and controls according to the reset operating parameter data of the plant protection UAV spray equipment.

[0076] It should be noted that this method can optimize the operating parameter data of the plant protection UAV spray equipment according to the charge amount of the droplets, thereby improving the accuracy of drug spraying by the plant protection UAV in the litchi orchard.

[0077] In addition, the method further comprises:

[0078] Obtaining the electric field strength degradation change characteristic data of the plant protection UAV spray equipment through big data, and constructing an electric field strength degradation characteristic prediction model based on a deep neural network, and inputting the electric field strength degradation change characteristic data of the plant protection UAV spray equipment into the electric field strength degradation characteristic prediction model for training;

[0079] Through training, a prediction model of electric field strength degradation characteristics that meets expectations is obtained, and the characteristic data of electric field strength degradation changes of plant protection drone spray equipment within a preset time is obtained;

[0080] Inputting the electric field strength degradation change characteristic data of the plant protection UAV spray equipment within the preset time into the expected electric field strength degradation characteristic prediction model for prediction, and obtaining the electric field strength characteristic data of the plant protection UAV spray equipment under different working parameters;

[0081] The operating parameter data of the plant protection drone spray equipment is updated according to the electric field strength characteristic data of the plant protection drone spray equipment under different working parameters. It should be noted that, in fact, the electrostatic system of the plant protection drone spray equipment will degrade after a certain number of years of use, resulting in the plant protection drone spray equipment having different electric field strength characteristic data under different working parameters. This method can further optimize the control parameters of the plant protection drone spray equipment, thereby improving the spray accuracy of the plant protection drone.

[0082] In addition, the method further comprises:

[0083] By setting an electric field sensor in the litchi garden, obtaining the electric field strength data in the litchi garden through the electric field sensor, and obtaining the location information of the plant protection drone, the motion trajectory analysis is performed based on the electric field strength data in the litchi garden, the location information of the plant protection drone, and the charged charge characteristic data of the droplets;

[0084] By analyzing the motion trajectory, the motion trajectory of the droplets is obtained, and the area and location information of the litchi tree region to be sprayed in the litchi garden are obtained, and a dynamic spray demonstration is performed based on the area and location of the litchi tree region to be sprayed in the litchi garden and the motion trajectory of the droplets by virtual reality technology;

[0085] Through dynamic demonstration, the area ratio information of the spraying area is obtained, and it is determined whether the area ratio information of the spraying area is greater than a preset area ratio threshold;

[0086] When the area proportion information of the spraying area is not greater than the preset area proportion threshold, the operating parameter data of the current plant protection UAV spray equipment is maintained unchanged; when the area proportion information of the spraying area is greater than the preset area proportion threshold, the operating parameters of the current plant protection UAV spray equipment are adjusted.

[0087] It should be noted that in some specific areas, there will be certain power equipment, and a certain electric field strength may be generated around the power equipment, thereby affecting the spraying effect of the plant protection UAV. This method can fully consider the influence of the external electric field strength on the spraying of the plant protection UAV, thereby improving the spraying accuracy of the plant protection UAV.

[0088] like Figure 2 As shown, the second aspect of the present invention provides a plant protection drone precision spraying system 4 for litchi orchards, comprising a memory 41 and a processor 42. The memory 41 includes a plant protection drone precision spraying method program for litchi orchards. When the plant protection drone precision spraying method program for litchi orchards is executed by the processor 42, any step of the plant protection drone precision spraying method for litchi orchards is implemented.

[0089] The third aspect of the present invention provides a computer-readable storage medium, including a program for a precision spraying method for plant protection drones in litchi orchards. When the program for a precision spraying method for plant protection drones in litchi orchards is executed by a processor, any step of the precision spraying method for plant protection drones in litchi orchards is implemented.

[0090] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0091] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0092] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0093] Those skilled in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiments; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), disks or optical disks, and other media that can store program codes.

[0094] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods of each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0095] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A precision spraying method for plant protection drones in litchi orchards, characterized in that: The following steps are involved: Obtaining operating parameter data of a plant protection UAV spray device, and constructing a droplet charge characteristic prediction model based on a generative adversarial network and the operating parameter data of the plant protection UAV spray device; Acquire environmental characteristic data in a litchi orchard, and obtain a droplet charge characteristic prediction result by using the droplet charge characteristic prediction model in combination with the environmental characteristic data in the litchi orchard; Based on the droplet charge characteristic prediction result, the charge of the droplets sprayed by the current plant protection UAV spray equipment is evaluated and analyzed to obtain the evaluation and analysis result; A first control strategy or a second control strategy is generated based on the evaluation and analysis result, and the operating parameter data of the plant protection UAV spray equipment is dynamically adjusted based on the first control strategy or the second control strategy.

2. The method for precise spraying of plant protection drones for litchi orchards according to claim 1, characterized in that: Based on the generative adversarial network and the operating parameter data of the plant protection UAV spray equipment, a prediction model for the charge characteristics of droplets is constructed, specifically: A prediction model for the charge characteristics of droplets is constructed based on a generative adversarial network, and electric field strength characteristic data of the plant protection UAV spray equipment is obtained according to the operating parameter data of the plant protection UAV spray equipment; Based on the electric field strength characteristic data of the plant protection UAV spray equipment, an estimate is made to obtain the charge characteristic data of the droplets when the plant protection UAV spray equipment is working, and according to the charge characteristic data of the droplets when the plant protection UAV spray equipment is working, a droplet charge characteristic data set is constructed under different operating parameter data; Inputting the droplet charge characteristic data set under different operating parameter data into the droplet charge characteristic prediction model, and setting a number of environmental parameters, and using the several environmental parameters as constraint conditions; The droplet charge characteristic prediction model is trained based on the constraint conditions to obtain a droplet charge characteristic prediction model that meets expectations.

3. The plant protection drone precision spraying method for litchi orchards according to claim 1, characterized in that: Acquire environmental characteristic data in the litchi orchard, and obtain droplet charge characteristic prediction results through the droplet charge characteristic prediction model in combination with the environmental characteristic data in the litchi orchard, specifically: Acquire environmental characteristic data in a litchi orchard and real-time operating parameter data of a plant protection UAV spray device, and input the real-time operating parameter data of the plant protection UAV spray device and the environmental characteristic data in the litchi orchard into the droplet charge characteristic prediction model; Generate an initial droplet charge characteristic prediction result based on the real-time operating parameter data of the plant protection UAV spray equipment through a generator, and input the initial droplet charge characteristic prediction result into a discriminator for judgment; If the discriminator accepts the initial droplet charge feature prediction result, the initial droplet charge feature prediction result is used as the final prediction result, and the final prediction result is output as the droplet charge feature prediction result; If the discriminator does not accept the initial droplet charge feature prediction result, the next droplet charge feature prediction result is generated until the discriminator accepts the current droplet charge feature prediction result and outputs the final prediction result as the droplet charge feature prediction result.

4. The plant protection drone precision spraying method for litchi orchards according to claim 1, characterized in that: Based on the droplet charge characteristic prediction result, the charge of the droplets sprayed by the current plant protection UAV spray equipment is evaluated and analyzed to obtain the evaluation and analysis results, specifically: Setting a droplet charge characteristic data threshold, counting the droplet charge characteristic prediction results, obtaining the distribution characteristics of the droplet charge characteristic prediction results in space, and constructing a droplet charge spatial distribution map according to the distribution characteristics of the droplet charge characteristic prediction results in space; Counting the proportion of the charge of the droplets in the droplet charge spatial distribution diagram that is lower than the droplet charge characteristic data threshold, and determining whether the proportion of the charge of the droplets in the droplet charge spatial distribution diagram that is lower than the droplet charge characteristic data threshold is greater than a preset proportion data threshold; When the proportion of the charge amount of the droplets in the droplet charge spatial distribution diagram that is lower than the droplet charge characteristic data threshold is greater than a preset proportion data threshold, an abnormal spray evaluation result is generated; When the charge amount of the droplets in the droplet charge spatial distribution diagram is lower than the droplet charge characteristic data threshold and the proportion of the data is not greater than the preset proportion data threshold, a normal spray evaluation result is generated, and an evaluation analysis result is generated based on the abnormal spray evaluation result or the normal spray evaluation result.

5. The plant protection drone precision spraying method for litchi orchards according to claim 1, characterized in that: Generate a first control strategy or a second control strategy based on the evaluation and analysis results, specifically: When the evaluation and analysis result is an abnormal spray evaluation result, a first control strategy is generated, and when the evaluation and analysis result is a normal spray evaluation result, a second control strategy is generated; The first control strategy or the second control strategy is output as an output result.

6. The plant protection drone precision spraying method for litchi orchards according to claim 1, characterized in that: Based on the first control strategy or the second control strategy, the operating parameter data of the plant protection UAV spray equipment is dynamically adjusted, specifically including: When the second control strategy is used, the control is performed according to the operating parameter data of the current plant protection UAV spray equipment; When the first control strategy is adopted, a genetic algorithm is introduced, a genetic algebra is set based on the genetic algorithm, and inheritance is performed based on the genetic algebra to reset the operating parameter data of the plant protection UAV spray equipment; Obtain the percentage data of the charge amount of the droplets corresponding to the reset operation parameter data of the plant protection UAV spray equipment being lower than the droplet charge characteristic data threshold value, and when the percentage data is not greater than the preset percentage data threshold value, the inheritance ends, and the reset operation parameter data of the plant protection UAV spray equipment is output; When the proportion data is not greater than the preset proportion data threshold, inheritance continues until the proportion data is no greater than the preset proportion data threshold, outputs the reset operating parameter data of the plant protection UAV spray equipment, and controls according to the reset operating parameter data of the plant protection UAV spray equipment.

7. The plant protection drone precision spraying system for litchi orchards is characterized by: It comprises a memory and a processor, wherein the memory comprises a program of a method for precision spraying of a plant protection drone for a litchi orchard, and when the program of the method for precision spraying of a plant protection drone for a litchi orchard is executed by the processor, the steps of the method for precision spraying of a plant protection drone for a litchi orchard as described in any one of claims 1 to 6 are implemented.

8. A computer-readable storage medium, characterized in that: It includes a program for a precision spraying method of a plant protection drone for a litchi orchard. When the program for the precision spraying method of a plant protection drone for a litchi orchard is executed by a processor, the steps of the precision spraying method of a plant protection drone for a litchi orchard as described in any one of claims 1 to 6 are implemented.

Images