Spraying operation control system and method for plant protection unmanned aerial vehicle

Abstract

A spraying operation control system and method for a plant protection unmanned aerial vehicle, which system and method relate to the technical field of unmanned aerial vehicles. The system (100) comprises a main control unit (110), a weighing unit (120) and a spraying unit (130). The weighing unit (120) is used for acquiring the mass of a liquid pesticide, and the spraying unit (130) is used for controlling the spraying flow of the liquid pesticide. The main control unit (110) is used for: determining a liquid pesticide flow prediction model on the basis of historical spraying data; determining a first spraying area on the basis of a liquid pesticide dosage per Chinese acre set by a user, and the initial mass of the liquid pesticide; determining a second spraying area on the basis of the liquid pesticide dosage per Chinese acre, the current mass of the liquid pesticide, and the area covered by the sprayed liquid pesticide; inputting the first spraying area and the second spraying area into the liquid pesticide flow prediction model, so as to determine the spraying flow of the liquid pesticide within a prediction time period; and determining a spraying control signal on the basis of the spraying flow of the liquid pesticide within the prediction time period. By combining the measurement of the mass of the liquid pesticide and the use of the liquid pesticide flow prediction model, the uniformity of liquid pesticide spraying can be improved.

Description

A plant protection drone spraying operation control system and method

[0001] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office of China on July 20, 2023, with application number 202310891625.0 and application name “A control system and method for spraying operations of a plant protection drone”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of drone technology, and specifically to a control system and method for spraying operations of a plant protection drone. Background Art

[0003] In recent years, my country's agricultural aviation industry has developed rapidly. As a new domestic plant protection operation method, aerial pesticide application by drones has been widely used in modern agricultural production, making it easier for farmers to manage farmland and spray pesticides.

[0004] To ensure consistent spraying progress and uniformity during drone-based crop protection operations, traditional spraying control systems rely heavily on the measurement accuracy of flow meters. However, in practice, both impeller-type and electromagnetic flow meters have their own limitations. Temperature, conductivity, fluid viscosity, strong magnetic fields, and wear and aging can all lead to reduced measurement accuracy, impacting the drone's normal crop protection operations.

[0005] Therefore, how to avoid the adverse effects of insufficient flow meter accuracy on plant protection operations has become a technical problem that needs to be solved.

[0006] Summary of the Invention

[0007] The present application provides a plant protection drone spraying operation control system and method. The present application introduces the measurement of the quality of the liquid medicine and establishes a liquid medicine flow prediction model. The first spraying area determined according to the liquid medicine usage per mu and the initial liquid medicine quality set by the user, and the second spraying area determined according to the liquid medicine usage per mu, the current liquid medicine quality and the area sprayed with the liquid medicine are input into the above-mentioned liquid medicine flow prediction model. The spraying flow rate of the liquid medicine within the prediction period can be determined, thereby improving the uniformity of the liquid medicine spraying operation.

[0008] In the first aspect, the present application provides a plant protection drone spraying operation control system. The plant protection drone spraying operation control system provided in the embodiment of the present application includes a main control unit, a weighing unit and a spraying unit. Among them, the weighing unit is used to obtain the quality of the liquid medicine, and the spraying unit is used to control the spraying flow of the liquid medicine. The main control unit is connected to the weighing unit and the spraying unit, and the main control unit is used to determine a liquid medicine flow prediction model based on historical spraying data. The first spraying area is determined according to the liquid medicine usage per mu and the initial liquid medicine quality set by the user. The second spraying area is determined according to the liquid medicine usage per mu, the current liquid medicine quality and the area where the liquid medicine has been sprayed. The first spraying area and the second spraying area are input into the liquid medicine flow prediction model to determine the spraying flow of the liquid medicine within the prediction period. The spraying control signal is determined according to the spraying flow of the liquid medicine within the prediction period.

[0009] The plant protection drone spraying operation control system provided in this embodiment establishes a liquid medicine flow prediction model and combines it with the measurement of liquid medicine quality. The first spraying area determined according to the liquid medicine usage per mu and the initial liquid medicine quality set by the user, and the second spraying area determined according to the liquid medicine usage per mu, the current liquid medicine quality and the area sprayed with the liquid are input into the above-mentioned liquid medicine flow prediction model. The spraying flow of the liquid medicine within the prediction period can be determined, thereby improving the uniformity of the liquid medicine spraying operation.

[0010] In conjunction with the first aspect, in certain implementations of the first aspect, the historical spraying data includes information on the quality of the spray liquid, spray flow rate, spray area, and speed of the historical operation. Further, determining a spray liquid flow rate prediction model based on the historical spraying data includes using a genetic algorithm to train a spray flow rate prediction value formula, y * (k+1)=a×u(k)+b×Q(k)+c×y(k), where y * (k+1) is the predicted value of the spraying flow rate at time k+1, a, b, c are identification parameters, u(k) is the mass of the liquid at time k, Q(k) is the sprayed area at time k, and y(k) is the spraying flow rate at time k.

[0011] In combination with the first aspect, in certain implementations of the first aspect, a cost function J(k) is established based on the liquid medicine flow prediction model. Further, the first spraying area and the second spraying area are input into the liquid medicine flow prediction model to determine the spraying flow of the liquid medicine within the prediction period, including determining the minimum value of the cost function J(k) based on the first spraying area and the second spraying area, and outputting the spraying flow of the liquid medicine within the prediction period, wherein, N is the time step in the prediction time domain of the plant protection UAV spraying operation, M is an integer in the prediction time domain of the plant protection UAV spraying operation, and q is the error weight coefficient of the real-time predicted spraying area.

[0012] In conjunction with the first aspect, in certain implementations of the first aspect, the plant protection drone spraying control system provided in embodiments of the present application further includes a guidance and control unit connected to the main control unit. The guidance and control unit is configured to determine drone status information, including speed, acceleration, and attitude information. The main control unit is configured to obtain the drone status information and determine a spraying control signal based on the drone status information and a predicted spray flow rate of the liquid medicine within a time period.

[0013] In the above technical solution, by combining the status information of the drone and the spraying flow rate of the liquid medicine within the predicted period to determine the spraying control signal, the accuracy of the liquid medicine spraying operation can be further improved, and the spraying effect can be improved.

[0014] In conjunction with the first aspect, in certain implementations of the first aspect, determining the spray control signal based on the spray flow rate of the liquid medicine within the predicted time period includes obtaining the liquid medicine flow rate at a current moment, and determining the spray control signal based on a difference between the liquid medicine flow rate at the current moment and the spray flow rate of the liquid medicine within the predicted time period.

[0015] In conjunction with the first aspect, in certain implementations of the first aspect, the main control unit includes a model control module, a flow control module, and a data acquisition module. The data acquisition module is configured to collect a liquid medicine mass signal from a weighing unit and a spray flow rate signal from a spray unit. The model control module is configured to determine a liquid medicine spray flow rate within a predicted time period based on a first spraying area and a second spraying area. The flow control module is configured to determine a spray unit control signal.

[0016] In a second aspect, the present application provides a method for controlling the spraying operation of a plant protection drone. The method for controlling the spraying operation of a plant protection drone provided in an embodiment of the present application includes determining a liquid medicine flow prediction model based on historical spraying data. Determine a first spraying area based on the liquid medicine usage per mu and the initial liquid medicine quality set by the user. Determine a second spraying area based on the liquid medicine usage per mu, the current liquid medicine quality, and the area where the liquid medicine has been sprayed. Input the first spraying area and the second spraying area into the liquid medicine flow prediction model to determine the spraying flow of the liquid medicine within the prediction period. Determine a spraying control signal based on the spraying flow of the liquid medicine within the prediction period.

[0017] In conjunction with the second aspect, in certain implementations of the second aspect, the historical spraying data includes information on the quality of the spray liquid, spray flow rate, spray area, and speed of the historical operation. Further, determining a spray liquid flow rate prediction model based on the historical spraying data includes using a genetic algorithm to train a spray flow rate prediction value formula, y * (k+1)=a×u(k)+b×Q(k)+c×y(k), where y *(k+1) is the predicted value of the spraying flow rate at time k+1, a, b, c are identification parameters, u(k) is the mass of the liquid at time k, Q(k) is the sprayed area at time k, and y(k) is the spraying flow rate at time k.

[0018] In conjunction with the second aspect, in certain implementations of the second aspect, a cost function J(k) is established based on the liquid medicine flow prediction model. Further, the first spraying area and the second spraying area are input into the liquid medicine flow prediction model to determine the spraying flow of the liquid medicine within the prediction period, including determining the minimum value of the cost function J(k) based on the first spraying area and the second spraying area, and outputting the spraying flow of the liquid medicine within the prediction period, wherein, N is the time step in the prediction time domain of the plant protection UAV spraying operation, M is an integer in the prediction time domain of the plant protection UAV spraying operation, and q is the error weight coefficient of the real-time predicted spraying area.

[0019] In combination with the second aspect, in certain implementations of the second aspect, drone status information is obtained, and a spraying control signal is determined based on the drone status information and the spraying flow rate of the liquid medicine within the predicted time period.

[0020] In conjunction with the second aspect, in certain implementations of the second aspect, the current flow rate of the liquid medicine is obtained, and the spraying control signal is determined according to the difference between the current flow rate of the liquid medicine and the spraying flow rate of the liquid medicine within the predicted time period.

[0021] In a third aspect, the present application provides a plant protection drone, including the plant protection drone spraying operation control system of the above-mentioned first aspect and any implementation method of the first aspect.

[0022] In a fourth aspect, the present application provides a computer-readable medium having a computer program stored thereon. When the program is executed by a computer, the computer executes the plant protection drone spraying operation control method of the above-mentioned second aspect and any implementation method of the second aspect.

[0023] The technical effects that can be achieved in the second, third and fourth aspects mentioned above can be referred to the description of the technical effects in the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] FIG1 is a schematic diagram of a spraying operation control system of a plant protection UAV provided in an embodiment of the present application.

[0025] FIG2 is a logic diagram of a liquid medicine flow prediction model provided in an embodiment of the present application.

[0026] FIG3 is a method for controlling spraying operations of a plant protection UAV provided in an embodiment of the present application.

[0027] FIG4 is a schematic diagram of a drone provided in an embodiment of the present application.

[0028] FIG5 is a schematic diagram of a control process of a liquid medicine flow prediction model provided in an embodiment of the present application. DETAILED DESCRIPTION

[0029] The technical solution in this application will be described below with reference to the accompanying drawings.

[0030] In the description of the embodiments of the present application, unless otherwise specified, " / " means or, for example, A / B can mean A or B; "and / or" in this article is merely a description of the association relationship of associated objects, indicating that three relationships can exist, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements or elements with the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and should not be understood as limiting the present application.

[0031] The terms "first", "second", "third", "fourth" etc. (if any) in this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the application described herein can be implemented in a sequence other than those illustrated or described herein. The size of the sequence number of each process below does not mean the order of execution, and the order of execution of each process should be determined by its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiment of the application. For example, in the embodiment of the application, words such as "110", "210", "220" are only marks made for the convenience of description, and are not intended to limit the system.

[0032] References to "some embodiments" and the like in this specification mean that a particular feature, structure, or characteristic described in connection with that embodiment is included in one or more embodiments of the present application. Thus, phrases such as "in some embodiments" and the like that appear in different places in this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "including," "comprising," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0033] The terms used in the embodiments of the present disclosure are for the purpose of describing specific embodiments only and are not intended to limit the embodiments of the present disclosure. The singular forms "a" and "the" used in the embodiments of the present disclosure and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.

[0034] First, the application scenario of this application is introduced.

[0035] In recent years, my country's agricultural aviation industry has developed rapidly. Aerial pesticide application using drones for plant protection has become a new and widely adopted method in modern agricultural production. Drones for plant protection are specialized drones used for agricultural plant protection. They offer advantages such as ease of operation, high efficiency, and low cost. They can effectively replace traditional manual and ground-based spraying methods, improving agricultural production efficiency, reducing pesticide use, and minimizing environmental pollution. This makes farmland management easier for farmers, saving both manpower and time. During drone plant protection operations, traditional spraying control systems rely heavily on the accuracy of flow meters to ensure consistent spraying progress and uniformity. However, in practice, both impeller and electromagnetic flow meters have their own limitations. Temperature, conductivity, fluid viscosity, strong magnetic fields, wear, and aging can all affect measurement accuracy, potentially compromising the proper functioning of drone plant protection operations.

[0036] In view of this, the embodiment of the present application provides a plant protection drone spraying operation control system and method. The present application establishes a liquid medicine flow prediction model and combines it with the measurement of the liquid medicine quality. The first spraying area determined according to the liquid medicine usage per mu and the initial liquid medicine quality set by the user, and the second spraying area determined according to the liquid medicine usage per mu, the current liquid medicine quality and the area where the liquid medicine has been sprayed are input into the above-mentioned liquid medicine flow prediction model. The spraying flow of the liquid medicine within the prediction period can be determined, thereby improving the uniformity of the liquid medicine spraying operation.

[0037] In order to make the technical problems solved by this application, the technical solutions adopted and the technical effects achieved clearer, the technical solutions of the embodiments of this application will be further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0038] In addition, the plant protection drone spraying operation control system described in the embodiment of the present application is for the purpose of more clearly illustrating the technical solution of the embodiment of the present application, and does not constitute a limitation on the technical solution provided in the embodiment of the present application. Ordinary technicians in this field can know that the technical solution provided in the embodiment of the present application is also applicable to similar technical problems.

[0039] It should also be understood that the various implementation methods described in this specification can be implemented individually or in combination, and the embodiments of the present application are not limited to this.

[0040] The plant protection drone spraying operation control system provided in the embodiment of the present application includes a main control unit, a weighing unit and a spraying unit. Among them, the weighing unit is used to obtain the quality of the liquid medicine, and the spraying unit is used to control the spraying flow of the liquid medicine. The main control unit is connected to the weighing unit and the spraying unit, and the main control unit is used to determine the liquid medicine flow prediction model based on historical spraying data. The first spraying area is determined according to the liquid medicine usage per mu and the initial liquid medicine quality set by the user. The second spraying area is determined according to the liquid medicine usage per mu, the current liquid medicine quality and the area where the liquid medicine has been sprayed. The first spraying area and the second spraying area are input into the liquid medicine flow prediction model to determine the spraying flow of the liquid medicine within the prediction period. The spraying control signal is determined according to the spraying flow of the liquid medicine within the prediction period.

[0041] FIG1 is a schematic diagram of a spraying operation control system of a plant protection UAV provided in an embodiment of the present application.

[0042] As shown in Figure 1, system 100 includes a main control unit 110, a weighing unit 120, and a spraying unit 130. The weighing unit 120 is used to obtain the mass of the liquid medicine, and the spraying unit 130 is used to control the spray flow rate of the liquid medicine. The main control unit 110 is connected to the weighing unit 120 and the spraying unit 130 and is configured to determine a liquid medicine flow rate prediction model based on historical spraying data. A first spraying area is determined based on the user-set per-mu liquid medicine dosage and the initial liquid medicine dosage. A second spraying area is determined based on the per-mu liquid medicine dosage, the current liquid medicine dosage, and the area already sprayed with the liquid medicine. The first and second spraying areas are input into the liquid medicine flow rate prediction model to determine the liquid medicine spray flow rate within a prediction period. A spraying control signal is determined based on the liquid medicine spray flow rate within the prediction period. The main control unit 110 includes a model control module 111, a flow rate control module 112, and a data acquisition module 113. The data acquisition module 113 is configured to collect the liquid medicine quality signal from the weighing unit and the spray flow rate signal from the spraying unit. The model control module 111 is used to determine the spraying flow rate of the liquid medicine within the prediction period according to the first spraying area and the second spraying area. The flow control module 112 is used to determine the spraying unit control signal.

[0043] In some embodiments, system 100 further includes a control unit 140, which is connected to main control unit 110 and configured to determine drone status information, including velocity, acceleration, and attitude information. The main control unit is configured to obtain the drone status information and determine a spraying control signal based on the drone status information and the predicted spray flow rate of the liquid medicine within a time period.

[0044] In some embodiments, the historical spraying data includes the quality of the liquid medicine, spraying flow rate, spraying area and speed information of the historical operation. Specifically, the main control unit 110 controls the historical spraying data of the operation system by collecting the historical spraying data, including the quality of the liquid medicine, spraying flow rate, spraying area and speed information of the historical operation.

[0045] In the embodiment of the present application, the main control unit 110 uses a model predictive control (MPC) algorithm to control the spraying control system of the plant protection drone. The MPC algorithm uses the predictions of mathematical models to drive decision-making and is widely used in industry and manufacturing, as well as in robotic control, energy management, traffic control and other fields. Its basic idea is to use mathematical models to predict the dynamic behavior of the system (including input variables and output variables) over a period of time in the future, thereby generating an optimal control strategy. At each moment, MPC will re-predict future behavior and regularly update the control strategy.

[0046] Specifically, the theoretical spraying area is calculated based on the quality of the liquid medicine and the spray flow rate, and finally the training sample data is formed with the liquid medicine flow rate at the corresponding moment, and the spray flow rate prediction value formula is trained using a genetic algorithm.

[0047] y * (k+1)=a×u(k)+b×Q(k)+c×y(k), where y * (k+1) is the predicted value of the spraying flow rate at time k+1, a, b, c are identification parameters, u(k) is the mass of the liquid at time k, Q(k) is the sprayed area at time k, and y(k) is the spraying flow rate at time k.

[0048] Finally, the prediction model after training in this embodiment is as follows:

[0049] Among them, C1 represents the initial liquid mass, C2 represents the liquid dosage per mu, △T represents the control step, for example, 5 minutes, y * represents the predicted liquid flow rate, y represents the real-time liquid flow rate, and M is an integer in the predicted time domain of the plant protection UAV spraying operation, M = 0, 1, ..., N-1.

[0050] FIG2 is a logical diagram of a liquid medicine flow prediction model provided in an embodiment of the present application. On the basis of determining the liquid medicine flow prediction model, the spraying operation information of the plant protection UAV is collected, mainly the quality of the liquid medicine and the spray flow rate of the liquid medicine. Furthermore, it also includes UAV status information, such as speed information, acceleration information and attitude information. When combined with speed information, the faster the UAV speed, the larger the calculated spraying area, and the greater the spray flow rate of the liquid medicine. The accuracy of the model can be further improved by combining the UAV status information.

[0051] Furthermore, based on the liquid medicine flow prediction model, a constrained cost function J(k) is established. By combining the real-time predicted spraying area, the function is minimized in the prediction time domain to optimize the liquid medicine spraying flow as much as possible to achieve the theoretical spraying area.

[0052] The cost function is:

[0053] Where N is the time step in the prediction time domain of the plant protection UAV spraying operation. For example, N = 60, that is, the time step in the prediction time domain of the plant protection UAV spraying operation is 60 minutes. M is an integer in the prediction time domain of the plant protection UAV spraying operation. y is the spraying flow rate, and q is the error weight coefficient of the real-time predicted spraying area. The constraints are: u min ≤u(k+M)≤u max , M=0,1,…,N-1. Where u min and u max are the minimum and maximum values ​​of the drug solution mass respectively.

[0054] In the initial state, after determining the liquid medicine flow prediction model, the main control unit 110 determines the first spraying area based on the user-set liquid medicine dosage per mu and initial liquid medicine mass. It should be understood that the initial state refers to the state before the plant protection drone begins spraying, and the initial liquid medicine mass refers to the liquid medicine mass before the plant protection drone begins spraying. In other words, the first spraying area is the theoretical spraying area calculated based on the user-set liquid medicine dosage per mu and initial liquid medicine mass.

[0055] When performing a spraying operation, the main control unit 110 determines the second spraying area based on the amount of liquid medicine used per mu, the current quality of the liquid medicine, and the area where the liquid medicine has been sprayed. It should be understood that the remaining sprayable area can be determined in real time based on the amount of liquid medicine used per mu and the current quality of the liquid medicine, and the second spraying area is determined by calculating the sum of the remaining sprayable area and the area where the liquid medicine has been sprayed. The second spraying area is the spraying area predicted in real time. The main control unit 110 uses the first spraying area and the second spraying area as inputs to the liquid medicine flow prediction model, and then outputs the predicted liquid medicine flow, and determines the spraying control signal based on the predicted liquid medicine flow. The spraying unit 130 uses the spraying control signal as input, and then converts it into the size of the water pump output power or the opening of the liquid medicine output port, thereby achieving the purpose of flow control.

[0056] In some embodiments, the main control unit 110 obtains the current flow rate of the liquid medicine, and determines a spraying control signal according to the difference between the current flow rate of the liquid medicine and the spraying flow rate of the liquid medicine within the predicted time period, thereby further adjusting the spraying unit 130 .

[0057] In each control cycle, the liquid medicine flow rate is predicted and optimized in a rolling manner to minimize the cost function J(k) in the prediction time domain and generate a prediction output. The main control unit 110 performs row optimization control on the liquid medicine flow rate based on the prediction output.

[0058] When the next moment begins, the liquid medicine flow information is collected for feedback correction to correct the deviation of the prediction model, and then the optimization is carried out again. This cycle is repeated to ensure the accuracy of the prediction results and the stability of the control system.

[0059] Based on the plant protection UAV spraying operation control system and the liquid medicine flow prediction model shown in Figures 1 and 2, the present application provides a plant protection UAV spraying operation control method, as shown in Figure 3.

[0060] Figure 3 is a schematic flow chart of a method for controlling spraying operations of a plant protection drone provided in an embodiment of the present application. It should be understood that this method can be applied to plant protection drones and their systems.

[0061] S311, determining a liquid medicine flow prediction model based on historical spraying data.

[0062] Among them, historical spraying data includes the quality of the liquid, spraying flow, spraying area and speed information of historical operations.

[0063] In some embodiments, a genetic algorithm is used to train the spray flow rate prediction formula, y * (k+1)=a×u(k)+b×Q(k)+c×y(k), where y * (k+1) is the predicted value of the spraying flow rate at time k+1, a, b, c are identification parameters, u(k) is the mass of the liquid at time k, Q(k) is the sprayed area at time k, and y(k) is the spraying flow rate at time k.

[0064] S312: Determine the first spraying area according to the per-mu dosage of the liquid medicine set by the user and the initial liquid medicine mass.

[0065] S313: Determine the second spraying area based on the amount of liquid medicine used per mu, the current liquid medicine quality, and the area already sprayed with the liquid medicine.

[0066] S314: Input the first spraying area and the second spraying area into a liquid medicine flow prediction model to determine the liquid medicine spraying flow rate within the prediction period.

[0067] In some embodiments, based on the liquid medicine flow prediction model, a cost function J(k) is established, the minimum value of the cost function J(k) is determined according to the first spraying area and the second spraying area, and the liquid medicine spray flow rate within the prediction period is output, wherein, N is the time step in the prediction time domain of the plant protection UAV spraying operation, M is an integer in the prediction time domain of the plant protection UAV spraying operation, and q is the error weight coefficient of the real-time predicted spraying area.

[0068] S315: Determine a spraying control signal according to the spraying flow rate of the liquid medicine within the predicted time period.

[0069] In some embodiments, the current flow rate of the liquid medicine is obtained, and the spraying control signal is determined according to the difference between the current flow rate of the liquid medicine and the spraying flow rate of the liquid medicine within the predicted time period.

[0070] According to the embodiment shown in Figure 3, by establishing a liquid medicine flow prediction model and combining it with the measurement of the quality of the liquid medicine, the first spraying area determined according to the liquid medicine usage per mu and the initial liquid medicine quality set by the user, and the second spraying area determined according to the liquid medicine usage per mu, the current liquid medicine quality and the area where the liquid medicine has been sprayed are input into the above-mentioned liquid medicine flow prediction model. The spraying flow rate of the liquid medicine within the prediction period can be determined, thereby improving the uniformity and dynamic response performance of the liquid medicine spraying operation.

[0071] In some embodiments, the method further includes obtaining drone status information, and determining a spraying control signal based on the drone status information and the spraying flow rate of the liquid medicine within a predicted time period.

[0072] FIG4 is a schematic diagram of a drone provided in an embodiment of the present application.

[0073] As shown in Figure 4, the drone includes system 100 from Figure 1. A weighing unit is used to determine the mass of the liquid medicine within the medicine tank, and a spraying unit 130 is used to control the spray rate of the liquid medicine. A main control unit connects the weighing unit and the spraying unit. For detailed implementation, please refer to the description of Figures 1 through 3 and will not be repeated here.

[0074] FIG5 is a schematic diagram of a control process of a liquid medicine flow prediction model provided in an embodiment of the present application.

[0075] As shown in Figure 5, after the liquid flow prediction model controls and adjusts the liquid flow, the plant protection drone spraying control system has higher control accuracy, improved the uniformity of the liquid spraying operation, and made the final actual spraying area consistent with the predicted area, resulting in better spraying effect.

[0076] An embodiment of the present application also proposes a computer-readable storage medium, which stores one or more programs, and the one or more programs include instructions. When the instructions are executed by an electronic device including multiple applications, the electronic device can execute the method of the embodiment shown in Figure 3.

[0077] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and modules can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0078] In the several embodiments provided in this application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the division of modules is only a logical function division. In actual implementation, there may be other division methods, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or module, which can be electrical, mechanical or other forms.

[0079] Modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, that is, they may be located in one place or distributed across multiple network elements. Some or all of these units may be selected to achieve the objectives of this embodiment based on actual needs.

[0080] In addition, each functional module in each embodiment of the present application may be integrated into one processing device, or each module may exist physically separately, or two or more modules may be integrated into one device.

[0081] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0082] The above are only specific embodiments of the present application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A control system for spraying operations of a plant protection drone, characterized in that: It includes a main control unit, a weighing unit and a spraying unit; among which, The weighing unit is used to obtain the mass of the liquid medicine, and the spraying unit is used to control the spraying flow rate of the liquid medicine; The main control unit is connected to the weighing unit and the spraying unit, and the main control unit is used to: Determine the liquid flow prediction model based on historical spraying data; Determine the first spraying area according to the amount of liquid medicine per mu set by the user and the initial liquid medicine quality; Determine the second spraying area according to the amount of the liquid medicine used per mu, the current liquid medicine quality and the area where the liquid medicine has been sprayed; Inputting the first spraying area and the second spraying area into the liquid medicine flow rate prediction model to determine the liquid medicine spraying flow rate within the prediction period; A spraying control signal is determined according to the spraying flow rate of the liquid medicine within the prediction period.

2. The plant protection UAV spraying operation control system according to claim 1, characterized in that: The historical spraying data includes the quality of the liquid medicine, the spraying flow rate, the spraying area and the speed information of the historical operation. The liquid medicine flow rate prediction model is determined according to the historical spraying data, including: Use genetic algorithm to train the spray flow prediction formula, y * (k+1)=a×u(k)+b×Q(k)+c×y(k), where y * (k+1) is the predicted value of the spraying flow rate at time k+1, a, b, c are identification parameters, u(k) is the mass of the liquid at time k, Q(k) is the sprayed area at time k, and y(k) is the spraying flow rate at time k.

3. The plant protection UAV spraying operation control system according to claim 2, characterized in that: Based on the liquid medicine flow prediction model, a cost function J(k) is established, and the first spraying area and the second spraying area are input into the liquid medicine flow prediction model to determine the spraying flow of the liquid medicine within the prediction period, including: The minimum value of the cost function J(k) is determined according to the first spraying area and the second spraying area, and the spraying flow rate of the liquid medicine in the predicted period is output, wherein, N is the time step in the prediction time domain of the spraying operation of the plant protection UAV, M is an integer in the prediction time domain of the spraying operation of the plant protection UAV, and q is the error weight coefficient of the real-time predicted spraying area.

4. The plant protection UAV spraying operation control system according to any one of claims 1 to 3, characterized in that: The system further comprises a guidance and control unit, the guidance and control unit being connected to the main control unit, the guidance and control unit being used to determine the state information of the drone, the state information of the drone comprising speed information, acceleration information and attitude information, and the main control unit being used to: Get drone status information, The spraying control signal is determined according to the drone status information and the spraying flow rate of the liquid medicine within the predicted time period.

5. The plant protection UAV spraying operation control system according to any one of claims 1 to 3, characterized in that: The step of determining the spraying control signal according to the spraying flow rate of the liquid medicine within the predicted time period includes: Get the current flow rate of the liquid medicine; The spraying control signal is determined according to the difference between the current flow rate of the liquid medicine and the spraying flow rate of the liquid medicine in the predicted time period.

6. The plant protection UAV spraying operation control system according to any one of claims 1 to 3, characterized in that: The main control unit includes a model control module, a flow control module and a data acquisition module. The data acquisition module is used to collect the liquid medicine mass signal of the weighing unit and the spray flow signal of the spray unit. The model control module is used to determine the spray flow of the liquid medicine within the prediction period according to the first spraying area and the second spraying area. The flow control module is used to determine the spray unit control signal.

7. A method for controlling spraying operations of a plant protection drone, characterized in that: The method comprises: Determine the liquid flow prediction model based on historical spraying data; Determine the first spraying area according to the amount of liquid medicine per mu set by the user and the initial liquid medicine quality; Determine the second spraying area according to the amount of the liquid medicine used per mu, the current liquid medicine quality and the area where the liquid medicine has been sprayed; Inputting the first spraying area and the second spraying area into the liquid medicine flow rate prediction model to determine the liquid medicine spraying flow rate within the prediction period; A spraying control signal is determined according to the spraying flow rate of the liquid medicine within the prediction period.

8. The method for controlling spraying operation of a plant protection UAV according to claim 7, characterized in that: The historical spraying data includes the quality of the liquid medicine, the spraying flow rate, the spraying area and the speed information of the historical operation. The liquid medicine flow rate prediction model is determined according to the historical spraying data, including: Use genetic algorithm to train the spray flow prediction formula, y * (k+1)=a×u(k)+b×Q(k)+c×y(k), where y * (k+1) is the predicted value of the spraying flow rate at time k+1, a, b, c are identification parameters, u(k) is the mass of the liquid at time k, Q(k) is the sprayed area at time k, and y(k) is the spraying flow rate at time k.

9. The method for controlling spraying operation of a plant protection UAV according to claim 8, characterized in that: The method further comprises: Based on the liquid medicine flow prediction model, a cost function J(k) is established, and the first spraying area and the second spraying area are input into the liquid medicine flow prediction model to determine the spraying flow of the liquid medicine within the prediction period, including: The minimum value of the cost function J(k) is determined according to the first spraying area and the second spraying area, and the spraying flow rate of the liquid medicine in the predicted period is output, wherein, N is the time step in the prediction time domain of the spraying operation of the plant protection UAV, M is an integer in the prediction time domain of the spraying operation of the plant protection UAV, and q is the error weight coefficient of the real-time predicted spraying area.

10. The spraying operation control method according to any one of claims 7 to 9, characterized in that: The method further comprises: Get drone status information, The spraying control signal is determined according to the drone status information and the spraying flow rate of the liquid medicine within the predicted time period.

11. The spraying operation control method according to any one of claims 7 to 9, characterized in that: The step of determining the spraying control signal according to the spraying flow rate of the liquid medicine within the predicted time period includes: Get the current flow rate of the liquid medicine; The spraying control signal is determined according to the difference between the current flow rate of the liquid medicine and the spraying flow rate of the liquid medicine in the predicted time period.

12. A plant protection drone, characterized in that: include: A plant protection UAV spraying operation control system as described in any one of claims 1 to 6.

13. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a computer, the computer executes the spraying operation control method of the plant protection UAV as described in any one of claims 7 to 11.

Images