System for controlling diseases and insect pests through precise spraying of unmanned aerial vehicle

Abstract

The invention discloses an unmanned aerial vehicle accurate spraying pest control system, which comprises an unmanned aerial vehicle, a spraying module, a sensor module, a data processing module and a control module, and is characterized in that the spraying module, the sensor module, the data processing module and the control module are all mounted on the unmanned aerial vehicle; the sensor module is electrically connected with the data processing module and transmits collected data to the data processing module, the data processing module is electrically connected with the control module and issues a control strategy to the control module, and the control module is electrically connected with the unmanned aerial vehicle and the spraying module and executes the control strategy. Through the integrated unmanned aerial vehicle system, precise recognition and treatment of diseases and insect pests can be achieved, pesticide use is reduced, environmental pollution is reduced, and meanwhile the crop yield and quality are improved.

Description

Technical Field

[0001] The present invention relates to the field of agricultural technology, and in particular to a system for accurately spraying pests and diseases by an unmanned aerial vehicle. Background Art

[0002] With the rapid advancement of drone technology, drones are increasingly used in the agricultural field, especially in pest control. Precision spraying by drones can effectively improve the utilization rate of pesticides, reduce environmental pollution, and improve agricultural production efficiency. However, the existing drone spraying technology still has some shortcomings in spraying accuracy, intelligence, and adaptability, which affects its effectiveness in practical applications.

[0003] After searching, a spraying device for a pesticide spraying drone with a publication number of CN113443143B was disclosed, and the publication date is December 22, 2023. This patent can change the angle of the adjustment device by setting a second motor, a second rotating rod and a rotating plate to change the shape of the sprayed liquid. However, this technical solution mainly focuses on the angle adjustment of the nozzle, lacks real-time data collection and intelligent control during the spraying process, and cannot be dynamically adjusted according to the actual environment and crop conditions, which may lead to uneven spraying and waste of resources.

[0004] After searching, a spraying device for a pesticide spraying drone with a publication number of CN113306723B was disclosed, and the publication date is January 10, 2023. This patent effectively prevents the spraying component from spraying the liquid medicine onto the drone body when spraying the liquid medicine through the cooperation of the telescopic adjustment frame and the support foot, avoiding the waste of liquid medicine and pollution of the drone body, and has a good shock absorption effect. However, this technical solution mainly focuses on the improvement of the mechanical structure, lacks real-time data collection and intelligent control during the spraying process, and cannot achieve precise spraying, especially in complex environments. It has poor adaptability and is difficult to meet the control needs of different crops and different pests and diseases.

[0005] The above problems show that the existing pesticide spraying drones still have certain shortcomings in spraying accuracy, intelligence and adaptability. Summary of the invention

[0006] The purpose of the present invention is to provide a system for accurately spraying pests and diseases using an unmanned aerial vehicle to solve the above-mentioned problems.

[0007] The present invention is achieved through the following technical solutions: A system for accurately spraying pests and diseases by a drone, comprising a drone, a spraying module, a sensor module, a data processing module and a control module, wherein the spraying module, the sensor module, the data processing module and the control module are all installed on the drone; The sensor module is electrically connected to the data processing module, and the collected data is transmitted to the data processing module. The data processing module is electrically connected to the control module, and the data processing module issues a control strategy to the control module. The control module is electrically connected to the drone and the spraying module to execute the control strategy. Preferably, the sensor modules include the following: Environmental sensor module: installed in multiple locations of the drone, including wind speed sensor module, wind direction sensor module, temperature sensor module, and humidity sensor module, used to monitor the environmental data around the drone in real time; Crop sensor module: installed at the bottom of the drone, including a camera and infrared sensor module, used to monitor crop growth and pests and diseases; Position sensor module: including GPS module and inertial measurement unit (IMU), used to monitor the position and attitude of the drone in real time; Liquid medicine sensor module: installed in the spray module, including flow sensor module and pressure sensor module, used to monitor the flow and pressure of the liquid medicine in real time.

[0008] Preferably, the data processing module includes an image processing and recognition unit, a sensor module data fusion unit and a decision unit, wherein the image processing and recognition unit is used to process the image data obtained from the crop sensor module and identify the crop growth status and pest and disease areas, and the sensor module data fusion unit is used to assist the decision unit in generating accurate spraying strategies.

[0009] Preferably, the image processing and recognition unit has the following specific operating steps: S1: Obtain farmland image I(x,y) from the crop sensor module; S2: Generate a clear image I'(x,y) through preprocessing, including denoising and image enhancement; S3: Use convolutional neural network (CNN) to extract image features and output feature maps F k (x, y) ; S4: Use segmentation algorithm to locate the pest area R(x,y).

[0010] Preferably, the convolutional neural network convolution expression is: F k (x, y) = ∑ i,j W k (i, j)·I(x + i, y + j) + b k in, i Hewei jis the index of the convolution kernel, indicating the position offset of each element in the convolution kernel. W k Indicates The convolution kernels are located at (i, j) The weight of b k Represents the convolution kernel The bias term of the feature map, F k (x, y) Indicates The output feature map after the convolution kernel is at position (x, y) The value of .

[0011] Activation function (ReLU): A(x, y) = max(0, F(x, y)) ; Parameter explanation: I(x, y) : original input image; W k (i, j) : convolution kernel parameters; b k : bias term; F k (x, y) : Convolution output features; A(x, y) : Feature map after activation.

[0012] Preferably, the sensor module data fusion unit has the following specific operating steps: T1: Obtain environmental sensor module data, including wind speed, wind direction, temperature, and humidity; T2: Use Kalman filtering to fuse the environmental sensor module data and estimate the environmental state x^(t) ; Preferably, the Kalman filter specifically includes the following formula: Kalman filter prediction update equation: x ^ (t|t - 1) = Ax ^ (t - 1) + Bu(t - 1) ; P(t|t - 1) = AP(t - 1)A + Q ; Kalman gain: K(t) = P(t|t - 1)H(HP(t|t - 1)H + R)^(-1) ; Status Update: x^(t|t) = x^(t|t - 1) + K(t)(z(t) - Hx^(t|t - 1)) ; P(t|t) = (I - K(t)H)P(t|t - 1) ; Parameter explanation: x^(t|t - 1) : predicted state at time t; P(t|t - 1) : covariance matrix of predicted state; A, B : state transfer matrix, control input matrix; Q : process noise covariance; K(t) : Kalman gain; z(t) : Sensor module measurement value; H : represents the observation matrix, which is used to establish the relationship between the state vector and the observation value; R : Represents the observation noise covariance matrix, which is used to represent the error or noise of the observation value.

[0013] Preferably, the decision-making unit has the following specific operating steps: F1: The pest area R(x,y) and the environmental status x^(t) Input to the decision-making unit to conduct pest and disease assessment and generate pest and disease severity scores S d (x, y) ; F2: Decide whether to spray based on the score. If it is decided to spray, the spraying angle is adjusted dynamically during the spraying process; Preferably, in F2, the spraying angle is dynamically adjusted according to wind speed, wind direction, drone position and attitude, and the calculation formula is: ; in, is the initial spraying angle, is the wind speed, is the wind direction angle, is the pressure difference, and is the correction factor.

[0014] Preferably, the spray module further includes an anti-clogging device, which includes an ultrasonic sensor and a vibration motor. The ultrasonic sensor is installed at the liquid inlet of the nozzle to detect the blockage of the nozzle. The vibration motor is installed at the base of the nozzle to periodically vibrate the nozzle to prevent the liquid from being blocked. The control module includes a central processing unit and a signal transceiver. When the central processing unit detects that the nozzle is blocked through the ultrasonic sensor, it sends a command to the vibration motor through the signal transceiver, and the vibration motor periodically vibrates the nozzle to clear the blockage. The drone also includes an autonomous obstacle avoidance module, which includes a millimeter-wave radar and an obstacle avoidance algorithm unit. The millimeter-wave radar is installed in the front, back, left, and right directions of the drone to detect obstacles around the drone in real time. The obstacle avoidance algorithm unit is installed in the central processor to process the data of the millimeter-wave radar and generate obstacle avoidance instructions. The control module is also connected to a power management module. When the millimeter-wave radar detects an obstacle, the obstacle avoidance algorithm unit sends instructions to the power management module through a signal transceiver to adjust the speed and power of the motor so that the drone automatically bypasses the obstacle to ensure flight safety.

[0015] Compared with the prior art, the present invention has the following advantages and beneficial effects: 1. By accurately identifying the pest and disease areas and adjusting the spraying amount according to environmental conditions, the spraying of drugs in ineffective areas is avoided; 2. The real-time data provided by the sensor module can accurately identify the pest and disease areas and adjust the spraying strategy according to environmental factors, avoiding the waste of traditional spraying methods; 3. The entire data processing module uses an automated process to achieve precise spraying of pests and diseases by drones. This intelligent regulation can respond to environmental changes in real time and dynamically adjust spraying strategies, greatly improving agricultural production efficiency and reducing labor costs; 4. Through image segmentation technology, the specific location and range of pests and diseases can be accurately identified and located, avoiding the problem of manual estimation errors in traditional methods, ensuring that drones can spray accurately according to the distribution of pests and diseases, and improving prevention and control efficiency; 5. Convolution operation can reduce the complexity of manual feature extraction, automatically learn features through the training process, and improve the adaptability and flexibility of the system. For different farmland environments and crop types, the convolutional neural network can be adaptively adjusted to provide efficient and accurate pest control solutions. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, constitute a part of this application, and do not constitute a limitation of the embodiments of the present invention. In the drawings: Figure 1 is a system block diagram of the present invention; Figure 2 It is a flowchart of the specific operation steps of the image processing and recognition unit; Figure 3 It is a flowchart of the specific operation steps of the decision-making unit. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical scheme and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the embodiments and drawings. The schematic implementation modes and descriptions of the present invention are only used to explain the present invention and are not intended to limit the present invention. It should be noted that the present invention is already in the actual development and use stage.

[0018] like Figures 1 - 3 As shown, an embodiment of the present invention provides a system for accurately spraying pests and diseases by a drone, comprising a drone, a spraying module, a sensor module, a data processing module and a control module, wherein the spraying module, the sensor module, the data processing module and the control module are all installed on the drone; The sensor module is electrically connected to the data processing module, and the collected data is transmitted to the data processing module. The data processing module is electrically connected to the control module, and the data processing module issues a control strategy to the control module. The control module is electrically connected to the UAV and the spraying module to execute the control strategy.

[0019] In one possible implementation, first, a sensor module is installed on the drone, responsible for collecting environmental and crop health data in real time. The sensor module includes environmental sensors (such as temperature, humidity, wind speed, and wind direction sensors) and crop sensors (such as high-definition cameras, infrared sensors, etc.). These sensors transmit the collected data to the data processing module through electrical connections. The sensor module and the data processing module are connected through a data bus to ensure real-time transmission and processing of information.

[0020] Furthermore, the data processing module is responsible for receiving data from the sensor module for processing and analysis. The data processing module first pre-processes the collected images and environmental data, such as denoising and image enhancement, in order to extract more accurate information on crop pests and diseases. Using image processing algorithms and convolutional neural networks (CNNs), the data processing module can accurately identify the areas and types of pests and diseases on crops. At the same time, the data processing module also fuses environmental data, estimates the most suitable time and area for spraying through algorithms such as Kalman filtering, and generates accurate control strategies.

[0021] Once the data processing module completes the analysis of the pest area and environmental conditions, it transmits the generated control strategy to the control module through an electrical connection. The control module determines the flight path, spraying method and spraying amount of the drone based on the strategy information provided by the data processing module. The control module is also responsible for adjusting the working status of the spraying module, such as spraying angle, flow rate, pressure, etc., to ensure the maximum spraying effect.

[0022] Furthermore, the spraying module is a device that performs specific spraying tasks. It sprays the liquid medicine to the pest area accurately according to the instructions issued by the control module. The spraying module includes a nozzle, a liquid medicine storage container, a pump and a flow sensor, and can dynamically adjust the spraying strategy according to real-time environmental data to adapt to changes in wind speed, humidity, etc.

[0023] In an embodiment of the present invention, the sensor module includes: Environmental sensor module: installed in multiple locations of the drone, including wind speed sensor module, wind direction sensor module, temperature sensor module, and humidity sensor module, used to monitor the environmental data around the drone in real time; Crop sensor module: installed at the bottom of the drone, including a camera and infrared sensor module, used to monitor crop growth and pests and diseases; Position sensor module: including GPS module and inertial measurement unit, used to monitor the position and attitude of the drone in real time; Liquid medicine sensor module: installed in the spray module, including flow sensor module and pressure sensor module, used to monitor the flow and pressure of the liquid medicine in real time.

[0024] In a possible implementation, first, the environmental sensor module includes a wind speed sensor, a wind direction sensor, a temperature sensor, and a humidity sensor. Multiple environmental sensors are installed at different locations of the drone to comprehensively monitor environmental changes around the drone. The real-time data of these sensors are transmitted to the data processing module via wireless or electrical connection. The data processing module generates a suitable spraying strategy by integrating environmental data, analyzing factors such as wind speed, wind direction, temperature, and humidity. For example, excessive temperature and humidity or excessive wind speed will affect the spraying effect. The data processing module will adjust the spraying timing and spraying amount based on this information to ensure the effective transmission and effect of the drug.

[0025] Furthermore, the crop sensor module is installed at the bottom of the drone, mainly including a high-definition camera and an infrared sensor. These sensors are used to monitor the growth status, pests and diseases of crops in real time. The crop sensor module transmits the collected image data and infrared data to the data processing module. The data processing module processes these images, detects whether there are pests and diseases on the surface of the crops through image recognition processing algorithms, and determines the type, distribution area and severity of pests and diseases. The data processing module uses these data to generate accurate spraying areas and drug dosage distribution plans.

[0026] Furthermore, the position sensor module includes a GPS module and an inertial measurement unit (IMU) for real-time monitoring of the position and attitude of the drone. The GPS module provides the position information of the drone, while the IMU provides the flight attitude data of the drone (such as tilt angle and acceleration). This information is transmitted to the data processing module through electrical connections, helping the system to adjust the flight path and spraying angle in real time. Ensure that the spraying module always maintains the correct flight trajectory and altitude to achieve the purpose of precise spraying.

[0027] Furthermore, the liquid medicine sensor module is installed in the spraying module, mainly including a flow sensor and a pressure sensor. The flow sensor monitors the flow of liquid medicine in the spraying system, and the pressure sensor monitors the pressure of the spraying system. The liquid medicine sensor module transmits real-time data to the control module, and the control module adjusts the spraying pressure and flow rate according to these data to ensure that the liquid medicine is sprayed evenly and avoid drug waste or uneven spraying due to unstable pressure or excessive flow rate.

[0028] In an embodiment of the present invention, the data processing module includes an image processing and recognition unit, a sensor module data fusion unit and a decision unit, wherein the image processing and recognition unit is used to process the image data obtained from the crop sensor module and identify the crop growth status and pest and disease areas, and the sensor module data fusion unit is used to assist the decision unit in generating an accurate spraying strategy.

[0029] In a possible implementation, the image processing and recognition unit acquires monitoring data such as crop growth conditions and pest and disease information collected by crop sensors in real time, and uses an image processing algorithm combined with a convolutional neural network (CNN) to process and analyze the acquired image data, thereby accurately identifying the pest and disease areas and types on the crops.

[0030] The main task of the image processing and recognition unit is to identify the health of crops and determine whether pests and diseases are present and their severity. For example, by analyzing information such as leaf color and shape, the system can identify pests, disease spots or other growth problems. For pest-infested areas, the unit will also mark the specific location to provide positioning information for subsequent precision spraying.

[0031] The sensor module data fusion unit is responsible for collecting data from multiple sensors in the environment, including temperature, humidity, wind speed, etc. These data reflect the environmental factors of crop growth and affect spraying decisions. These sensor data are combined with the pest and disease information provided by the image processing unit to generate a comprehensive crop and environmental status model, which reflects the spread of pests and diseases and crop needs in the current environment, and assists the decision-making unit in formulating spraying plans.

[0032] Furthermore, based on the pest and disease identification data provided by the image processing and recognition unit and the environmental data provided by the sensor module, the decision unit performs data analysis and processing, and generates an accurate spraying strategy in combination with the crop growth cycle, current pest and disease conditions and environmental conditions.

[0033] For example, the decision-making unit will determine the type of medicine, spraying amount, spraying time and spraying range according to the type of pests and diseases. At the same time, according to environmental data, the decision-making unit will adjust the spraying amount to avoid drug drift or waste when the wind speed is too high.

[0034] In the embodiment of the present invention, the image processing and recognition unit has the following specific operating steps: S1: Obtain farmland image I(x,y) from the crop sensor module; S2: Generate a clear image I'(x,y) through preprocessing, including denoising and image enhancement; S3: Use convolutional neural network to extract image features and output feature maps F k (x, y) ; S4: Use segmentation algorithm to locate the pest area R(x,y).

[0035] In a possible implementation, the crop sensor module (such as a high-definition camera, infrared camera, etc.) collects image data of farmland in real time through sensors installed on drones. These images capture the overall view or local area of ​​the farmland, including information such as the health status of the crops, environmental changes, possible pests and diseases, etc. The obtained original image I (x, y) will be used as input data for subsequent image processing.

[0036] The original image is usually affected by noise (for example, lighting changes, weather effects, etc.), so preprocessing is necessary to improve the image quality. Denoising algorithms (such as Gaussian filtering, median filtering, etc.) are used to remove noise from the image, while image enhancement (such as histogram equalization, contrast enhancement, etc.) can enhance image details, especially the tiny features of pests and diseases. The clear image I'(x,y) generated after preprocessing will provide higher quality data input for subsequent feature extraction and pest and disease detection.

[0037] Convolutional neural networks (CNNs) are used to automatically extract useful image features from a clear image I'(x,y). CNNs can identify local and global patterns in images, such as the color, shape, texture of crops, and the characteristics of pests and diseases. CNNs extract features at different levels through multiple convolutional layers and ultimately generate feature maps. F k(x, y), each point corresponds to the feature information of a certain position in the image. This process can effectively extract the key information of pests and diseases and provide a reliable basis for subsequent regional segmentation.

[0038] Feature map of the image F k (x, y) will be input into the image segmentation algorithm (such as the segmentation model based on U-Net). The algorithm can automatically distinguish between normal areas and pest areas by analyzing the feature information in the image, thereby accurately locating the location and range of pests and diseases. The resulting pest area R (x, y) will be transmitted to the control module to guide the drone to perform precise spraying.

[0039] The convolutional neural network convolution expression described in the embodiment of the present invention is: F k (x, y) = ∑ i,j W k (i, j)·I(x + i, y + j) + b k ; in, i Hewei j is the index of the convolution kernel, indicating the position offset of each element in the convolution kernel. W k Indicates The convolution kernels are located at (i, j) The weight of b k Represents the convolution kernel The bias term of the feature map, F k (x, y) Indicates The output feature map after the convolution kernel is at position (x, y) The value of Activation function (ReLU): A(x, y) = max(0, F(x, y)) ; Parameter explanation: I(x, y) : original input image; W k (i, j) : convolution kernel parameters; b k : bias term; F k (x, y) : Convolution output features; A(x, y) : Feature map after activation.

[0040] In one possible implementation, the convolution expression represents the operation of the convolutional layer in a convolutional neural network. Here, the input image I(x, y) will be convolved with the convolution kernel W k (i,j) performs convolution operation. The convolution kernel is a fixed-size matrix that contains the parameters learned by the network. These parameters can be trained to learn the features in the image (such as edges, textures, etc.). The result of the convolution operation is a feature map F k (x, y), which is generated by weighting the local area of ​​the input image, thereby extracting the local features of the image to a certain extent. The bias term b_k is a constant adjustment after the convolution operation, which is used to improve the performance of the network.

[0041] Furthermore, the ReLU function activates the feature map output by the convolution layer, outputting negative values ​​as zero and keeping positive values ​​unchanged. This nonlinear operation helps introduce nonlinear transformations, allowing the neural network to fit more complex patterns. The feature map A(x,y) activated by ReLU is smaller than the feature map after convolution. F k (x,y) can more effectively capture and express the salient features of the image. Through this activation process, the system can identify key elements in the image, such as changes in the crop surface, traces of pests and diseases, etc.

[0042] In a convolutional neural network, the input image I(x,y) and the convolution kernel W k The convolution operation of (i, j) generates a convolution feature map by performing weighted summation on the local area of ​​the image. F k (x,y). This local perception mechanism allows the network to extract useful spatial features from the input image, providing a basis for the detection of pests and diseases.

[0043] Feature map after convolutional layer processing F k (x, y) is further transformed by the ReLU activation function A(x, y), thereby filtering out negative values ​​in the features and retaining positive activation values. This process improves the network's sensitivity to image details and enables the neural network to better capture subtle changes in pests and diseases, avoiding some unimportant features from affecting system judgment.

[0044] The convolution process is often not a one-time process, but a multi-layer stacking process. After each layer of convolution kernel and activation function is combined, different levels of features are extracted, gradually converting complex image information into high-level semantic information. This hierarchical feature extraction mechanism ensures that the network can gradually identify and locate pest and disease areas in farmland, improving the accuracy of detection.

[0045] In the embodiment of the present invention, the sensor module data fusion unit has the following specific operating steps: T1: Obtain environmental sensor module data, including wind speed, wind direction, temperature, and humidity; T2: Use Kalman filtering to fuse the environmental sensor module data and estimate the environmental state x^(t).

[0046] In a possible implementation, the system first obtains multiple data of the current environment through the environmental sensor module, including wind speed, wind direction, temperature, humidity, etc. These data can reflect the environmental conditions and directly affect the accuracy of the spraying operation and the distribution effect of the agent. For example, wind speed and wind direction may affect the propagation direction and diffusion range of the spray droplets, and temperature and humidity may affect the evaporation speed and effect of the agent. Therefore, obtaining these sensor data provides a basis for subsequent calculations and judgments.

[0047] After obtaining the data from various sensors, the Kalman filter algorithm is used to fuse these data. Kalman filtering is a recursive estimation algorithm that can predict and correct the state of a dynamic system and estimate more accurate state information in the case of incomplete or noisy data. In this system, Kalman filtering calculates an optimal estimate (environmental state) by fusing data such as wind speed, wind direction, temperature and humidity from different sensors, thereby providing a more accurate environmental state model.

[0048] The specific steps of Kalman filtering include the following parts: Prediction step: Based on the estimated state at the previous moment and the dynamic model, predict the current state of the environment. The predicted state at this time is not necessarily accurate and may contain certain errors.

[0049] Update step: Use the newly acquired sensor data to correct the predicted state and reduce the estimation error. By calculating the Kalman gain, the system can weigh the importance of the current sensor data and the predicted data, and finally update the estimated value of the environmental state.

[0050] In the embodiment of the present invention, the Kalman filter specifically includes the following formula: Kalman filter prediction update equation: x ^ (t|t - 1) = Ax ^ (t - 1) + Bu(t - 1) ; P(t|t - 1) = AP(t - 1)A + Q ; Kalman gain: K(t) = P(t|t - 1)H(HP(t|t - 1)H + R)^(-1) ; Status Update: x^(t|t) = x^(t|t - 1) + K(t)(z(t) - Hx^(t|t - 1)) ; P(t|t) = (I - K(t)H)P(t|t - 1) ; Parameter explanation: x^(t|t - 1) : predicted state at time t; P(t|t - 1) : covariance matrix of predicted state; A, B : state transfer matrix, control input matrix; Q : process noise covariance; K(t) : Kalman gain; z(t) : Sensor module measurement value; H : represents the observation matrix, which is used to establish the relationship between the state vector and the observation value; R : Represents the observation noise covariance matrix, which is used to represent the error or noise of the observation value.

[0051] In one possible implementation, the core of Kalman filtering is to estimate the state by combining predictions and measurements. In the drone spraying system, the information such as wind speed and humidity provided by the environmental sensor module is usually interfered by noise, so there may be errors in making decisions directly using these measurement data. Kalman filtering effectively reduces the impact of noise by weighted fusion of predictions and actual measurement results, and obtains a more accurate estimate of the environmental state. In this way, the system can control spraying according to more precise environmental conditions.

[0052] In practical applications, sensor data may be delayed or unstable. Kalman filtering can dynamically adjust the trust in data based on previous state predictions and current measurement information, so that the system can cope with sudden sensor failures or data anomalies. This robustness is crucial for drones to continue operating in complex weather conditions.

[0053] Accurate environmental state estimation can help drones adjust spraying parameters such as flight speed, spraying angle and amount of medicine in real time during the spraying process to ensure accurate coverage of the medicine and reduce waste. For example, if the wind speed is too high, the system can increase the amount of medicine sprayed to compensate for the drift of the medicine, or adjust the flight altitude to reduce the impact of wind, thereby improving spraying efficiency and operation accuracy.

[0054] In the embodiment of the present invention, the decision-making unit has the following specific operating steps: F1: The pest area R(x,y) and the environmental status x^(t)Input to the decision-making unit to conduct pest and disease assessment and generate pest and disease severity scores S d (x, y) ; F2: Decide whether to spray based on the score. If it is decided to spray, the spraying angle is dynamically adjusted during the spraying process.

[0055] In a possible implementation, in step F1, the decision unit receives two input signals: Pest and disease area: This is a set of pest and disease information collected in real time by sensors carried by drones (such as image recognition equipment, infrared sensors, etc.). Each coordinate point represents a part of the crop field, and the sensor data will indicate the type and severity of pests and diseases in the area. This information can help decision-makers understand the distribution of pests and diseases and provide a basis for spraying decisions.

[0056] Environmental status: Environmental information provided in real time by environmental sensors (such as temperature, humidity, wind speed, etc.). Environmental status has an important impact on the spread and diffusion speed of pests and diseases and the effect of pesticide spraying. Therefore, the decision-making unit needs to integrate this data to predict the diffusion effect of the pesticide after spraying.

[0057] The above input signals are combined together to generate a pest severity score through the built-in pest assessment algorithm. The score reflects the severity of pests and diseases in different areas. The higher the score, the more serious the pests and diseases in the area, and the greater the amount of pesticides required for spraying. The generation of the score not only takes into account the number and type of pests and diseases, but also combines the influence of environmental factors.

[0058] Specifically, the decision unit first obtains input signals from two main sources: pest area information and environmental status information. Pest area information comes from the image processing and recognition unit, indicating whether there are pests and diseases on the crops, as well as the type and distribution of pests and diseases. Each position (x, y) contains pest and disease information in the area, including the type of pest and disease, area, and possible impact. These data are usually processed by an image processing and recognition unit (such as a convolutional neural network CNN) to generate a pest and disease area R (x, y).

[0059] Environmental status information is the environmental sensor data fused by the sensor module data fusion unit. These environmental factors have an important impact on the spread of pests and diseases and the spraying effect of the agent. For example, higher temperatures may promote the spread of pests and diseases, higher humidity may increase the instability of the spraying effect, and excessive wind speed may cause the drift of the drug. All of this information is processed by algorithms such as Kalman filtering to provide an accurate environmental state estimate x^(t).

[0060] Then, a pest severity score is generated. After obtaining the pest area information and environmental status information, the decision unit uses the built-in pest assessment algorithm to fuse and analyze the two signals to generate a pest severity score (Sd(x,y)). This score not only considers the type, quantity and distribution of pests and diseases, but also combines the environmental status to assess the potential threat of pests and diseases. The specific process is as follows: For the pest severity assessment, the algorithm first calculates the pest index of the area based on the characteristics of the pest area R(x,y). For example, in a specific area, different weights are assigned based on the type and quantity of pests and diseases (such as insect pests, fungi, etc.). The size of the area and the spread of pests and diseases will also affect the final score. The weight value of the pest type is determined through prior learning and database accumulation.

[0061] In addition, the crop and environmental state model plays a regulatory role in the evaluation process according to the environmental state x^(t). For example, when the temperature is high and the humidity is high, the spread of pests and diseases may be faster. In the case of high wind speed, the system will consider the spread range of the agent and the adjustment of the spraying angle, which will affect the adjustment of the spraying amount. Environmental factors such as wind speed and humidity have a significant impact on the spread of pests and diseases and the spraying effect of the agent. Therefore, it is necessary to comprehensively consider the impact of the environment on the spraying accuracy and efficacy. The crop and environmental state model plays a core role in the evaluation of the severity of pests and diseases. Specifically, the model combines crop state information such as the type, quantity, and spread range of pests and diseases, as well as environmental state information such as wind speed, humidity, and temperature to form a comprehensive pest and disease severity score. For a specific area, the type and quantity of pests and diseases (such as insect pests, fungi, etc.) are assigned different weights, which are determined based on historical data and learning algorithms. The spread range of pests and diseases and the size of the affected area will further affect the score. In addition, the environmental state x^(t) plays a regulatory role in the evaluation process. For example, when the temperature is high and the humidity is high, the spread of pests and diseases may be faster, and the score will increase accordingly; when the wind speed is high, the system will comprehensively evaluate the diffusion range and spraying angle of the agent, and adjust the spraying amount to ensure the efficacy. Through the crop and environmental state model, the system can comprehensively evaluate the threat level of pests and diseases, and formulate accurate spraying plans accordingly. Finally, based on all the above information, the severity score Sd(x, y) of pests and diseases in each area is generated through weighted processing. The higher the score, the more serious the pests and diseases in the area, and the system believes that the spraying need in the area is more urgent.

[0062] In addition, the flight path is used by the drone to determine the flight route during the spraying process to ensure that the pesticide can evenly cover the pest and disease area that needs to be treated. The process of calculating the optimal flight path is as follows: Input data: Based on pest severity score, environmental status information (such as wind speed, temperature, humidity) and geographical data of the flight area.

[0063] Path planning method: Use the shortest path algorithm (such as A* algorithm, Dijkstra algorithm, etc.) or area-based coverage algorithm (such as grid coverage algorithm, heuristic algorithm, etc.) to generate the flight path of the drone. By calculating the distribution density of the pest area, flight distance, flight altitude, obstacles, and the impact of environmental factors on the flight path, ensure that the path can effectively cover the pest area and avoid obstacles and dangerous areas.

[0064] Output: Flight path trajectory, usually including the flight start point, end point, waypoints and flight altitude, etc.

[0065] Spraying decision is used to dynamically adjust spraying parameters during the flight of the drone to ensure that the pesticide can be accurately sprayed to the pest area under different environmental conditions. The spraying control algorithm for spraying amount, spraying angle and spraying timing is: Input data: severity score of pest and disease areas, environmental status information, drone flight path, technical parameters of pesticide sprayers, etc.

[0066] Control strategy: Adjust the spraying amount according to the severity score of the pest and disease. Increase the spraying amount in areas with more serious pests and diseases, and reduce the spraying amount in areas with less severe pests and diseases.

[0067] Spraying angle adjustment: Dynamically adjust the spraying angle according to information such as wind speed, wind direction, and flight altitude to reduce the drift of the agent and ensure accurate spraying of the agent.

[0068] Spraying timing: Dynamically determine the spraying timing based on real-time environmental data (such as wind speed changes, temperature and humidity, etc.) to avoid poor efficacy or waste of the agent due to excessive wind speed or high humidity.

[0069] Output: spraying instructions, including spraying amount, spraying angle, spraying time and coverage of spraying area, etc.

[0070] In step F2, based on the severity score of the pests and diseases, the decision unit decides whether to start spraying. If the severity score of a certain area exceeds the preset threshold, the decision unit will issue a spraying command to instruct the drone to spray the area. Otherwise, the spraying will be skipped to avoid unnecessary waste of pesticides.

[0071] During the spraying process, the decision-making unit will also dynamically adjust the spraying angle according to the real-time environmental conditions. This process is crucial to improving spraying accuracy: Influence of environmental factors: For example, changes in wind speed and direction will affect the spraying effect of the pesticide. If the wind speed is high, the pesticide may drift with the wind, causing waste. The decision-making unit will adjust the spraying angle based on real-time wind speed and direction data to ensure that the pesticide is accurately sprayed in the areas with the most serious pests and diseases.

[0072] The morphology of the pest and disease area: The morphology and distribution of different pest and disease areas vary greatly. The decision-making unit dynamically adjusts the spraying angle according to the geometric shape and severity score of the pest and disease area to ensure that the pesticide evenly covers the pest and disease-dense areas and avoid unnecessary waste.

[0073] In the embodiment of the present invention, in F2, the spraying angle is dynamically adjusted according to the wind speed, wind direction, drone position and attitude, and the calculation formula is: ; in, is the initial spraying angle, is the wind speed, is the wind direction angle, is the pressure difference, and is the correction factor.

[0074] In one possible implementation, the initial spraying angle is a preset value of the drone spraying system, which is usually determined by the design parameters of the drone or the spraying task requirements. This angle represents the ideal working angle of the spraying equipment without the influence of external factors (such as changes in wind speed and wind direction).

[0075] Wind speed and wind direction are acquired in real time through the wind speed sensor and wind direction sensor on the drone. Wind speed indicates the strength of air flow, and wind direction indicates the direction of wind, usually expressed as an angle with the spraying direction. Wind speed and wind direction are important factors affecting the spraying effect. Excessive wind speed will cause the agent to drift, while wind direction determines whether the agent is blown to areas that do not need to be sprayed.

[0076] By calculation The system can dynamically adjust the spraying angle according to the wind speed and direction. Specifically, if the wind speed is high or the wind direction deviates from the ideal spraying direction, the spraying angle will be adjusted accordingly to ensure accurate spraying of the agent.

[0077] The pressure difference represents the change in nozzle pressure of the agent spraying device. The pressure difference change directly affects the injection speed and flow rate of the agent, and then affects the spraying range of the agent. By adjusting the spraying angle, the influence of the pressure difference on the spraying effect is compensated to ensure that the agent can be evenly covered in the predetermined area.

[0078] The calculation formula It is used to correct the spraying angle according to the change of pressure difference to compensate for the influence of pressure fluctuation on spraying accuracy.

[0079] Correction coefficients are constants obtained through experimental or simulation data debugging. Their function is to quantify the relationship between factors such as wind speed, wind direction, pressure difference and spraying angle. Due to different environmental conditions and different spraying tasks, the correction coefficients will be different, so they need to be adjusted according to the actual situation.

[0080] In an embodiment of the present invention, the spray module further includes an anti-clogging device, which includes an ultrasonic sensor and a vibration motor. The ultrasonic sensor is installed at the liquid inlet of the nozzle to detect the blockage of the nozzle. The vibration motor is installed at the base of the nozzle to periodically vibrate the nozzle to prevent the liquid from being blocked. The control module includes a central processing unit and a signal transceiver. When the central processing unit detects that the nozzle is blocked through the ultrasonic sensor, it sends a command to the vibration motor through the signal transceiver, and the vibration motor periodically vibrates the nozzle to clear the blockage. The drone also includes an autonomous obstacle avoidance module, which includes a millimeter-wave radar and an obstacle avoidance algorithm unit. The millimeter-wave radar is installed in the front, back, left, and right directions of the drone and is used to detect obstacles around the drone in real time. The obstacle avoidance algorithm unit is used to process the data of the millimeter-wave radar and generate obstacle avoidance instructions. The control module is also connected to a power management module. When the millimeter-wave radar detects an obstacle, the obstacle avoidance algorithm unit sends instructions to the power management module through a signal transceiver to adjust the speed and power of the motor so that the drone automatically bypasses the obstacle.

[0081] In a possible implementation, an ultrasonic sensor is installed at the liquid inlet of the nozzle, and monitors the flow state of the liquid medicine in real time by transmitting and receiving ultrasonic signals. When the liquid medicine flow is abnormal, the ultrasonic sensor can detect whether the nozzle is clogged. The sensor transmits the detected clog information to the central processor.

[0082] The vibration motor is installed on the base of the nozzle and is responsible for periodically vibrating the nozzle. Its operation is controlled by the central processor. When the ultrasonic sensor detects that the nozzle is clogged, the central processor sends a command to the vibration motor through the signal transceiver to start the vibration function. The vibration motor effectively clears the blockage in the nozzle through periodic vibration and restores the normal operation of the nozzle.

[0083] During the spraying operation, the ultrasonic sensor continuously monitors the flow of the nozzle. If a blockage is detected, the signal is transmitted to the central processor. The central processor immediately sends a command to the vibration motor through the signal transceiver to start the vibration motor to clean the nozzle, ensure that the nozzle is unobstructed and resume spraying. In this way, the nozzle can continue to work efficiently and reduce downtime or operation interruptions caused by blockage.

[0084] Millimeter-wave radars are installed in the front, back, left, and right directions of the drone to detect obstacles in the surrounding environment in real time. The radar can accurately measure the position and distance of obstacles by emitting millimeter-wave signals and receiving reflected signals. When an obstacle enters the detection range, the radar transmits the data to the central processor.

[0085] The obstacle avoidance algorithm unit is installed in the central processor and is responsible for processing the data from the millimeter wave radar. By analyzing the obstacle data, the obstacle avoidance algorithm unit can generate the optimal obstacle avoidance path and strategy. The generated obstacle avoidance command is sent to the drone's power management module through the signal transceiver.

[0086] After receiving the obstacle avoidance command, the power management module adjusts the motor speed and power of the drone to ensure that the drone bypasses the obstacle. During this process, the power management module adjusts the operating status of the motor in real time, allowing the drone to autonomously avoid obstacles and maintain a stable heading and flight.

[0087] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A drone precise spraying system for pest control, characterized by: It includes a drone, a spraying module, a sensor module, a data processing module and a control module, wherein the spraying module, the sensor module, the data processing module and the control module are all installed on the drone; The sensor module is electrically connected to the data processing module, and the collected data is transmitted to the data processing module. The data processing module is electrically connected to the control module, and the data processing module issues a control strategy to the control module. The control module is electrically connected to the UAV and the spraying module to execute the control strategy.

2. The system for precise spraying of pests and diseases by an unmanned aerial vehicle according to claim 1, characterized in that: The sensor module includes: Environmental sensor module: installed in multiple locations of the drone, including wind speed sensor module, wind direction sensor module, temperature sensor module, and humidity sensor module, used to monitor the environmental data around the drone in real time; Crop sensor module: installed at the bottom of the drone, including a camera and infrared sensor module, used to monitor crop growth and pests and diseases; Position sensor module: including GPS module and inertial measurement unit, used to monitor the position and attitude of the drone in real time; Liquid medicine sensor module: installed in the spray module, including flow sensor module and pressure sensor module, used to monitor the flow and pressure of the liquid medicine in real time.

3. The system for precise spraying of pests and diseases by an unmanned aerial vehicle according to claim 2, characterized in that: The data processing module includes an image processing and recognition unit, a sensor module data fusion unit and a decision unit. The image processing and recognition unit is used to process the image data obtained from the crop sensor module and identify the crop growth status and pest and disease areas. The sensor module data fusion unit is used to assist the decision unit in generating accurate spraying strategies.

4. The system for precise spraying of pests and diseases by an unmanned aerial vehicle according to claim 3 is characterized in that: The image processing and recognition unit has the following specific operating steps: S1: Obtain farmland image I(x,y) from the crop sensor module; S2: Generate a clear image I'(x,y) through preprocessing, including denoising and image enhancement; S3: Use convolutional neural network to extract image features and output feature maps F k (x,y) ; S4: Use segmentation algorithm to locate the pest area R(x,y).

5. The system for precise spraying of pests and diseases by an unmanned aerial vehicle according to claim 4, characterized in that: The convolutional neural network convolution expression is: F k (x,y)=∑ i,j W k (i,j)·I(x+i,y+j)+b k ； in, i Hewei j is the index of the convolution kernel, indicating the position offset of each element in the convolution kernel. W k Indicates The convolution kernels are located at (i,j) The weight of b k Represents the convolution kernel The bias term of the feature map, F k (x,y) Indicates The output feature map after the convolution kernel is at position (x,y) The value of Activation function (ReLU): A(x, y) = max(0, F(x, y)) ； Parameter explanation: I(x,y) : original input image; W k (i,j) : convolution kernel parameters; b k : bias term; F k (x,y) : Convolution output features; A(x,y) : Feature map after activation.

6. The system for precise spraying of pests and diseases by an unmanned aerial vehicle according to claim 5, characterized in that: The sensor module data fusion unit has the following specific operating steps: T1: Obtain environmental sensor module data, including wind speed, wind direction, temperature, and humidity; T2: Use Kalman filtering to fuse the environmental sensor module data and estimate the environmental state x^(t).

7. The system for precise spraying of pests and diseases by an unmanned aerial vehicle according to claim 6, characterized in that: The Kalman filter specifically includes the following formula: Kalman filter prediction update equation: x ^ (t|t-1)=Ax ^ (t-1)+Bu(t-1) ； P(t|t-1)= AP(t-1)A+Q ； Kalman gain: K(t)= P(t|t-1)H(HP(t|t-1)H+R)-1 ； Status Update: x^(t|t)=x^(t|t-1)+K(t)(z(t)-Hx^(t|t-1)) ； P(t|t)=(IK(t)H)P(t|t-1) ； Parameter explanation: x^(t|t-1) : predicted state at time t; P(t|t-1) : covariance matrix of predicted state; A,B : state transfer matrix, control input matrix; Q : process noise covariance; K(t) : Kalman gain; z(t) : Sensor module measurement value; H : represents the observation matrix, which is used to establish the relationship between the state vector and the observation value; R : Represents the observation noise covariance matrix, which is used to represent the error or noise of the observation value.

8. The system for precise spraying of pests and diseases by an unmanned aerial vehicle according to claim 7, characterized in that: The specific operation steps of the decision-making unit are as follows: F1: The pest area R(x,y) and the environmental status x^(t) Input to the decision-making unit to conduct pest and disease assessment and generate pest and disease severity scores S d (x, y) ; F2: Decide whether to spray based on the score. If it is decided to spray, the spraying angle is dynamically adjusted during the spraying process.

9. The system for precise spraying of pests and diseases by an unmanned aerial vehicle according to claim 8, characterized in that: In F2, the spraying angle is dynamically adjusted according to wind speed, wind direction, drone position and attitude. The calculation formula is: ； in, is the initial spraying angle, is the wind speed, is the wind direction angle, is the pressure difference, and is the correction factor.

10. The system for precise spraying of pests and diseases by an unmanned aerial vehicle according to claim 9, characterized in that: The spray module also includes an anti-clogging device, which includes an ultrasonic sensor and a vibration motor. The ultrasonic sensor is installed at the liquid inlet of the nozzle to detect the blockage of the nozzle. The vibration motor is installed at the base of the nozzle to periodically vibrate the nozzle to prevent the liquid from being blocked. The control module includes a central processing unit and a signal transceiver. When the central processing unit detects that the nozzle is blocked through the ultrasonic sensor, it sends a command to the vibration motor through the signal transceiver, and the vibration motor periodically vibrates the nozzle to clear the blockage. The drone also includes an autonomous obstacle avoidance module, which includes a millimeter-wave radar and an obstacle avoidance algorithm unit. The millimeter-wave radar is installed in the front, back, left, and right directions of the drone and is used to detect obstacles around the drone in real time. The obstacle avoidance algorithm unit is used to process the data of the millimeter-wave radar and generate obstacle avoidance instructions. The control module is also connected to a power management module. When the millimeter-wave radar detects an obstacle, the obstacle avoidance algorithm unit sends instructions to the power management module through a signal transceiver to adjust the speed and power of the motor so that the drone automatically bypasses the obstacle.

Images