Method for accurately regulating and controlling nutrients in whole growth period of litchis based on unmanned aerial vehicle
Through drones collecting data and using machine learning algorithms to establish a lychee growth model, automatically generate nutrition control solutions, solving the problems of low efficiency and environmental pollution of traditional lychee cultivation methods, realizing precise regulation and efficient management, and enhancing the adaptability of the system and robustness.
Patent Information
- Application Number
- CN202411062375.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-05
- Publication Date
- 2024-11-22
AI Technical Summary
Traditional lychee cultivation methods have high labor intensity and low efficiency, making it difficult to accurately control the use of fertilizers and pesticides, resulting in waste of resources and environmental pollution. The existing intelligent atomization cultivation system cannot effectively evaluate crop growth conditions and formulate corresponding cultivation strategies.
Using the drone-based nutritional precision control method for the whole growth period of litchi, the growth status and environmental parameters of litchi trees are collected in real time through the data acquisition module, and the growth model is established using machine learning algorithms to automatically generate nutritional control plans, including fertilizer types, concentrations and spraying. The application time is carried out, and the precise spraying of the drone is realized through the route planning and operation execution module. The monitoring and feedback module adjusts the strategy in real time to adapt to environmental changes.
Improve decision-making accuracy and response speed, reduce manual intervention, improve management efficiency and accuracy, achieve uniform coverage and efficient cultivation, enhance the adaptability and robustness of the system, and be able to predict and manage diseases and according to microclimate Change and adjust the work plan.
Smart Images

Figure CN119003985A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of plant cultivation technology, and in particular to a method for precise regulation of nutrient content of litchi during its entire growth period based on an unmanned aerial vehicle. Background Art
[0002] Traditional litchi cultivation mostly relies on manual fertilization and spraying of pesticides. This method is not only labor-intensive and inefficient, but also difficult to accurately control the amount of fertilizer and pesticide used, which easily leads to waste of resources and environmental pollution.
[0003] After searching, the application scheme of Chinese patent application number CN201710298673.3 discloses an intelligent atomization cultivation system and its control method, including a cultivator, a first controller, and a second controller. The first controller collects signals through the root internal temperature and humidity sensor, the root internal carbon dioxide sensor, the root external temperature and humidity sensor, the root external carbon dioxide sensor, the digital light intensity sensor, the PH sensor, and the immersion liquid level transmitter, and sends them to the second controller through the wireless transceiver. The second controller gives a control decision through multi-input fuzzy control to control the corresponding actions of the fan, heating wire, hydraulic solenoid valve, and atomizing nozzle to achieve wireless transmission control. The cultivation system in the above patent has the following shortcomings: it cannot well evaluate the crop growth conditions and environmental factors, and formulate corresponding cultivation strategies, which needs to be improved. Summary of the invention
[0004] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a method for precise regulation of nutrient content of litchi throughout its growth period based on an unmanned aerial vehicle.
[0005] In order to achieve the above object, the present invention adopts the following technical solutions:
[0006] A method for precise regulation of nutrient content of litchi during the entire growth period based on drones is implemented based on a nutrient regulation system, which includes:
[0007] Data collection module: including drones equipped with high-definition cameras, high / multi-spectral sensors, and soil detectors, which are used to collect real-time data on the growth status of litchi trees, soil nutrition, and environmental parameters;
[0008] Data processing and analysis module: Use machine learning algorithms to process the collected data, establish a litchi growth model, and predict litchi growth requirements based on real-time data;
[0009] Nutrition regulation scheme generation module: based on data processing results and the preset nutrition management knowledge base, automatically generates nutrition regulation schemes for each block, including fertilizer type, concentration, and spraying time;
[0010] Route planning and operation execution module: Plan the flight route of the drone based on the nutrient regulation plan and terrain information, and control the drone to perform foliar spraying as planned;
[0011] Monitoring and feedback module: real-time monitoring of drone operation status and litchi tree response, and adjustment of nutrient regulation schemes through feedback mechanisms to adapt to environmental changes.
[0012] Preferably, the method comprises the following steps:
[0013] S1: During the litchi shoot period, the leaf spectral data is obtained through high / multi-spectral sensors, and the nitrogen demand is calculated based on the soil nutrient test results;
[0014] S2: Determine the type and amount of fertilizer to be applied and generate a spraying plan based on the nitrogen demand and the preset nutrient database;
[0015] S3: The route planning module optimizes the flight path of the drone based on the litchi garden block division and terrain information to ensure uniform coverage and maximum efficiency;
[0016] S4: Execute the spraying operation, and the monitoring module collects the operation data and the response of the litchi tree in real time, and adjusts the subsequent nutrient management strategy by comparing the expected effect with the actual effect;
[0017] S5: Repeat the above steps during the flowering and fruiting periods, and adjust the nutrition plan according to different growth stages to achieve precise regulation.
[0018] Preferably: the data processing and analysis module comprises:
[0019] Data preprocessing unit: cleans, standardizes and synchronizes multi-source data to improve data quality and prepare for subsequent analysis;
[0020] Feature Extraction Unit: Extract key biological and environmental features from complex data for modeling and decision making;
[0021] Model training unit: Use machine learning algorithms to train prediction models;
[0022] Real-time data analysis unit: Uses streaming data processing technology to analyze real-time data and quickly provide feedback on decision support information.
[0023] Preferably, the data processing and analysis module trains the prediction model in the following manner:
[0024] For a dataset {(x1,y1),(x2,y2),…,(x n ,y n )}, where x i is the eigenvector, y iis the target variable, and the optimal parameter vector w and bias term b are found through linear regression so that the linear model y = w T x+b is the best predictor of y;
[0025] Among them, the loss function of linear regression uses mean square error, specifically:
[0026]
[0027] The loss function is minimized by the gradient descent algorithm, and the update rule is:
[0028]
[0029] Here, α is the learning rate.
[0030] Preferably: the nutrition regulation scheme generation module comprises:
[0031] Nutritional demand assessment unit: assess the nutritional demand of litchi at different growth stages based on data processing results;
[0032] Regulation strategy formulation unit: Combine agronomic knowledge and database to generate scientific fertilization and spraying plans;
[0033] Scheme Optimization Unit: Considering cost, efficiency and environmental impact, optimize the control scheme to achieve sustainable cultivation.
[0034] Preferably: the route planning and operation execution module includes:
[0035] Route calculation unit: calculates the optimal route based on the park map and operation objectives;
[0036] Task scheduling unit: arranges the execution time, sequence and collaborative operations of drones to avoid conflicts and duplication of work;
[0037] Operation execution unit: controls the drone to perform fixed-point spraying, fertilization or other management tasks;
[0038] Safety monitoring unit: real-time monitoring of the drone status and environment to ensure operational safety;
[0039] The monitoring and feedback module comprises:
[0040] Real-time monitoring unit: Tracking the progress of drone operations and the response of litchi trees;
[0041] Effect evaluation unit: evaluate the actual effect of nutritional regulation through comparative analysis and machine learning;
[0042] Feedback Adjustment Unit: Adjust nutrition programs and operation plans based on evaluation results to continuously improve management strategies.
[0043] Preferably: the nutrition regulation system further comprises:
[0044] Intelligent disease prediction and prevention module: Identify possible diseases of litchi; establish a prediction model for disease occurrence based on historical disease data and environmental factors, and automatically recommend prevention and control measures;
[0045] Microclimate simulation and analysis module: Combine meteorological data and geographic information system to use computational fluid dynamics to simulate microclimate changes in the litchi orchard; adjust the drone operation plan by analyzing the impact of microclimate on litchi growth;
[0046] Among them, the intelligent disease prediction and prevention module includes:
[0047] Disease Identification Unit: uses image recognition technology to detect signs of disease on litchi leaves and fruits;
[0048] Disease development prediction unit: predict disease development trends based on historical data and environmental models;
[0049] Prevention and control suggestion unit: Generate disease prevention and control plans, including pesticide types, dosage and spraying time;
[0050] Microclimate simulation and analysis modules include:
[0051] Microclimate data collection unit: integrates weather station data and drone observation data to obtain microclimate information;
[0052] Microclimate simulation unit: establish the microclimate model in the park through numerical simulation method;
[0053] Microclimate effect assessment unit: Analyze the impact of microclimate on litchi growth and guide management and operation adjustments.
[0054] Preferably, the microclimate simulation and analysis module, when establishing the microclimate model in the garden, specifically includes:
[0055] According to the basic fluid dynamics algorithm, the heat and humidity transfer algorithm is discretized by the finite difference method, the finite volume method or the finite element method and solved. The specific formula of the basic fluid dynamics algorithm is:
[0056]
[0057] Among them, ρ is the air density, u is the velocity vector, p is the pressure, μ is the dynamic viscosity coefficient, and F is the external force;
[0058] The specific formula for the heat and humidity transfer algorithm is:
[0059]
[0060] Where T is temperature, k is thermal conductivity, c p is the specific heat capacity;
[0061]
[0062] Where q is the specific humidity and D is the diffusion coefficient of water vapor.
[0063] Preferably: the nutrition regulation system further comprises:
[0064] Resource optimization allocation module: linear programming and optimization algorithms are used to determine the task allocation and scheduling of drones; based on factors such as drone power, spraying load, and estimated operation time, the operation sequence and path of drones are optimized to reduce energy consumption and improve operation efficiency;
[0065] Real-time data processing and intelligent decision support module: Integrate real-time data processing functions to upload data collected by drones and ground sensors to the cloud in real time through IoT technology; use complex event processing and streaming data analysis technology to quickly make nutrition regulation decisions and instantly update the instructions for drones to perform tasks;
[0066] Among them, the resource optimization allocation module includes:
[0067] Resource monitoring unit: real-time monitoring of drone resource status;
[0068] Optimization Algorithm Unit: Apply linear programming and constraint satisfaction problem solving to optimize resource allocation;
[0069] Task allocation unit: intelligently assign tasks to specific drones based on optimization results;
[0070] Real-time data processing and intelligent decision support modules include:
[0071] Real-time data receiving unit: build a data receiving framework to ensure the real-time and integrity of data;
[0072] Decision Analysis Unit: Uses complex event processing and online analytical processing technology to provide a basis for rapid decision-making;
[0073] Decision-making execution unit: Converts analysis results into operational instructions and automatically adjusts the operation of drones and other equipment.
[0074] Preferably: the nutrition regulation system further comprises:
[0075] Crop growth simulation and prediction module: Use plant growth models and machine learning methods to simulate the growth process of litchi based on historical data and current environmental conditions; predict the future growth trend of litchi and adjust management strategies in advance to adapt to the predicted results;
[0076] Genetic algorithm optimized fertilization strategy module: Optimize fertilization strategy using genetic algorithm, based on soil nutrient status, litchi growth stage and historical fertilization effects, find the optimal fertilization combination and timing through multiple generations of iterations;
[0077] Among them, the crop growth simulation and prediction module includes:
[0078] Growth data modeling unit: Use historical data and statistical models to build a basic model for litchi growth;
[0079] Growth prediction unit: combines environmental and nutritional data to predict the future growth of litchi;
[0080] Decision support unit: provides management suggestions based on forecast data to help farmers make scientific decisions;
[0081] The genetic algorithm optimized fertilization strategy module includes:
[0082] Genetic coding unit: Encode the fertilization strategy parameters into chromosomes in the genetic algorithm;
[0083] Adaptability evaluation unit: calculate the fitness of fertilization strategies and analyze the promotion effect of strategies on litchi growth;
[0084] Genetic operation unit: performs selection, crossover and mutation operations to continuously evolve fertilization strategies;
[0085] Strategy implementation unit: Apply the optimized fertilization strategy to actual nutrition management.
[0086] The beneficial effects of the present invention are:
[0087] 1. The present invention collects real-time data on litchi growth conditions, soil nutrition and environmental parameters through a data acquisition module, and uses a machine learning algorithm to establish a litchi growth model in a data processing and analysis module, thereby improving the accuracy and response speed of decision-making.
[0088] 2. The present invention automatically generates a nutrition control plan for each block based on the data analysis results and a preset nutrition management knowledge base, thereby reducing manual intervention and improving management efficiency and accuracy. The flight route of the drone is planned based on the nutrition control plan and terrain information to ensure uniform coverage and maximum efficiency. At the same time, the execution strategy is adjusted through real-time monitoring to adapt to environmental changes.
[0089] 3. The monitoring and feedback module of the present invention monitors the operation status of the UAV and the response of the litchi tree in real time, adjusts the nutrition regulation plan through the feedback mechanism, and realizes the continuous optimization of the management strategy; through the combination of the intelligent disease prediction and prevention module and the microclimate simulation and analysis module, the system can not only predict and manage diseases, but also adjust the operation plan according to microclimate changes, thereby enhancing the adaptability and robustness of the system. BRIEF DESCRIPTION OF THE DRAWINGS
[0090] Figure 1 This is a flow chart of a method for precise regulation of lychee nutrition throughout its growth period based on drones proposed in the present invention. DETAILED DESCRIPTION
[0091] The technical solution of the present invention is further described in detail below in conjunction with specific implementation methods.
[0092] Embodiment 1:
[0093] A method for precise regulation of nutrient content of litchi during the entire growth period based on drones is implemented based on a nutrient regulation system, which includes:
[0094] Data collection module: including high-definition cameras, high / multi-spectral sensors, soil detectors, etc. carried by drones, used to collect real-time data on the growth status of litchi trees, soil nutrition and environmental parameters;
[0095] Data processing and analysis module: Use machine learning algorithms to process the collected data, establish a litchi growth model, and predict litchi growth requirements based on real-time data;
[0096] Nutrition regulation plan generation module: based on data processing results and the preset nutrition management knowledge base, automatically generates nutrition regulation plans for each block, including fertilizer type, concentration, spraying time, etc.;
[0097] Route planning and operation execution module: Plan the flight route of the drone based on the nutrient regulation plan and terrain information, and control the drone to perform foliar spraying as planned;
[0098] Monitoring and feedback module: real-time monitoring of drone operation status and litchi tree response, and adjustment of nutrient regulation schemes through feedback mechanisms to adapt to environmental changes.
[0099] The method comprises the following steps:
[0100] S1: During the litchi shoot period, the leaf spectral data is obtained through high / multi-spectral sensors, and the nitrogen demand is calculated based on the soil nutrient test results;
[0101] S2: Determine the type and amount of fertilizer to be applied and generate a spraying plan based on the nitrogen demand and the preset nutrient database;
[0102] S3: The route planning module optimizes the flight path of the drone based on the litchi garden block division and terrain information to ensure uniform coverage and maximum efficiency;
[0103] S4: Execute the spraying operation, and the monitoring module collects the operation data and the response of the litchi tree in real time, and adjusts the subsequent nutrient management strategy by comparing the expected effect with the actual effect;
[0104] S5: Repeat the above steps during the flowering and fruiting periods, and adjust the nutrition plan according to different growth stages to achieve precise regulation.
[0105] Wherein, the data processing and analysis module includes:
[0106] Data preprocessing unit: cleans, standardizes and synchronizes multi-source data to improve data quality and prepare for subsequent analysis;
[0107] Feature Extraction Unit: Extract key biological and environmental features from complex data for modeling and decision making;
[0108] Model training unit: Use machine learning algorithms to train prediction models, such as litchi growth and disease occurrence;
[0109] Real-time data analysis unit: Uses streaming data processing technology to analyze real-time data and quickly provide feedback on decision support information.
[0110] The data processing and analysis module trains the prediction model in the following manner:
[0111] For a dataset {(x1,y1),(x2,y2),…,(x n ,y n )}, where x i is the eigenvector, y i is the target variable, and the optimal parameter vector w and bias term b are found through linear regression so that the linear model y = w T x+b is the best predictor of y;
[0112] Among them, the loss function of linear regression uses mean square error, specifically:
[0113]
[0114] The loss function is minimized by the gradient descent algorithm, and the update rule is:
[0115]
[0116] Here, α is the learning rate.
[0117] Wherein, the nutrition regulation scheme generation module includes:
[0118] Nutritional demand assessment unit: assess the nutritional demand of litchi at different growth stages based on data processing results;
[0119] Regulation strategy formulation unit: Combine agronomic knowledge and database to generate scientific fertilization and spraying plans;
[0120] Scheme Optimization Unit: Considering cost, efficiency and environmental impact, optimize the control scheme to achieve sustainable cultivation.
[0121] The route planning and operation execution module includes:
[0122] Route calculation unit: calculates the optimal route based on the park map and operation objectives;
[0123] Task scheduling unit: arranges the execution time, sequence and collaborative operations of drones to avoid conflicts and duplication of work;
[0124] Operation execution unit: controls the drone to perform fixed-point spraying, fertilization or other management tasks;
[0125] Safety monitoring unit: real-time monitoring of drone status and environment to ensure operational safety.
[0126] Wherein, the monitoring and feedback module includes:
[0127] Real-time monitoring unit: Tracking the progress of drone operations and the response of litchi trees;
[0128] Effect evaluation unit: evaluate the actual effect of nutritional regulation through comparative analysis and machine learning;
[0129] Feedback Adjustment Unit: Adjust nutrition programs and operation plans based on evaluation results to continuously improve management strategies.
[0130] Embodiment 2:
[0131] A method for precise regulation of nutrient content of litchi during the entire growth period based on drones. In this embodiment, based on embodiment 1, the nutrient regulation system further includes:
[0132] Intelligent disease prediction and prevention module: Identify possible diseases of litchi; establish a prediction model for disease occurrence based on historical disease data and environmental factors, and automatically recommend prevention and control measures;
[0133] Microclimate simulation and analysis module: Combine meteorological data and geographic information system to use computational fluid dynamics to simulate microclimate changes in the litchi orchard; by analyzing the impact of microclimate on litchi growth, adjust the drone operation plan, such as selecting the best spraying time to ensure the maximum efficiency of fertilizers and pesticides;
[0134] Among them, the intelligent disease prediction and prevention module includes:
[0135] Disease Identification Unit: uses image recognition technology to detect signs of disease on litchi leaves and fruits;
[0136] Disease development prediction unit: predict disease development trends based on historical data and environmental models;
[0137] Prevention and control suggestion unit: Generate disease prevention and control plans, including pesticide types, dosage and spraying time;
[0138] Microclimate simulation and analysis modules include:
[0139] Microclimate data collection unit: integrates weather station data and drone observation data to obtain microclimate information;
[0140] Microclimate simulation unit: establish the microclimate model in the park through numerical simulation method;
[0141] Microclimate effect assessment unit: Analyze the impact of microclimate on litchi growth and guide management and operation adjustments.
[0142] The microclimate simulation and analysis module, when establishing the microclimate model in the garden, specifically includes:
[0143] According to the basic fluid dynamics algorithm, the heat and humidity transfer algorithm is discretized by the finite difference method, the finite volume method or the finite element method and solved. The specific formula of the basic fluid dynamics algorithm is:
[0144]
[0145] Among them, ρ is the air density, u is the velocity vector, p is the pressure, μ is the dynamic viscosity coefficient, and F is the external force;
[0146] The specific formula for the heat and humidity transfer algorithm is:
[0147]
[0148] Where T is temperature, k is thermal conductivity, c p is the specific heat capacity;
[0149]
[0150] Where q is the specific humidity and D is the diffusion coefficient of water vapor.
[0151] Embodiment 3:
[0152] A method for precise regulation of nutrient content of litchi during the entire growth period based on drones. In this embodiment, based on embodiment 2, the nutrient regulation system further includes:
[0153] Resource optimization allocation module: linear programming and optimization algorithms are used to determine the task allocation and scheduling of drones; based on factors such as drone power, spraying load, and estimated operation time, the operation sequence and path of drones are optimized to reduce energy consumption and improve operation efficiency;
[0154] Real-time data processing and intelligent decision support module: Integrate real-time data processing functions to upload data collected by drones and ground sensors to the cloud in real time through IoT technology; use complex event processing and streaming data analysis technology to quickly make nutrition regulation decisions and instantly update the instructions for drones to perform tasks;
[0155] Among them, the resource optimization allocation module includes:
[0156] Resource monitoring unit: real-time monitoring of drone resource status, such as power, load capacity and operating capacity;
[0157] Optimization Algorithm Unit: Apply linear programming and constraint satisfaction problem solving to optimize resource allocation;
[0158] Task allocation unit: intelligently assign tasks to specific drones based on optimization results;
[0159] Real-time data processing and intelligent decision support modules include:
[0160] Real-time data receiving unit: build a data receiving framework to ensure the real-time and integrity of data;
[0161] Decision Analysis Unit: Uses complex event processing and online analytical processing technology to provide a basis for rapid decision-making;
[0162] Decision-making execution unit: Converts analysis results into operational instructions and automatically adjusts the operation of drones and other equipment.
[0163] Embodiment 4:
[0164] A method for precise regulation of lychee nutrition during the entire growth period based on drones. This embodiment is based on embodiment 3, and the nutrition regulation system further includes:
[0165] Crop growth simulation and prediction module: Use plant growth models and machine learning methods to simulate the growth process of litchi based on historical data and current environmental conditions; predict the future growth trend of litchi and adjust management strategies in advance to adapt to the predicted results;
[0166] Genetic algorithm optimized fertilization strategy module: Optimize fertilization strategy using genetic algorithm, based on multi-dimensional information such as soil nutrient status, litchi growth stage and historical fertilization effect, and find the optimal fertilization combination and timing through multiple generations of iteration;
[0167] Among them, the crop growth simulation and prediction module includes:
[0168] Growth data modeling unit: Use historical data and statistical models to build a basic model for litchi growth;
[0169] Growth prediction unit: combines environmental and nutritional data to predict the future growth of litchi;
[0170] Decision support unit: provides management suggestions based on forecast data to help farmers make scientific decisions;
[0171] The genetic algorithm optimized fertilization strategy module includes:
[0172] Genetic coding unit: Encode the fertilization strategy parameters into chromosomes in the genetic algorithm;
[0173] Adaptability evaluation unit: calculate the fitness of fertilization strategies and analyze the promotion effect of strategies on litchi growth;
[0174] Genetic operation unit: performs selection, crossover and mutation operations to continuously evolve fertilization strategies;
[0175] Strategy implementation unit: Apply the optimized fertilization strategy to actual nutrition management.
[0176] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.
Claims
1. A method for precise regulation of litchi nutrition during the entire growth period based on drones, characterized in that: It is based on the nutrition regulation system, which includes: Data collection module: including drones equipped with high-definition cameras, high / multi-spectral sensors, and soil detectors, which are used to collect real-time data on the growth status of litchi trees, soil nutrition, and environmental parameters; Data processing and analysis module: Use machine learning algorithms to process the collected data, establish a litchi growth model, and predict litchi growth requirements based on real-time data; Nutrition regulation scheme generation module: based on data processing results and the preset nutrition management knowledge base, automatically generates nutrition regulation schemes for each block, including fertilizer type, concentration, and spraying time; Route planning and operation execution module: Plan the flight route of the drone based on the nutrient regulation plan and terrain information, and control the drone to perform foliar spraying as planned; Monitoring and feedback module: real-time monitoring of drone operation status and litchi tree response, and adjustment of nutrient regulation schemes through feedback mechanisms to adapt to environmental changes.
2. The method for precise regulation of litchi nutrition during the entire growth period based on an unmanned aerial vehicle according to claim 1, characterized in that: The steps include: S1: During the litchi shoot period, the leaf spectral data is obtained through high / multi-spectral sensors, and the nitrogen demand is calculated based on the soil nutrient test results; S2: Determine the type and amount of fertilizer to be applied and generate a spraying plan based on the nitrogen demand and the preset nutrient database; S3: The route planning module optimizes the flight path of the drone based on the litchi garden block division and terrain information to ensure uniform coverage and maximum efficiency; S4: Execute the spraying operation, and the monitoring module collects the operation data and the response of the litchi tree in real time, and adjusts the subsequent nutrient management strategy by comparing the expected effect with the actual effect; S5: Repeat the above steps during the flowering and fruiting periods, and adjust the nutrition plan according to different growth stages to achieve precise regulation.
3. The method for precise regulation of litchi nutrition during the entire growth period based on an unmanned aerial vehicle according to claim 1, characterized in that: The data processing and analysis module comprises: Data preprocessing unit: cleans, standardizes and synchronizes multi-source data to improve data quality and prepare for subsequent analysis; Feature Extraction Unit: Extract key biological and environmental features from complex data for modeling and decision making; Model training unit: Use machine learning algorithms to train prediction models; Real-time data analysis unit: Uses streaming data processing technology to analyze real-time data and quickly provide feedback on decision support information.
4. The method for precise regulation of litchi nutrition during the entire growth period based on an unmanned aerial vehicle according to claim 3, characterized in that: The method of training the prediction model by the data processing and analysis module is specifically as follows: For a dataset {(x1,y1),(x2,y2),…,(x n ,y n )}, where x i is the eigenvector, y i is the target variable, and the optimal parameter vector w and bias term b are found through linear regression so that the linear model y = w T x+b is the best predictor of y; Among them, the loss function of linear regression uses mean square error, specifically: The loss function is minimized by the gradient descent algorithm, and the update rule is: Here, α is the learning rate.
5. The method for precise regulation of litchi nutrition during the entire growth period based on an unmanned aerial vehicle according to claim 1, characterized in that: The nutrition regulation scheme generation module comprises: Nutritional demand assessment unit: assess the nutritional demand of litchi at different growth stages based on data processing results; Regulation strategy formulation unit: Combine agronomic knowledge and database to generate scientific fertilization and spraying plans; Scheme Optimization Unit: Considering cost, efficiency and environmental impact, optimize the control scheme to achieve sustainable cultivation.
6. The method for precise regulation of litchi nutrition during the entire growth period based on an unmanned aerial vehicle according to claim 1, characterized in that: The route planning and operation execution module includes: Route calculation unit: calculates the optimal route based on the park map and operation objectives; Task scheduling unit: arranges the execution time, sequence and collaborative operations of drones to avoid conflicts and duplication of work; Operation execution unit: controls the drone to perform fixed-point spraying, fertilization or other management tasks; Safety monitoring unit: real-time monitoring of the drone status and environment to ensure operational safety; The monitoring and feedback module comprises: Real-time monitoring unit: Tracking the progress of drone operations and the response of litchi trees; Effect evaluation unit: evaluate the actual effect of nutritional regulation through comparative analysis and machine learning; Feedback Adjustment Unit: Adjust nutrition programs and operation plans based on evaluation results to continuously improve management strategies.
7. The method for precise regulation of litchi nutrition during the entire growth period based on an unmanned aerial vehicle according to claim 1, characterized in that: The nutrition regulation system also includes: Intelligent disease prediction and prevention module: Identify possible diseases of litchi; establish a prediction model for disease occurrence based on historical disease data and environmental factors, and automatically recommend prevention and control measures; Microclimate simulation and analysis module: Combine meteorological data and geographic information system to use computational fluid dynamics to simulate microclimate changes in the litchi orchard; adjust the drone operation plan by analyzing the impact of microclimate on litchi growth; Among them, the intelligent disease prediction and prevention module includes: Disease Identification Unit: uses image recognition technology to detect signs of disease on litchi leaves and fruits; Disease development prediction unit: predict disease development trends based on historical data and environmental models; Prevention and control suggestion unit: Generate disease prevention and control plans, including pesticide types, dosage and spraying time; Microclimate simulation and analysis modules include: Microclimate data collection unit: integrates weather station data and drone observation data to obtain microclimate information; Microclimate simulation unit: establish the microclimate model in the park through numerical simulation method; Microclimate effect assessment unit: Analyze the impact of microclimate on litchi growth and guide management and operation adjustments.
8. The method for precise regulation of litchi nutrition during the entire growth period based on an unmanned aerial vehicle according to claim 7, characterized in that: The microclimate simulation and analysis module, when establishing the microclimate model in the garden, specifically includes: According to the basic fluid dynamics algorithm, the heat and humidity transfer algorithm is discretized by the finite difference method, the finite volume method or the finite element method and solved. The specific formula of the basic fluid dynamics algorithm is: Among them, ρ is the air density, u is the velocity vector, p is the pressure, μ is the dynamic viscosity coefficient, and F is the external force; The specific formula for the heat and humidity transfer algorithm is: Where T is temperature, k is thermal conductivity, c p is the specific heat capacity; Where q is the specific humidity and D is the diffusion coefficient of water vapor.
9. The method for precise regulation of litchi nutrition during the entire growth period based on an unmanned aerial vehicle according to claim 1, characterized in that: The nutrition regulation system also includes: Resource optimization allocation module: linear programming and optimization algorithms are used to determine the task allocation and scheduling of drones; based on factors such as drone power, spraying load, and estimated operation time, the operation sequence and path of drones are optimized to reduce energy consumption and improve operation efficiency; Real-time data processing and intelligent decision support module: Integrate real-time data processing functions to upload data collected by drones and ground sensors to the cloud in real time through IoT technology; use complex event processing and streaming data analysis technology to quickly make nutrition regulation decisions and instantly update the instructions for drones to perform tasks; Among them, the resource optimization allocation module includes: Resource monitoring unit: real-time monitoring of drone resource status; Optimization Algorithm Unit: Apply linear programming and constraint satisfaction problem solving to optimize resource allocation; Task allocation unit: intelligently assign tasks to specific drones based on optimization results; Real-time data processing and intelligent decision support modules include: Real-time data receiving unit: build a data receiving framework to ensure the real-time and integrity of data; Decision Analysis Unit: Uses complex event processing and online analytical processing technology to provide a basis for rapid decision-making; Decision-making execution unit: Converts analysis results into operational instructions and automatically adjusts the operation of drones and other equipment.
10. The method for precise regulation of litchi nutrition during the entire growth period based on an unmanned aerial vehicle according to claim 1, characterized in that: The nutrition regulation system also includes: Crop growth simulation and prediction module: Use plant growth models and machine learning methods to simulate the growth process of litchi based on historical data and current environmental conditions; predict the future growth trend of litchi and adjust management strategies in advance to adapt to the predicted results; Genetic algorithm optimized fertilization strategy module: Optimize fertilization strategy using genetic algorithm, based on soil nutrient status, litchi growth stage and historical fertilization effects, find the optimal fertilization combination and timing through multiple generations of iterations; Among them, the crop growth simulation and prediction module includes: Growth data modeling unit: Use historical data and statistical models to build a basic model for litchi growth; Growth prediction unit: combines environmental and nutritional data to predict the future growth of litchi; Decision support unit: provides management suggestions based on forecast data to help farmers make scientific decisions; The genetic algorithm optimized fertilization strategy module includes: Genetic coding unit: Encode the fertilization strategy parameters into chromosomes in the genetic algorithm; Adaptability evaluation unit: calculate the fitness of fertilization strategies and analyze the promotion effect of strategies on litchi growth; Genetic operation unit: performs selection, crossover and mutation operations to continuously evolve fertilization strategies; Strategy implementation unit: Apply the optimized fertilization strategy to actual nutrition management.
Citation Information
Patent Citations
Intelligent atomization culture system and control method thereof
CN107203132A
Unmanned aerial vehicle intelligent spraying system and method based on prescription map
CN109353504A
Terrace mechanized operation method based on unmanned aerial vehicle transfer
CN112034883A
Agricultural robot path position control system
CN116820109A
Agricultural production management system and method based on machine learning and Internet of Things technology
CN117114448A
Cited By
Mulberry field monitoring method and system based on Internet of Things
CN119227978A
Rice planting equipment with high enzyme activity and planting method thereof
CN119422585A
Wheat growth regulation and yield prediction integrated method based on artificial intelligence
CN120952231A
Hillside orchard fertilization equipment with intelligent detection and precise fertilization functions and fertilization method
CN121100650A
Underforest cultivation area microclimate precise regulation and control system based on unmanned aerial vehicle
CN121680089A
