Detection management system and management method based on automatic spraying fertilization of crops

Abstract

The invention discloses an automatic spraying fertilization detection management system and management method based on crop cultivation, and the management system comprises a positioning module, a detection module, a spraying control module, a fertilization control module and a processor module, and the positioning module is used for obtaining and marking the position of a corresponding soil plot; and providing the soil plot positioning data. The detection module collects to-be-detected soil plot information; the spraying control module is used for controlling the switching value of the first sprayer, the advancing path of the first sprayer and the spraying time; the fertilization control module controls the switching value of the second sprayer, the advancing path of the second sprayer and the spraying time; according to the management method, the processor module has a self-adaptive learning function according to a built-in crop growth model database, and model parameters can be optimized according to actual growth conditions of crops; automation of crop irrigation and fertilization is achieved, the yield and quality of crops are improved, and agricultural production management is optimized.

Description

Technical Field

[0001] The present invention relates to the technical field of agricultural automation, and in particular to a system and method for detecting and managing automatic spraying and fertilizing of crops, which can realize precise irrigation and fertilization and comprehensive management of crops. Background Art

[0002] In modern agricultural production, with the development of large-scale land management, traditional artificial spray fertilization is inefficient and difficult to ensure accuracy. Crop growth has a high degree of specificity in terms of soil conditions, water and nutrients. Irrational irrigation and fertilization may lead to resource waste, environmental pollution, and reduced crop yield and quality.

[0003] Prior art CN202121308920.1 discloses the field of greenhouse spraying technology, specifically a spraying system for intelligent identification of species partitions for smart agriculture, which includes a spraying device, a species partition identification device, a controller, and a species partition identifier; the species partition identification device is installed on the spraying device; the species partition identifier is installed in the species partition. The utility model can intelligently identify the species attributes of the area to be sprayed and intelligently control the intensity of the spraying.

[0004] However, the above technology cannot reasonably control the growth cycle and external environmental parameters of various species, nor can it be automatically optimized, which leads to its poor practicality.

[0005] Therefore, there is a need for an intelligent, highly automated and automatically optimized system, and an automatic spray fertilization detection management system and management method that can accurately meet the growth needs of crops is an issue that technical personnel in the field urgently need to solve. Summary of the invention

[0006] In view of this, the present invention provides an intelligent, highly automated and automatically optimized system, as well as an automatic spray fertilization detection management system and management method that can accurately meet the growth needs of crops.

[0007] In order to achieve the above object, the present invention adopts the following technical solution:

[0008] A detection and management system based on automatic spraying and fertilization of crops, comprising:

[0009] A positioning module, the positioning module is used to obtain and mark the position of the corresponding soil block; and provide the soil block positioning data;

[0010] A detection module, wherein the detection module collects information of a soil plot to be detected;

[0011] a spray control module, the spray control module receiving data associated with the information of the soil plot to be detected collected by the detection module, and controlling a switch value of the first sprayer, a travel path of the first sprayer, and a spraying time;

[0012] A fertilization control module, the fertilization control module receives data associated with the information of the soil plot to be detected of the detection module set, and controls the switch value of the second sprayer, the travel path of the second sprayer, and the spraying time;

[0013] The processor module is responsible for coordinating the work between the above modules, receiving information from the positioning module and the detection module, and sending the processed instructions to the spray control module and the fertilization control module;

[0014] The processor module is internally provided with a crop growth model database and an optimization algorithm, wherein the optimization algorithm is a least squares method to optimize a linear regression model or a gradient descent algorithm.

[0015] Furthermore, it also includes a data storage module, which is used to store the detection data of the detection module, the historical records of the spray control module and the fertilization control module, the relevant data of the corresponding crop growth of the corresponding soil plot located by the positioning module, and the communication data between the processor module and the above modules;

[0016] The data storage module is in communication with the processor module, the detection module, the spray control module and the fertilization control module.

[0017] Furthermore, it also includes a user interaction module and a network communication module, wherein the user interaction module provides a user interface, allowing the user to input instructions, view system status and historical data, and adjust spraying and fertilization parameters;

[0018] The network communication module is responsible for exchanging data with external devices or networks to achieve remote monitoring and control functions.

[0019] Furthermore, the positioning module uses a combination of GPS or BDS and geographic information system GIS to obtain and mark soil plot location information.

[0020] Furthermore, the detection module includes a soil moisture sensor based on the time domain reflectometry (TDR) principle, a soil nutrient sensor using ion selective electrode technology or near infrared spectroscopy analysis technology, and a sensor for detecting atmospheric temperature, humidity, wind speed, wind direction, and carbon dioxide concentration.

[0021] A method for detecting and managing automatic spraying and fertilization of crops, comprising the following steps:

[0022] S1, dividing the plots, using the positioning module to obtain the location information of the soil plots and divide them into sub-areas; and setting the corresponding detection modules in the above sub-areas;

[0023] S2, collecting corresponding soil and environmental data through the corresponding detection module, and the processor module analyzes the data of the detection module according to the corresponding positioned crop growth model and generates spraying and fertilization control instructions;

[0024] S3, the spray control module and the fertilization control module control the sprayer to move along a preset path and control the spraying time according to the instruction;

[0025] S4, the data storage module stores and manages system data;

[0026] S5, the user checks and adjusts system parameters through the user interaction module, and the network communication module realizes remote monitoring and data transmission.

[0027] Furthermore, in step S2, during data analysis and instruction generation, the crop growth model database of the processor module covers the water and nutrient demand patterns of different crops at various growth stages, and has an adaptive learning function, which can optimize model parameters according to the actual growth conditions of crops.

[0028] Furthermore, the adaptive learning is to clean the collected data, remove outliers and erroneous data, and normalize and standardize the data. The processed data is compared with the ideal data of the corresponding crop growth stage in the crop growth model database. If there is a difference, the linear regression model or gradient descent algorithm is optimized by the least squares method, and the parameters of the model regarding the water and nutrient requirements of the crops are updated according to the error between the actual data and the model predicted data.

[0029] Furthermore, the user interaction module displays system data in visual charts and supports multi-user permission management. The network communication module uses encryption protocols for data transmission and can connect to external data sources to obtain information.

[0030] The automatic spray fertilization detection and management method for crops of the present invention is used in paddy fields, dry land, open-air orchards, vegetable / fruit greenhouses, tea gardens, or forage planting.

[0031] The present invention accurately obtains soil plot information through the positioning module, does not rely on specific cards or RFID electronic tags, and reduces manual labor when planting on a large scale; the processor module covers the water and nutrient requirements of different crops at various growth stages based on the built-in crop growth model database, and the crop growth model database of the processor module has an adaptive learning function, which can optimize the model parameters according to the actual growth conditions of the crops. The spray control module and the fertilization control module can automatically control the operation of the sprayer according to the instructions generated by the processor module, without the need for manual irrigation and fertilization operations in each area. It supports multi-user authority management, and users of different levels have different operating authorities, which can not only ensure the security of the system, but also meet the operation and management needs of different personnel, such as farm technicians, managers, owners, etc.

[0032] The present invention realizes automation and precision of crop irrigation and fertilization through accurate acquisition and detection of soil plot information, as well as intelligent control of spraying and fertilization. It also supports data storage, user interaction and remote monitoring functions to improve crop yield and quality and optimize agricultural production management. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0034] Figure 1 This is a modular schematic diagram of the automatic spraying and fertilization detection and management system for crops;

[0035] Figure 2 The present invention is a flow chart of the detection and management method of automatic spray fertilization for crops. DETAILED DESCRIPTION

[0036] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0037] This embodiment provides a management system and a management method based on automatic spraying and fertilization detection of crops.

[0038] The present invention utilizes high-precision positioning technology (such as GPS, BDS, etc.), namely, the positioning module 1 to obtain and mark the corresponding soil plot position, and generate accurate positioning data at the same time. These data include not only the latitude and longitude information of the plot, but also the geometric features such as the area and shape of the plot, providing a basis for subsequent precision operations. The positioning module can also be integrated with a geographic information system (GIS) to achieve a more detailed geographical analysis of the plot, such as analyzing the impact of factors such as the slope and orientation of the plot on the irrigation and fertilization effects. By docking with the overall planning system of the farm, the positioning module can incorporate soil plot information into the macro-management of the farm, facilitating resource allocation and production arrangements.

[0039] Detection module 2: Integrates a variety of advanced sensors, such as soil moisture sensors, soil nutrient sensors using capacitive or time domain reflectometry principles, that is, based on ion selective electrodes or near-infrared spectroscopy analysis technology. Comprehensively collect information on the soil plot to be detected, including the physical and chemical properties of the soil and real-time changes. In addition, the detection module can also be equipped with meteorological sensors to collect data such as atmospheric temperature, humidity, wind speed, and wind direction, because these meteorological factors will affect soil moisture evaporation and the absorption of moisture and nutrients by crops. The layout of the sensors adopts a distributed network structure to ensure comprehensive coverage and accurate detection of the entire soil plot.

[0040] Spray control module 3: Receives data collected by the detection module, and uses the built-in intelligent algorithm to accurately control the switch value, travel path and spraying time of the first sprayer according to the water demand model of crops at different growth stages. For example, during the peak period of crop water demand, the spraying time and coverage can be appropriately increased. The spray control module can also adjust the spraying strategy according to meteorological data, such as lowering the spraying height or adjusting the spraying angle when the wind speed is high to reduce water drift loss. At the same time, it can be connected to the water supply system of the irrigation water source to adjust the water supply pressure and flow as needed to ensure the stability of the spraying effect.

[0041] Fertilization control module 4: According to the data transmitted by the detection module and the nutrient model required for crop growth, the switch value, travel path and spraying time of the second sprayer are accurately controlled. According to different soil fertility conditions and crop growth stages, the fertilization strategy is reasonably adjusted. The fertilization control module can accurately control the type, concentration and ratio of fertilizers to meet the special needs of different crops. In addition, it can also work with the fertilizer storage and delivery system to realize automatic fertilizer replenishment and mixing, ensuring the continuity and accuracy of fertilization.

[0042] Processor module 5: As the core coordinator of the system, it is responsible for receiving information from the positioning module and the detection module. After complex calculations and analysis, it sends the processed instructions to the spray control module and the fertilization control module to ensure the coordinated work of the entire system. The processor module uses a high-performance microprocessor chip with powerful data processing and multi-tasking capabilities. It has a built-in crop growth model database. These models are established through a large number of field tests and data analysis, covering the water and nutrient requirements of different crops at various growth stages. In addition, the processor module also has an adaptive learning function, which can continuously optimize the model parameters according to the actual growth of crops and improve the accuracy of the system.

[0043] Data storage module 6: used to store the detection data of the detection module, the historical records of the spray control module and the fertilization control module, and the relevant data of the corresponding crop growth of the corresponding soil plot located by the positioning module. A large-capacity, high-reliability storage medium, such as a solid-state hard drive or a disk array, is used to ensure the safe storage and fast reading and writing of data. The data storage module also has data backup and recovery functions to prevent data loss due to unexpected situations. At the same time, it can classify, index and compress the stored data to facilitate subsequent data query and analysis.

[0044] User interaction module 7: Provides a simple and intuitive user interface, supports users to input commands, view system status and historical data through touch, buttons, etc., and can easily adjust spraying and fertilization parameters. For example, users can fine-tune the thresholds of irrigation and fertilization according to crop varieties and actual growth conditions. The user interaction module also provides visual charts and report functions, presenting complex data to users in an intuitive form, such as soil moisture change curves, fertilizer application statistics charts, etc., to help users better understand the crop growth environment and system operation. In addition, the user interaction module supports multi-user authority management, and users of different levels (such as farmers, technicians, operators) have different operating permissions to ensure the security of the system.

[0045] Network communication module 8: Use wired or wireless communication technology (such as 4G / 5G, Ethernet, etc.) to exchange data with external devices or networks to achieve remote monitoring and control functions. Farm managers can remotely manage the system through mobile phone APP or web page to obtain system information and operate in time. The network communication module also supports connection with external data sources such as agricultural research institutions and meteorological departments to obtain the latest crop planting technology, weather forecasts and other information, providing more basis for system decision-making. At the same time, it has data encryption and secure transmission mechanisms to ensure the confidentiality and integrity of system data during network transmission.

[0046] Example 1: Application in corn plantation

[0047] Working process of positioning module 1: In the corn plantation, the positioning module is started to quickly determine the boundary and center coordinates of the plantation. Assume that the plantation is rectangular, with a length of [X1] meters, a width of [Y1] meters, and a center coordinate of ([longitude value 1], [latitude value 1]). The plantation is divided into multiple small squares of equal area, and the coordinate information of each square is accurately recorded to provide a location reference for subsequent precise operations. At the same time, combined with GIS data, it is analyzed that the slope of the plantation is [slope value 1] degrees and the orientation is [orientation direction 1]. This information is used to optimize the spraying and fertilization path to ensure uniform coverage under different terrain conditions. The positioning module synchronizes the location information of the plantation with the overall planning system of the farm. Farm managers can clearly see the distribution and related attributes of the corn plantation on the farm map, which is convenient for the overall arrangement of irrigation water sources, fertilizer supply and other resources.

[0048] Working process of detection module 2: The soil moisture sensor in the detection module detects different depths of the soil every [time interval 1] hours. The results show that the average humidity at a depth of 0-20 cm is [humidity value 1] during the corn seedling stage. The soil nutrient sensor detects that the nitrogen content in the soil is [nitrogen content value 1], the phosphorus content is [phosphorus content value 1], and the potassium content is [potassium content value 1] before sowing. During the growth of corn, the temperature sensor monitors the soil temperature range in real time to be [temperature range 1], and the pH sensor measures the soil pH value to be [pH value 1]. In addition, the meteorological sensor detects that the atmospheric temperature is [atmospheric temperature value 1], the humidity is [atmospheric humidity value 1], the wind speed is [wind speed value 1], and the wind direction is [wind direction value 1]. These data are transmitted to the processor module in real time through the wireless sensor network. The sensor network adopts a low-power, high-reliability communication protocol to ensure the stability and timeliness of data transmission, and can work normally even in complex farmland environments.

[0049] Working process of spray control module 3: The processor module determines the need for irrigation based on the detection data and the water requirement model of corn seedlings. The spray control module calculates the opening of [number of first sprayers 1] sprayers and sets the spraying time to [spraying time 1] minutes based on the plantation area, the spraying radius of the first sprayer ([radius value 1] meters) and the flow rate ([flow rate value 1] cubic meters / hour). According to the preset serpentine path, starting from one end of the plantation, each small square is evenly irrigated in turn to ensure that the soil moisture meets the growth requirements of corn. Considering the influence of wind speed ([wind speed value 1]) and wind direction ([wind direction value 1]), the spray control module adjusts the spraying angle of some sprayers and reduces the spraying height by [height reduction value 1] meters to reduce the dispersion of water outside the plantation. At the same time, it communicates with the water supply system of the irrigation water source and adjusts the water supply pressure to [water supply pressure value 1] Pascal to ensure that the spraying flow of the first sprayer is stable at the set value.

[0050] Working process of fertilization control module 4: According to the soil nutrient test results and the nutrient demand model of corn seedlings, it is found that the nitrogen content is slightly low. The fertilization control module controls the second sprayer to open, and plans the travel path according to the fertilizer concentration ([fertilization concentration value 1]%), the spraying angle of the second sprayer ([angle value 1] degrees) and the fertility distribution of the small squares, focusing on fertilizing areas with low nitrogen content, and the fertilization time is set to [fertilization time 1] minutes. The fertilization control module works in conjunction with the fertilizer storage and delivery system to accurately extract mixed fertilizers containing appropriate amounts of nitrogen fertilizers from the storage tank and adjust the fertilizer ratio as needed. During the fertilization process, the flow and pressure of the fertilizer are monitored in real time to ensure the accuracy and uniformity of fertilization.

[0051] Processor module 5 working process: As the core coordinator of the system, processor module 5 is responsible for receiving information from positioning module 1 and detection module 2. After complex calculations and analysis, it sends the processed instructions to spray control module 3 and fertilization control module 4 to ensure the coordinated work of the entire system. Processor module 5 uses a high-performance microprocessor chip with powerful data processing and multi-tasking capabilities. It has a built-in crop growth model database. For leafy vegetables grown in greenhouses, its growth model is established through a large number of field tests and data analysis in greenhouse environments, covering the demand for water and nutrients for leafy vegetables at various growth stages. In addition, the processor module also has an adaptive learning function, which can continuously optimize the model parameters and improve the accuracy of the system according to the actual growth of leafy vegetables in the greenhouse, such as the actual growth rate, leaf color and other appearance performances reflecting the growth trend, so that the subsequent spraying and fertilization control is more in line with the actual growth needs of vegetables, ensuring that vegetables can grow healthily and vigorously in the greenhouse.

[0052] Data storage module 6 working process: store the humidity value, nutrient value, temperature, pH value, meteorological data, spraying and fertilization parameters, time and other data detected this time to provide data support for subsequent analysis of corn growth and optimization of the system. The data storage module classifies and stores data according to dimensions such as date, time, and sensor type, and generates indexes for easy and quick query. At the same time, the data is compressed to save storage space. Every [backup cycle 1] days, the data storage module automatically backs up the data to an external storage device to prevent data loss due to hardware failure and other reasons.

[0053] User interaction module 7 working process: Farm staff can view the current status of the system through the user interaction module, including soil moisture, nutrient status, spraying and fertilization progress, etc. The user interface displays data in the form of intuitive charts, such as a line chart of soil moisture changes and a bar chart of fertilizer application. At the same time, the parameters of spraying and fertilization can be fine-tuned through the user interface according to the actual growth performance of corn, such as leaf color and growth rate. For example, if the corn leaves are slightly yellowed, the amount of fertilizer can be appropriately increased or the fertilizer ratio can be adjusted. The user interaction module also supports multi-user login, and different users have different permissions. The farmer has the highest authority and can view and modify all system parameters; technicians can view detailed data and make some parameter adjustments; operators can only view the system status and perform basic operations.

[0054] Network communication module 8 working process: The network communication module transmits system data to the server of the farm management office in real time. Farm managers can remotely monitor the situation of the corn plantation through mobile APP or web page. If abnormalities are found, system parameters can be adjusted in time. The network communication module uses SSL / TLS encryption protocol to encrypt data transmission to ensure the security of data during network transmission. At the same time, it establishes a connection with the server of agricultural research institutions to obtain the latest corn planting technology information and research results, and provide a reference for farm production management. In addition, it communicates with the server of the meteorological department to obtain more accurate weather forecast information, adjust the spraying and fertilization plans in advance, and deal with possible weather conditions such as drought or heavy rain.

[0055] Example 2: Application in vegetable greenhouses

[0056] Working process of positioning module 1: In the vegetable greenhouse, the positioning module accurately determines the location of each planting area in the greenhouse. Assume that there are multiple planting beds in the greenhouse, and the shape and position of each planting bed are accurately located. For example, the coordinate range of a planting bed is ([longitude interval 2], [latitude interval 2]), and the area is [area value 2] square meters. The positioning module also detects the light distribution in the greenhouse. By setting up multiple light sensors in the greenhouse, the light intensity and light duration data at different locations are obtained. These data are combined with soil position information to analyze the special needs of different planting areas for irrigation and fertilization, because light conditions will affect the photosynthesis and water transpiration of vegetables. In addition, the positioning module can further integrate the detailed location information of the planting areas in these greenhouses with the overall geographic information system (GIS) of the farm, and analyze the impact of factors such as the slope of the planting area in the relatively independent environment of the greenhouse (although the slope in the greenhouse is usually small, there may still be subtle differences that affect water flow, etc.), orientation, etc. on the irrigation and fertilization effects, and connect with the overall planning system of the farm to incorporate the information of each soil plot in the vegetable greenhouse into the macro-management scope of the farm, so as to facilitate the rational allocation of resources such as irrigation water and fertilizer, as well as subsequent production arrangements.

[0057] Working process of detection module 2: The detection module performs high-frequency detection on the soil in the vegetable greenhouse. The soil moisture sensor detects once every [interval 2] minutes and finds that in the early growth stage of leafy vegetables, the soil moisture at a depth of 0-15cm is [humidity value 2]. The soil nutrient sensor detects that the phosphorus content is [phosphorus content value 2] and the potassium content is [potassium content value 2]. The temperature sensor shows that the soil temperature is [temperature value 2], and the pH sensor measures the pH value as [pH value 2]. At the same time, the meteorological sensor in the greenhouse detects that the air temperature is [atmospheric temperature value 2], the humidity is [atmospheric humidity value 2], and the carbon dioxide concentration is [carbon dioxide concentration value 2]. These data are crucial for understanding the vegetable growth environment and adjusting management strategies. The detection module transmits all data to the processor module through wired communication. The wired communication method has better anti-interference ability in the greenhouse environment and ensures the accuracy of data transmission. In addition, the sensors in the detection module are arranged in various key positions in the greenhouse using a distributed network structure to ensure comprehensive coverage and accurate detection of the soil plots in the entire planting area of ​​the greenhouse, without missing any subtle environmental changes that may affect the growth of vegetables.

[0058] Working process of spray control module 3: The processor module controls the spray control module based on the water demand model and detection data of leafy vegetables in the early growth stage. According to the planting bed area and the parameters of the first sprayer (spraying radius [radius value 2] meters, flow rate [flow rate value 2] cubic meters / hour), it is determined to open [number of first sprayers 2] sprayers, and the spraying time is [spraying time 2] minutes. The sprayer moves inward in a circular trajectory along the edge of the planting bed to ensure that every corner can be evenly irrigated. Considering the air humidity in the greenhouse ([atmospheric humidity value 2]), the spray control module will combine real-time meteorological data and built-in intelligent algorithms to further fine-tune the spraying strategy, such as appropriately reducing the spraying amount when the air humidity is high to avoid soil water accumulation affecting the growth of vegetable roots; at the same time, if there is local ventilation in the greenhouse, resulting in differences in air flow in different areas, the spraying angle of each sprayer can be fine-tuned accordingly to ensure that water can fall accurately on the vegetable planting area, and minimize the attachment of water to other non-planting areas in the greenhouse or the waste caused by unreasonable spraying. In addition, the spray control module can also be connected to the water supply system of the irrigation water source in the greenhouse, and the water supply pressure and flow rate can be adjusted as needed to ensure the stability of the spraying effect. Even when there are certain water pressure fluctuations in the water supply system, a stable and appropriate spraying state can be maintained to meet the water needs of leafy vegetables in the early growth stages.

[0059] Working process of fertilization control module 4: The fertilization control module accurately controls the switch value, travel path and spraying time of the second sprayer according to the soil nutrients (such as the detected phosphorus content is [phosphorus content value 2], potassium content is [potassium content value 2], etc.) and the nutrient model required for the early growth of leafy vegetables transmitted by the detection module. According to the current soil fertility status in the greenhouse and the characteristics of the growth stage of leafy vegetables, the fertilization strategy is reasonably adjusted, such as accurately controlling the type of fertilizer (selecting the ratio of nitrogen fertilizer, phosphorus fertilizer, potassium fertilizer, etc. suitable for the early growth of leafy vegetables), concentration (determining the appropriate addition concentration according to the existing nutrient content of the soil to avoid excess or insufficient nutrients) and ratio to meet the special needs of leafy vegetables. In addition, it can also work with the fertilizer storage and delivery system installed in the greenhouse to realize automatic replenishment and mixing of fertilizers, ensuring the continuity and accuracy of fertilization. For example, when the reserve of a certain fertilizer is insufficient during the spraying process, it can automatically replenish the corresponding fertilizer from the storage system in time and continue to spray after mixing according to the set ratio, ensuring that vegetables can continue to obtain sufficient and appropriate nutrient supply.

[0060] Processor module 5 working process: As the core coordinator of the system, the processor module is responsible for receiving information from the positioning module and the detection module. After complex calculations and analysis, the processed instructions are sent to the spray control module and the fertilization control module to ensure the coordinated work of the entire system. The processor module uses a high-performance microprocessor chip with powerful data processing and multi-tasking capabilities. It has a built-in crop growth model database. For leafy vegetables grown in greenhouses, its growth model is established through a large number of field tests and data analysis in greenhouse environments, covering the demand for water and nutrients for leafy vegetables at various growth stages. In addition, the processor module also has an adaptive learning function, which can continuously optimize the model parameters according to the actual growth of leafy vegetables in the greenhouse (such as the actual growth rate, the growth trend reflected by the appearance of the leaves, such as color), improve the accuracy of the system, and make the subsequent spraying and fertilization control more in line with the actual growth needs of vegetables, ensuring that vegetables can grow healthily and vigorously in the greenhouse.

[0061] Working process of data storage module 6: The data storage module is used to store the detection data of the detection module, the historical records of the spray control module and the fertilization control module, and the growth-related data of the corresponding crops (i.e., leafy vegetables in the greenhouse) corresponding to the soil plot located by the positioning module. A large-capacity, high-reliability storage medium, such as a solid-state hard drive or a disk array, is used to ensure the safe storage and fast reading and writing of data. The data storage module also has data backup and recovery functions to prevent data loss due to unexpected situations that may occur in the greenhouse (such as power failures, sudden equipment failures, etc.). At the same time, it can classify, index and compress the stored data to facilitate subsequent data query and analysis. For example, when it is necessary to view the soil moisture changes or fertilizer application trends at a certain growth stage of leafy vegetables, the corresponding data can be quickly and accurately retrieved and presented in an intuitive form, providing strong data support for adjusting management strategies.

[0062] User interaction module 7 working process: The user interaction module provides a simple and intuitive user interface, supports users to input instructions, view system status and historical data through touch, buttons, etc., and can easily adjust the parameters of spraying and fertilization. For example, users can fine-tune the thresholds of irrigation and fertilization according to the varieties of leafy vegetables grown in the greenhouse (different leafy vegetable varieties may have slight differences in water and nutrient requirements) and actual growth conditions (such as when abnormal phenomena such as yellowing of vegetable leaves are observed). The user interaction module also provides visual charts and report functions, presenting complex data to users in an intuitive form, such as soil moisture change curves, fertilizer application statistics charts, etc., to help users better understand the vegetable growth environment and system operation, and facilitate users to intuitively judge whether the current management strategy is appropriate and whether further adjustments are needed. In addition, the user interaction module supports multi-user authority management. Users of different levels (such as farmers, technicians, and operators) have different operating permissions to ensure the security of the system. For example, farmers can make comprehensive parameter adjustments and system settings, technicians can view detailed data and give professional suggestions, and operators mainly execute daily operating instructions.

[0063] Network communication module 8 working process: The network communication module uses wired or wireless communication technology (such as 4G / 5G, Ethernet, etc.) to exchange data with external devices or networks to achieve remote monitoring and control functions. Farm managers can remotely manage the system in the vegetable greenhouse through mobile phone APP or web page, obtain system information in time and operate. For example, even if they are not at the greenhouse site, they can check the data detected by each sensor, the operating status of each control module, etc. at any time, and remotely adjust the spraying and fertilization parameters according to actual conditions. The network communication module also supports connection with external data sources such as agricultural research institutions and meteorological departments to obtain the latest crop planting technology, weather forecast and other information. For vegetable greenhouses, spraying and fertilization strategies can be adjusted in advance according to weather forecasts to cope with possible weather changes (such as cooling, rainfall, etc. on the growth environment of vegetables in the greenhouse), providing more basis for system decision-making. At the same time, it has data encryption and secure transmission mechanisms to ensure the confidentiality and integrity of system data during network transmission, prevent important data related to vegetable planting in the greenhouse from being leaked or tampered with, and ensure the safe and stable operation of the entire management system.

[0064] The present invention also proposes a detection and management method based on automatic spraying and fertilization of crops. Through the accurate acquisition and detection of soil plot information, and the intelligent control of spraying and fertilization, the automation and precision of crop irrigation and fertilization are realized. At the same time, it supports data storage, user interaction and remote monitoring functions to improve crop yield and quality and optimize agricultural production management.

[0065] 2. Specific methods and steps

[0066] 1. Positioning and data collection

[0067] The positioning module 1 uses high-precision positioning technologies such as GPS and BDS combined with the GIS system to obtain the location information of the soil plot, including longitude and latitude, area, shape, slope, orientation, and light distribution, etc., divide the soil plot into multiple sub-areas, and record the coordinate information of each sub-area.

[0068] The various sensors (soil moisture sensor, soil nutrient sensor, soil temperature sensor, pH sensor, meteorological sensor, etc.) in the detection module 2 collect soil and environmental information of each sub-area at set time intervals, including soil moisture at different depths, nutrient content such as nitrogen, phosphorus and potassium, temperature, pH value, and atmospheric temperature, humidity, wind speed, wind direction, carbon dioxide concentration and other data, and transmit the data to the processor module 5.

[0069] (II) Data Analysis and Instruction Generation

[0070] After receiving the data from the detection module 2, the processor module 5 analyzes the difference between the soil and environmental data and the crop requirements based on the built-in crop growth model database and the types and growth stages of the crops currently planted. For soil moisture data, it determines whether irrigation is needed based on the water demand model of crops at different growth stages; for soil nutrient data, it determines whether fertilization is needed and the type and amount of fertilization based on the nutrient model required for crop growth.

[0071] According to the analysis results, the processor module 5 generates control instructions and sends them to the spray control module 3 and the fertilization control module 4. The instruction content includes parameters such as the switch value, travel path, spraying time, spraying angle, water supply or fertilizer supply pressure and flow adjustment of the first sprayer and the second sprayer.

[0072] (III) Spraying and fertilization control

[0073] Spray control

[0074] The spray control module 3 controls the first sprayer to open according to the instructions of the processor module 5. The number of sprayers to be opened is calculated based on the area of ​​the planting area, the spray radius and flow parameters of the first sprayer, and the travel path is planned in combination with the sub-area coordinate information and considering meteorological factors (such as wind speed and wind direction). During the spraying process, the spraying height and angle are adjusted as needed, and the water supply pressure and flow are adjusted in coordination with the irrigation water source supply system to ensure uniform irrigation and reduce water loss.

[0075] After the irrigation is completed, the spray control module 3 feeds back the execution result to the processor module 5.

[0076] Fertilization control

[0077] The fertilization control module 4 controls the second sprayer to start according to the instructions of the processor module 5. The route and working time of the second sprayer are planned according to the soil fertility distribution, crop planting density, fertilization parameters of the second sprayer (fertilization concentration, spraying angle, etc.) and the nutrients that need to be supplemented. At the same time, it works in coordination with the fertilizer storage and transportation system to accurately extract and allocate fertilizers to ensure the accuracy and uniformity of fertilization.

[0078] After the fertilization operation is completed, the fertilization control module 4 feeds back the fertilization situation to the processor module 5 .

[0079] (IV) Data storage and management

[0080] The data storage module 6 receives and stores the detection data of the detection module 2, the execution parameters and history records of the spray control module 3 and the fertilization control module 4, the positioning data of the positioning module 1, and the crop growth-related data. The data is classified and stored (by date, time, sensor type, sub-area, etc.), indexed, and compressed to facilitate query and save storage space.

[0081] Automatically back up data to external storage devices according to the set backup cycle to prevent data loss.

[0082] 5. User interaction and remote monitoring

[0083] The user inputs commands, checks system status and historical data through the user interaction module 7. The user interaction module 7 displays data in visual charts (such as line charts, bar charts, etc.), such as soil moisture changes, fertilizer application statistics, etc. The user can fine-tune the spraying and fertilization parameters through the user interface according to the actual growth performance of crops (such as leaf color, growth rate, etc.). At the same time, the user interaction module 7 supports multi-user authority management, and users of different levels have different operation authorities.

[0084] The network communication module 8 transmits system data to the server in real time, and farm managers can remotely monitor the system through mobile phone APP or web page. The network communication module 8 uses encryption protocol to ensure the security of data transmission, and can connect with external data sources such as agricultural research institutions and meteorological departments to obtain the latest planting technology and weather forecast information for adjusting system parameters and plans. Specific embodiments

[0086] Example 3: Rice field irrigation and fertilization management

[0087] Positioning and data collection

[0088] In the rice field, the positioning module 1 determines the boundary and shape of the rice field. For example, the rice field is an irregular polygon with an area of ​​[X] square meters and a center coordinate of ([longitude value X], [latitude value X]). The rice field is divided into multiple square sub-areas with a side length of [side length value X] meters. At the same time, the slope of the rice field and the surrounding water system are analyzed through GIS, and the light sensor detects the light intensity in different areas.

[0089] The soil moisture sensor in the detection module 2 detects the humidity of the soil depth of 0-30cm every [time interval X1] hours, and the result shows that during the rice tillering period, the average humidity is [humidity value X1]. The soil nutrient sensor detects that the nitrogen content is [nitrogen content value X1], the phosphorus content is [phosphorus content value X1], and the potassium content is [potassium content value X1]. The temperature sensor shows that the soil temperature is [temperature range X1], and the pH value sensor measures the pH value as [pH value X1]. The meteorological sensor detects that the atmospheric temperature is [atmospheric temperature value X1], the humidity is [atmospheric humidity value X1], the wind speed is [wind speed value X1], and the wind direction is [wind direction value X1]. These data are transmitted to the processor module 5.

[0090] Data analysis and instruction generation

[0091] Processor module 5 compares the detection data according to the water and nutrient model of the rice tillering period. Since the humidity is lower than the required value and the nitrogen content is slightly low, an instruction is generated: open [number of first sprayers X] first sprayers for irrigation, the flow rate of each sprayer is [flow value X] cubic meters / hour, and the spraying time is [spraying time X1] minutes; open [number of second sprayers X] second sprayers for fertilization, the fertilizer concentration is [fertilizer concentration value X]%, and the fertilizer time is [fertilization time X2] minutes. At the same time, adjust the angle of the first sprayer according to the wind direction, and plan the route of the second sprayer according to the fertility distribution of the rice field.

[0092] Spraying and fertilization control

[0093] The spray control module 3 controls the first sprayer to irrigate each sub-area starting from one side of the rice field according to the instruction, and coordinates with the irrigation water source to adjust the water supply pressure to [water supply pressure value X] Pascal. During the irrigation process, the spraying angle is dynamically adjusted according to the change of wind speed.

[0094] The fertilization control module 4 controls the second sprayer to fertilize according to the planned path, extracts mixed fertilizer containing an appropriate amount of nitrogen fertilizer from the fertilizer storage tank, and controls the fertilization concentration and flow rate by adjusting the fertilization pipeline valve.

[0095] Data storage and management

[0096] The data storage module 6 stores all the collected data, control instructions and execution status. For example, the date is used as the folder, and the file is named according to the sensor type and sub-area number to store the data. At the same time, the data is indexed to facilitate the query of humidity, nutrients and other data of a sub-area at a specific time. Data backup is performed at 2 am every day.

[0097] User interaction and remote monitoring

[0098] The farm technician checks the system status through the user interaction module 7 and finds that the rice growth in some sub-areas is slightly slow. He adjusts the fertilization parameters of the area through the user interface to increase the nitrogen fertilizer supply. The farm manager checks the overall situation of the rice field through the mobile phone APP. After receiving the heavy rain warning information from the meteorological department, he remotely suspends the irrigation plan through the network communication module 8.

[0099] Example 4: Orchard irrigation and fertilization management

[0100] Positioning and data collection

[0101] In the orchard, the positioning module 1 determines the position coordinates of each fruit tree and the terrain information of the orchard. For example, the orchard is trapezoidal, with an area of ​​[Y] square meters, and has [number of fruit trees Y] fruit trees. The coordinates of each fruit tree are accurately recorded. The light sensor is used to analyze the differences in light duration and intensity of the fruit trees.

[0102] The soil moisture sensor in the detection module 2 detects the humidity of the soil depth of 0-60cm around the fruit tree every [time interval Y1] hours. The result shows that during the fruit expansion period, the average soil humidity in a certain area is [humidity value Y1]. The soil nutrient sensor detects the content of trace elements such as calcium and magnesium, as well as the content of nitrogen, phosphorus and potassium, such as the calcium content is [calcium content value Y1]. The temperature sensor shows that the soil temperature is [temperature range Y1], and the pH value sensor measures the pH value as [pH value Y1]. The meteorological sensor detects that the atmospheric temperature is [atmospheric temperature value Y1], the humidity is [atmospheric humidity value Y1], the wind speed is [wind speed value Y1], and the wind direction is [wind direction value Y1]. The data is transmitted to the processor module 5.

[0103] Data analysis and instruction generation

[0104] The processor module 5 analyzes the data according to the demand model of the fruit trees for water and nutrients during the fruit expansion period. For areas with insufficient humidity and low calcium content, an instruction is generated: turn on the corresponding first and second sprayers. The spraying parameters (quantity, flow rate, time, etc.) of the first sprayer are determined according to the planting density of the fruit trees and the soil moisture. The fertilization parameters of the second sprayer are adjusted according to the degree of calcium deficiency and the distribution of the fruit trees, while considering the influence of wind direction on the spraying effect.

[0105] Spraying and fertilization control

[0106] The spray control module 3 controls the first sprayer to spray in a circular trajectory around the fruit tree, and adjusts the spray radius and height according to the size of the fruit tree crown to ensure that the water evenly covers the root range of the fruit tree. In the case of wind, the spray direction is adjusted to maintain a certain angle with the wind direction to reduce the dispersion of water.

[0107] The fertilization control module 4 controls the second sprayer to focus on fertilizing areas with low calcium content, and adjusts the fertilizer formula and spraying angle to make the fertilizer accurately fall on the soil surface where calcium needs to be supplemented. During the fertilization process, it cooperates with the fertilizer supply system to ensure a stable supply and accurate ratio of calcium fertilizer.

[0108] Data storage and management

[0109] The data storage module 6 stores all the data of the orchard in categories, including the historical moisture and nutrient change data of the soil around each fruit tree. The data is compressed to save storage space. A full data backup is performed every [backup period Y] days, and an incremental backup is performed after each major operation (such as fertilizer formula adjustment).

[0110] User interaction and remote monitoring

[0111] The orchard manager can check the growth data of fruit trees through the user interaction module 7. If the fruit of a certain variety of fruit trees is found to have cracked fruit, it is suspected to be related to the calcium supply. The orchard manager can check the calcium fertilization history data through the user interface and adjust the fertilization plan. The orchard owner can obtain the overall irrigation and fertilization report of the orchard through the web-based remote monitoring system, and receive the latest fruit tree cultivation technology information pushed by agricultural research institutions, and apply it to system management through the network communication module 8.

[0112] The following is a detailed description of how the processor module uses the crop growth model database for adaptive learning in the data analysis and instruction generation steps:

[0113] 1. Data Analysis Phase

[0114] Data Collection

[0115] Collect real-time data on the crop growth environment from various sensors, such as soil moisture sensors and nutrient content monitors. These data include but are not limited to soil moisture, soil nutrients such as nitrogen, phosphorus, and potassium content, air temperature, light intensity, etc., and also record actual growth indicators of crops, such as plant height, number of leaves, fruit size, etc.

[0116] For example, for wheat crops, during their jointing stage, the soil moisture collected was 60%, the nitrogen content was 30 mg per kg of soil, and the wheat plant height was measured to be around 30 cm.

[0117] Data preprocessing

[0118] Clean the collected data to remove outliers and erroneous data. For example, if a soil moisture sensor fails, it may return a data point that is outside the normal range of 0-100%, such as 150%, which needs to be identified and corrected or removed.

[0119] Standardize the data to make different types of data comparable. For example, standardize the temperature data, which ranges from -10℃ to 40℃, and the soil nutrient data, which ranges from 0 to 100 mg / kg, to a suitable numerical range for subsequent data analysis.

[0120] Comparative analysis with the model

[0121] The preprocessed data is compared with the ideal data of the corresponding crop growth stage in the crop growth model database. For example, in the tasseling period of corn, the model stipulates that the suitable soil moisture is 70% to 80%, while the actual collected data shows that the soil moisture is 60%, and the difference can be found.

[0122] Analyze the possible impact of data differences on crop growth. For example, the low soil moisture mentioned above may cause corn plants to grow slowly and leaves to turn yellow.

[0123] 2. Instruction Generation Phase

[0124] Parameter Tuning Decisions

[0125] Based on the results of data comparison and analysis, it is decided whether the parameters of the crop growth model need to be adjusted. If the difference is large and continues to occur, it indicates that the model may need to be optimized. For example, if the soil potassium content of rice at the booting stage is detected to be lower than the optimal value set in the model for a week in a row, and the rice leaf tips turn yellow, it is necessary to consider adjusting the parameters of the model regarding the potassium demand of rice at the booting stage.

[0126] Consider the actual growth performance of crops to determine the direction and magnitude of adjustments. If crops are only slightly affected, only small adjustments to model parameters may be necessary; if crop growth is severely hampered, larger adjustments may be required.

[0127] Model parameter update

[0128] Use appropriate algorithms to update model parameters. For example, machine learning algorithms such as gradient descent can be used to update the parameters of crop water and nutrient requirements in the model based on the error between actual data and model predictions.

[0129] Taking tomatoes as an example, assuming that the original model sets the absorption coefficient of tomatoes for phosphorus fertilizer during the fruiting period to 0.8, data analysis shows that the actual absorption situation deviates from the model prediction. After the algorithm is updated, the absorption coefficient is adjusted to 0.9, so that the model better meets the actual growth needs of tomatoes for phosphorus fertilizer.

[0130] Instruction generation and output

[0131] Generate specific instructions based on the updated model parameters. These instructions may include adjusting the amount of irrigation, changing the type and amount of fertilizer, etc. For example, for cucumbers at their peak, based on the updated model, the instructions generated are "increase the frequency of irrigation from once a day to twice a day, with an irrigation volume of 5 liters each time; and increase the amount of nitrogen fertilizer by 5 grams per square meter."

[0132] These instructions are sent to the corresponding agricultural equipment control systems (such as irrigation systems and fertilization systems) to achieve precise control of the crop growth environment. At the same time, the execution of the instructions and the subsequent growth data of the crops are fed back for the next round of adaptive learning.

[0133] More specifically: The optimization of model parameters using comparative analysis results is mainly done in the following ways:

[0134] Data collection and preprocessing

[0135] The detection module is used to collect various data in the crop growth environment, including soil moisture, soil nutrients, soil temperature, pH value, and meteorological data. For example, in corn plantation applications, soil moisture sensors detect different depths of soil at regular intervals, soil nutrient sensors detect nitrogen, phosphorus, potassium and other contents, temperature sensors and pH sensors monitor corresponding data in real time, and meteorological sensors collect atmospheric temperature, humidity, wind speed, wind direction and other data; in vegetable greenhouse applications, soil moisture sensors detect soil moisture at high frequencies, soil nutrient sensors detect phosphorus and potassium contents, temperature sensors and pH sensors obtain data, and meteorological sensors in the greenhouse detect air temperature, humidity, carbon dioxide concentration, etc. These data are preprocessed, such as cleaning abnormal values ​​and erroneous data, and standardization, in preparation for subsequent comparative analysis.

[0136] Comparative analysis with the model

[0137] Compare the preprocessed data with the ideal data of the corresponding crop growth stage in the crop growth model database. For example, in a corn plantation, compare the actual soil moisture, nutrient content and other data of the corn seedling stage with the ideal data of the model at this stage to determine whether there is a difference. In a vegetable greenhouse, compare the actual test data of leafy vegetables in the early growth stage with the model data.

[0138] Analyze the possible impact of data differences on crop growth. For example, soil moisture lower than the ideal value of the model may affect the growth rate of crops, and differences in nutrient content may cause changes in leaf color.

[0139] Parameter Tuning Decisions

[0140] According to the comparative analysis results, if the difference is large and continues to occur, it indicates that the model may need to be optimized. For example, in a corn plantation, if the soil nitrogen content is continuously detected to be lower than the optimal value of the corn seedling stage in the model, and the corn grows slowly, it is necessary to consider adjusting the parameters of the model regarding the nitrogen demand of the corn seedling stage.

[0141] Consider the actual growth performance of crops to determine the direction and extent of adjustment. If crops are only slightly affected, it may only be necessary to make small adjustments to the model parameters; if crop growth is seriously hindered, it may be necessary to adjust the parameters to a greater extent. For example, the yellowing of leaves of leafy vegetables in a greenhouse may be due to a lack of certain nutrients. The adjustment range of the corresponding nutrient requirement parameters should be determined based on the growth performance such as the degree of yellowing.

[0142] Model parameter update

[0143] Use appropriate algorithms (such as machine learning algorithms such as gradient descent algorithms) to update model parameters. According to the error between the actual data and the model prediction data, adjust the parameters such as water and nutrient requirements in the crop growth model. For example, in a corn plantation, if the actual water demand is found to deviate from the model prediction, the algorithm is used to update parameters such as the water absorption coefficient of corn at different growth stages.

[0144] Continuous Optimization

[0145] The processor module repeats the above process continuously, uses the newly collected data to conduct comparative analysis again, and continuously optimizes the model parameters, so that the system can more accurately adapt to the growth needs of crops and improve the accuracy and effectiveness of the automatic spraying and fertilization detection management system for crops. At the same time, the data stored in the data storage module provides historical data support for subsequent comparative analysis and parameter optimization, which facilitates the system to conduct long-term adaptive learning and improvement.

[0146] in:

[0147] Least squares method to optimize linear regression model (taking the relationship between crop yield and fertilizer application as an example)

[0148] Establish the initial model: Assume that there is a linear relationship between crop yield and fertilizer application amount y=l0+l1χ+∈, where l0 is the intercept, l1 is the slope, and ∈ is the error term.

[0149] Collect data: Get a series of fertilizer application amounts X through experiments or actual measurements iand the corresponding crop yield y i data points.

[0150] Calculate the objective function: The goal is to minimize the sum of squared errors

[0151] Find the partial derivative and set it to 0: Find the partial derivative for l0 and l1 respectively and

[0152] Solving parameters: Solve the above equations to get the optimal estimated values ​​of l0 and l1, thereby optimizing the model. In practical applications, multiple linear regression may be involved (considering the impact of multiple factors such as fertilizer application, irrigation amount, etc. on crop yields), and the formula is as follows:

[0153] y=l0+l1χ1+l2χ2+……+l k χ k +∈

[0154] where χ1, χ2...χ k There are different influencing factors (such as fertilizer application amount, irrigation amount, temperature, etc.). The least squares method can also be used to solve the parameters through matrix operations to optimize the model.

[0155] Gradient descent algorithm optimization (taking crop growth prediction as an example)

[0156] Constructing a neural network model: Suppose a simple feedforward neural network is constructed to predict crop growth indicators (such as plant height). The network includes an input layer (such as input factors such as soil moisture and light intensity), a hidden layer, and an output layer (plant height).

[0157] Define the loss function: For example, use the mean square error loss function:

[0158]

[0159] where y yuce，i is the predicted plant height, y true,i is the actual measured plant height.

[0160] Calculate the gradient: For each parameter θ in the neural network (including weights and biases), calculate the gradient of the loss function L with respect to θ

[0161] And use the back-propagation algorithm to gradually calculate the gradient from the output layer to the input layer through the chain rule.

[0162] Update parameters: According to the gradient descent algorithm, according to the formula Update the parameters, where α is the learning rate, which determines the step size of the parameter update. By continuously iterating this process, the loss function L is gradually reduced, thereby optimizing the model. In the actual crop growth model optimization, it may be necessary to combine a more complex neural network architecture and more input factors to improve the accuracy of the model.

[0163] The present invention has the following technical effects:

[0164] 1. Accurately obtain soil plot information through the positioning module, without relying on specific cards or RFID electronic tags, reducing manual labor when planting on a large scale;

[0165] Specifically, in the rice field example, multiple sub-areas can be accurately divided, so that subsequent irrigation and fertilization operations can be more targeted. The detection module collects soil moisture, nutrients and other data of each sub-area in detail. Taking the tillering period of rice as an example, it is clearly known that the humidity is lower than the required value and the nitrogen content is slightly lower, thereby generating accurate irrigation and fertilization instructions. Excessive irrigation and fertilization can be avoided, and the waste of water resources and fertilizers can be reduced. According to statistics, in traditional agricultural irrigation methods, the water resource waste rate can reach 30% to 50% due to the inability to accurately control it. The use of this system can significantly reduce this waste rate, which may be controlled at around 10% to 20%.

[0166] In orchard management, in response to insufficient soil moisture and low calcium content in different areas during the fruit expansion period, the corresponding sprayers can be accurately turned on and appropriate parameters can be set for irrigation and fertilization, ensuring that each fruit tree can get just the right amount of water and nutrients, improving fertilizer utilization and reducing nutrient loss due to uneven fertilization.

[0167] 2. The present invention can meet the needs of crops at different growth stages:

[0168] The processor module is based on the built-in crop growth model database, covering the water and nutrient requirements of different crops at various growth stages. For example, rice in the tillering period and orchard fruit trees in the fruit expansion period can analyze data and generate accurate instructions based on the demand model of the corresponding stage. This allows irrigation and fertilization to closely fit the growth process of crops, promote the healthy growth of crops, and increase yield and quality. Taking corn planting as an example, under the traditional planting model, the yield may be affected to a certain extent because it is not possible to accurately apply fertilizers according to the needs of each growth stage. After adopting this system, the yield is expected to increase by 10% to 20% by accurately meeting the nutrient needs of different stages.

[0169] 3. Intelligent control and management

[0170] Automated operation saves manpower:

[0171] The spray control module and the fertilization control module can automatically control the operation of the sprayer according to the instructions generated by the processor module, without the need for manual irrigation and fertilization operations in each area. During the irrigation and fertilization process of the rice field, the spray control module can automatically irrigate each sub-area according to the planned zigzag path, and the fertilization control module can also automatically extract and allocate fertilizers and fertilize according to the planned path. This greatly saves labor costs. After a large farm adopts this system, the irrigation and fertilization work that originally required many people to spend several days to complete may only require a few people to monitor the system and occasionally fine-tune the parameters, and the manpower input can be reduced by 50% to 70%.

[0172] The same is true in orchard management. The first sprayer is automatically controlled to spray in a circular trajectory around the fruit trees, and the second sprayer focuses on fertilizing specific areas, realizing automated operations and improving work efficiency.

[0173] Adaptive learning optimization management:

[0174] The crop growth model database of the processor module has an adaptive learning function, which can optimize the model parameters according to the actual growth of crops. For example, if the actual growth is found to be different from the model prediction during a certain season of rice planting, the system can analyze the actual data collected and adjust the model parameters regarding the rice's demand for water, nutrients, etc. at this growth stage, making subsequent irrigation and fertilization instructions more accurate. This helps the system to continuously adapt to the growth characteristics of crops in different years and environments, and maintain good management results in the long term.

[0175] 4. Data Management and User Interaction

[0176] Convenient data storage and query:

[0177] The data storage module classifies, stores (by date, time, sensor type, sub-area, etc.), indexes, and compresses the various data collected. In rice field management, the date is used as the folder, and the files are named by sensor type and sub-area number to store data, which makes it easy to query the humidity, nutrients, and other data of a sub-area at a specific time. In orchard management, it is also easy to query the historical humidity and nutrient change data of the soil around each fruit tree. This facilitates subsequent analysis and decision-making, and farm managers can quickly obtain the required data for evaluation and adjustment of management strategies.

[0178] It has an automatic backup function and can set backup cycles to prevent data loss, ensuring the security and integrity of data and accumulating valuable data resources for long-term agricultural production management.

[0179] 5. User-friendly interactive experience:

[0180] The user interaction module displays system data in visual charts (such as line charts, bar charts, etc.), such as soil moisture changes, fertilizer application statistics, etc., so that users can intuitively understand the crop growth environment and management situation. For example, farm technicians can view the system status through the user interface and quickly find problems such as slightly slow rice growth in some sub-areas. They can also fine-tune the spraying and fertilization parameters through the user interface according to the actual growth performance of crops. Orchard managers can also view fruit tree growth data. If they find fruit cracking, they can check the calcium fertilization history data in time and adjust the fertilization plan.

[0181] It supports multi-user authority management, and users of different levels have different operating permissions, which can not only ensure the security of the system, but also meet the operation and management needs of different personnel, such as farm technicians, managers, owners, etc.

[0182] 6. Remote monitoring and information integration

[0183] Real-time remote monitoring convenience:

[0184] The network communication module transmits system data to the server in real time, and farm managers can remotely monitor the system through mobile phone APP or web page. In rice field management, farm managers can remotely suspend irrigation plans through the network communication module after receiving rainstorm warning information from the meteorological department. In orchard management, orchard owners can obtain the overall irrigation and fertilization situation report of the orchard through the web page remote monitoring system. This allows managers to keep abreast of the operation of crop growth and management systems in a timely manner no matter where they are, make decisions in a timely manner, and avoid losses caused by the inability to obtain information in a timely manner.

[0185] The encryption protocol is used to ensure the security of data transmission, ensuring that system data is not leaked or tampered with during transmission, thus protecting the privacy of the farm and the security of production data.

[0186] 7. Information integration improves scientific decision-making:

[0187] The network communication module can be connected to external data sources such as agricultural research institutions and meteorological departments to obtain the latest planting technology and weather forecast information for adjusting system parameters and plans. For example, orchard owners can obtain the latest fruit tree cultivation technology information pushed by agricultural research institutions through the network communication module and apply it to system management. Production management can combine external expertise and real-time information to make more scientific and reasonable decisions, further improving the yield and quality of crops.

[0188] The above description of the disclosed embodiments enables those skilled in the art to implement or use the embodiments. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the embodiments.

[0189] Therefore, the present embodiments will not be limited to those shown herein but will be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A detection and management system based on automatic spraying and fertilization of crops, characterized in that: include A positioning module (1), the positioning module (1) is used to obtain and mark the position of the corresponding soil block; and provide the soil block positioning data; A detection module (2), wherein the detection module (2) collects information of a soil block to be detected; A spray control module (3), the spray control module (3) receives data associated with the soil plot information to be detected collected by the detection module (2), and controls the switch value of the first sprayer, the travel path of the first sprayer, and the spraying time; A fertilization control module (4), the fertilization control module (4) receives data associated with the information of the soil plot to be detected collected by the detection module (2), and controls the switch value of the second sprayer, the travel path of the second sprayer, and the spraying time; A processor module (5) is responsible for coordinating the work between the above modules, receiving information from the positioning module (1) and the detection module (2), and sending the processed instructions to the spray control module (3) and the fertilization control module (4); The processor module (5) is internally provided with a crop growth model database and an optimization algorithm, wherein the optimization algorithm is a least squares method for optimizing a linear regression model or a gradient descent algorithm.

2. The system for detecting and managing automatic spraying and fertilization of crops according to claim 1 is characterized in that: It also includes a data storage module (6), the data storage module (6) is used to store the detection data of the detection module (2), the historical records of the spray control module (3) and the fertilization control module (4), the relevant data of the growth of the corresponding crop of the corresponding soil plot located by the positioning module (1), and the communication data between the processor module (5) and the above modules; The data storage module (6) is communicatively connected with the processor module (5), the detection module (2), the spray control module (3) and the fertilization control module (4).

3. The system for detecting and managing automatic spraying and fertilization of crops according to claim 1 is characterized in that: It also includes a user interaction module (7) and a network communication module (8), wherein the user interaction module (7) and the network communication module (8) are both communicatively connected to the processor module (5); The user interaction module (7) provides a user interface, allowing the user to input instructions, view system status and historical data, and adjust spraying and fertilization parameters; The network communication module (8) is responsible for exchanging data with external devices or networks to achieve remote monitoring and control functions.

4. The system for detecting and managing automatic spraying and fertilization of crops according to claim 3 is characterized in that: The positioning module (1) uses a combination of GPS or BDS and geographic information system GIS to obtain and mark soil plot location information.

5. The system for detecting and managing automatic spraying and fertilization of crops according to claim 3 is characterized in that: The detection module (2) comprises a soil moisture sensor based on the time domain reflectometry (TDR) principle, a soil nutrient sensor using ion selective electrode technology or near infrared spectrum analysis technology, and a sensor for detecting atmospheric temperature, humidity, wind speed, wind direction, and carbon dioxide concentration.

6. A detection and management method based on automatic spraying and fertilization of crops, characterized in that: A crop automatic spray fertilization detection and management system according to claim 4 or 5 comprises the following steps: S1, dividing the land into plots, using the positioning module (1) to obtain the location information of the soil plot and divide it into sub-areas; and setting the corresponding detection module (2) in the above sub-areas; S2, collecting corresponding soil and environmental data through the corresponding detection module (2), and the processor module (5) analyzing the data of the detection module according to the corresponding positioned crop growth model and generating spraying and fertilization control instructions; S3, the spray control module and the fertilization control module control the sprayer to move along a preset path and control the spraying time according to the instruction; S4, the data storage module stores and manages system data; S5, the user checks and adjusts system parameters through the user interaction module, and the network communication module realizes remote monitoring and data transmission.

7. A method for detecting and managing automatic spraying and fertilization of crops according to claim 6, characterized in that: In step S2, during data analysis and instruction generation, the crop growth model database of the processor module covers the demand patterns of different crops for water and nutrients at various growth stages, and has an adaptive learning function, which can optimize model parameters according to the actual growth conditions of crops.

8. The method for detecting and managing automatic spraying and fertilizing of crops according to claim 7 is characterized in that: The adaptive learning is to clean the collected data, remove outliers and erroneous data, and normalize and standardize the data. The processed data is compared with the ideal data of the corresponding crop growth stage in the crop growth model database. If there is a difference, the linear regression model or gradient descent algorithm is optimized by the least squares method, and the parameters of the model regarding the water and nutrient requirements of the crops are updated according to the error between the actual data and the model predicted data.

9. The method for detecting and managing automatic spraying and fertilization of crops according to claim 6, characterized in that: The user interaction module displays system data in visual charts and supports multi-user permission management. The network communication module uses encryption protocols for data transmission and can connect to external data sources to obtain information.

10. A method for detecting and managing automatic spraying and fertilization of crops according to any one of claims 6 to 9, characterized in that: The method is used in paddy fields, dry land, open-air orchards, vegetable / fruit greenhouses, tea gardens, or forage cultivation.

Images