Corn and wheat water and fertilizer self-adaptive control method and system

Abstract

The invention discloses a corn and wheat water and fertilizer adaptive control method and system, and relates to the technical field of water and fertilizer control. S2, disease monitoring and diagnosis; s3, nutrient demand analysis; s4, adjusting the irrigation amount; and S5, growth data feedback. According to the invention, through disease monitoring and diagnosis, whether the crops in the planting area have diseases and the types and severity of the diseases can be found in time, through nutrient demand analysis, the crop nutrient demands of the disease area and the non-disease area can be obtained respectively, and according to the disease occurrence condition and the nutrient demands of the crops, the crop quality is improved. Real-time partition accurate regulation and control are achieved, more accurate self-adaptive water and fertilizer irrigation amount regulation is achieved, a suitable growth environment is provided for crops, the influence of diseases on crop growth is relieved, recovery and growth of the crops are guaranteed, and therefore the yield and quality of the crops are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of water and fertilizer control, and in particular to a method and system for adaptive water and fertilizer control of corn and wheat. Background Art

[0002] Crop water and fertilizer irrigation is a key measure in agricultural production to provide crops with the water and nutrients they need for growth. It aims to meet the growth and development needs of crops, increase crop yield and quality, and promote sustainable agricultural development.

[0003] For example, Chinese patent CN119087862A discloses an IoT-based water and fertilizer control method, which includes: obtaining crop area size and crop distribution information, deploying soil water and fertilizer concentration sensors, and collecting soil water and fertilizer concentration data; calculating and predicting the distribution of water and fertilizer concentration in the crop area; collecting crop images, extracting crop characteristic parameters and evaluating crop health status; and constructing an intelligent water and fertilizer irrigation regulation strategy to regulate and control the water and fertilizer irrigation amount.

[0004] In the above patent, although the problem of difficulty in achieving uniformity and accuracy in water and fertilizer irrigation is solved by detecting and evaluating the health status of different crops, when crops are diseased, different control measures need to be adopted for the diseases. The control measures will change the crops' demand for water and fertilizer. If water and fertilizer irrigation cannot be adjusted according to the characteristics of the pesticides and soil changes, the subsequent recovery and growth of crops will be affected. Summary of the Invention

[0005] The purpose of the present invention is to provide a method and system for adaptive water and fertilizer control of corn and wheat to solve the problem raised in the above background technology that when diseases occur in crops, different control measures need to be adopted for the diseases. The control measures will change the crops' demand for water and fertilizer. If water and fertilizer irrigation cannot be adjusted according to the characteristics of the pesticides and soil changes, the subsequent recovery and growth of the crops will be affected.

[0006] To achieve the above object, the present invention provides the following technical solution: a method and system for adaptive water and fertilizer control of corn and wheat, comprising the following steps:

[0007] S1. Data acquisition: Real-time collection of corn and wheat image information, soil moisture, nutrient data, and meteorological data through image acquisition equipment, soil sensors, and weather stations;

[0008] S2. Disease monitoring and diagnosis: Setting up detection points within the corn and wheat planting areas, and identifying and analyzing the data collected at the detection points;

[0009] S3, nutrient demand analysis: Divide the entire planting area, mark the diseased areas, and combine the data from S1 and S2 to analyze the nutrient requirements of the diseased and non-disease areas respectively;

[0010] S4. Irrigation amount adjustment: Establish a disease-water and fertilizer relationship model and an adaptive water and fertilizer regulation model to adjust the water and fertilizer irrigation amounts in the disease area and non-disease area in real time;

[0011] S5. Growth data feedback: Regularly collect the plant morphology data, physiological index data and soil data of the crops, analyze the collected growth data, and feed back the analysis results to the adaptive control system. The system automatically adjusts the fertilization strategy according to the feedback information.

[0012] Preferably, in S1, images of the leaves and stems of corn and wheat are taken by an image acquisition device, and the humidity and nutrient content data of the soil are collected in real time by a soil sensor.

[0013] Preferably, in S2, image recognition technology and machine learning algorithms are used to analyze the collected crop images, identify whether there are diseases and the types and severities of the diseases, and comprehensively judge the causes of the diseases in combination with the soil sensor data and meteorological data.

[0014] Preferably, in S4, when establishing the disease-water and fertilizer relationship model, collect disease data, water and fertilizer data and environmental data, sort out and preprocess the collected data, use methods such as correlation analysis to find out the potential relationships between diseases and water and fertilizer factors as well as environmental factors, and construct a model according to the analysis results. The relevant calculation expressions are as follows:

[0015] ;

[0016] In the formula, y is the dependent variable of the disease severity, x1 is the irrigation amount, x2 is the fertilization amount, is the regression coefficient, is the error term.

[0017] Preferably, the relevant expression of the adaptive water and fertilizer regulation model is as follows:

[0018] ;

[0019] In the formula, I is the irrigation amount, k1 is the adjustment coefficient of the irrigation amount, ET d is the evapotranspiration of the crops, P is the precipitation, SW is the set target soil water content, F is the fertilization amount, k2 is the adjustment coefficient of the fertilization amount, U d is the nutrient absorption amount, M is the mineralization amount of organic fertilizer, N f is the biological nitrogen fixation amount, and N is the set target nitrogen content of the soil.

[0020] Preferably, in S4, when adjusting the water and fertilizer irrigation amounts in real time, the following contents are also included:

[0021] S41. Real-time data collection and transmission: Use sensors installed in the field to collect data on the growth environment and disease status of crops in real time, and transmit the data to the central control system through a wireless communication network;

[0022] S42. Model calculation and decision-making: After receiving the real-time data, the central control system inputs it into the disease-water and fertilizer relationship model and the adaptive water and fertilizer adjustment model for calculation, and calculates the specific adjustment plans for water and fertilizer irrigation amounts for the disease-affected areas and non-disease areas;

[0023] S43. Irrigation equipment control: According to the decision-making results obtained from the model calculation, control the irrigation equipment and fertilization equipment to accurately adjust the water and fertilizer irrigation amounts for the disease-affected areas and non-disease areas;

[0024] S44. Dynamic detection and feedback adjustment: After implementing the water and fertilizer adjustment, continuously monitor the growth status of the crops and the development of diseases, and feed the new data back to the central control system.

[0025] Preferably, in S5, use data analysis methods and machine learning algorithms to analyze the collected growth data, conduct correlation analysis on the fertilization amount, fertilization time, fertilization type and crop growth indicators, and find out the quantitative relationship and change law.

[0026] A water and fertilizer adaptive control system for corn and wheat, including a data collection module, a disease identification unit, an adaptive adjustment unit and a feedback collection module;

[0027] The data collection module collects crop data in real time through image collection devices, soil sensors and weather stations, and transmits the collected data to the disease identification unit; the disease identification unit is used to identify whether there are diseases in the crops, diagnose the type and degree of the diseases, and mark the disease-affected areas; the adaptive adjustment unit combines the crop disease data in the disease identification unit and changes the irrigation amount of water and fertilizer through adaptive adjustment; the feedback collection module is used to receive the growth data of the crops and transmit the feedback information to the adaptive adjustment unit.

[0028] Preferably, the disease identification unit includes a data processing module, a diagnostic analysis module and a disease location module;

[0029] The data processing module analyzes and processes the collected data, and conveys the processed data to the diagnostic analysis module;

[0030] The diagnostic analysis module uses image recognition algorithms and disease diagnostic models to judge whether the crops have diseases, the type and severity of the diseases, and analyzes the nutrient requirements of the crops according to the diagnostic results;

[0031] The disease location module locates and marks the diseased crops in the planting area after diagnosis.

[0032] Preferably, the adaptive adjustment unit includes a control decision module and a fertilization execution module;

[0033] The control decision module generates a control instruction according to the diagnosis result of the diagnosis and analysis module and sends it to the irrigation and fertilization equipment;

[0034] The fertilization execution module receives the instruction sent by the control decision module and performs zoned water and fertilizer irrigation on the crops.

[0035] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0036] 1. In the present invention, through disease monitoring and diagnosis, it is possible to timely detect whether there are diseases in the crops in the planting area, as well as the types and severity of the diseases. Through nutrient demand analysis, the nutrient demands of the crops in the disease area and the non-disease area can be obtained respectively. According to the disease occurrence situation and nutrient demands of the crops, real-time zoned precise regulation is carried out to achieve more precise adjustment of the adaptive water and fertilizer irrigation amount, provide a suitable growth environment for the crops, reduce the impact of diseases on the growth of the crops, ensure the recovery and growth of the crops, and thus improve the yield and quality of the crops;

[0037] 2. In the present invention, through the feedback of growth data, the growth data of the crops after adjusting the water and fertilizer irrigation amount can be obtained. Through the analysis of the growth data, the quantitative relationship and change law between the fertilization amount, fertilization time, fertilization type and the crop growth index can be found, the historical adjustment effect can be automatically learned, and the model parameters can be iteratively optimized, which is convenient for the system to automatically adjust the subsequent fertilization strategy according to the feedback information, realize closed-loop feedback optimization, and improve the long-term regulation accuracy. Description of the Drawings

[0038] Figure 1 It is a flowchart of a method for adaptive control of water and fertilizer for corn and wheat according to the present invention;

[0039] Figure 2 It is a system block diagram of a system for adaptive control of water and fertilizer for corn and wheat according to the present invention.

[0040] Legend: 1. Data acquisition module; 2. Disease identification unit; 21. Data processing module; 22. Diagnosis and analysis module; 23. Disease location module; 3. Adaptive adjustment unit; 31. Control decision module; 32. Fertilization execution module; 4. Feedback collection module. Detailed Embodiments

[0041] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0042] Embodiment 1: Refer to Figure 1 As shown, the core is to achieve precise water and fertilizer regulation in disease areas and non-disease areas through multi-source data collection, disease diagnosis, model calculation, and dynamic feedback. The specific technical principle is as follows:

[0043] I. Technical Solution

[0044] 1. Multi-source data collection (S1)

[0045] Collection Object

[0046] Image information: Images of parts such as the leaves and stems of corn and wheat are taken through an image acquisition device (such as a camera) for subsequent disease identification. The image acquisition uses a multi-spectral / hyperspectral camera, covering the visible light (400 - 700nm) and near-infrared (700 - 1000nm) bands to capture features such as leaf lesions and withering. An AI edge computing module (such as NVIDIA Jetson) is carried to preprocess the images (denoise and enhance contrast) in real time to reduce the amount of transmitted data.

[0047] Soil data: Soil sensors are used to collect data such as soil humidity and nutrient content (such as nitrogen, phosphorus, and potassium) in real time to reflect the soil water and fertilizer conditions. The soil sensors are deployed with TDR (Time Domain Reflectometry) soil moisture sensors (such as Decagon EC-5) with an accuracy of ±2% to monitor the humidity of the 0 - 30cm / 30 - 60cm soil layers in real time. An EC conductivity sensor (monitoring soil salinity), a pH sensor (accuracy ±0.1), and nutrient electrodes (N / P / K ion-selective electrodes with a resolution of 0.1ppm) are integrated.

[0048] Meteorological data: Environmental parameters such as temperature, humidity, light, and precipitation are obtained through a weather station to analyze the impact of the environment on crop diseases and water and fertilizer requirements. The parameters monitored by the weather station: air temperature (accuracy ±0.5°C), relative humidity (±2% RH), light intensity (photosynthetically active radiation PAR, μmol / m² / s), wind speed / direction (ultrasonic sensor), precipitation (tipping bucket rain gauge, resolution 0.1mm).

[0049] In the data transmission technology part, field sensors are connected to the central control system through LoRa wireless modules (transmission distance 1 - 5 km, low power consumption) or 4G DTUs (suitable for long distances), and encrypted transmission is carried out using the MQTT protocol to ensure data real-time performance (delay < 10 s).

[0050] Core function: Provide basic data support for disease diagnosis, nutrient analysis, and model calculation.

[0051] 2. Disease Monitoring and Diagnosis (S2)

[0052] Technical means

[0053] Image recognition and machine learning: Analyze crop images to identify disease types (such as corn leaf spot, wheat powdery mildew) and severity levels (mild, moderate, severe).

[0054] Multi - data fusion analysis: Combine soil sensor data (e.g., abnormal humidity may cause root rot) and meteorological data (e.g., high temperature and high humidity are prone to cause rust), and comprehensively judge the causes of diseases (such as water shortage, improper fertilization, environmental factors).

[0055] Output results: Mark the specific areas where diseases occur (localize to field plots), and record the disease types and severity levels.

[0056] 3. Nutrient Requirement Analysis (S3)

[0057] Regional division: Divide the planting area into disease areas and non - disease areas, and respectively evaluate the differences in nutrient requirements between the two.

[0058] Analysis basis

[0059] Disease areas: Consider the impact of diseases on the absorption ability of crops (e.g., leaf diseases reduce photosynthesis and nutrient requirements; root diseases affect water absorption and the irrigation amount needs to be adjusted).

[0060] Non - disease areas: Determine the conventional water and fertilizer requirements according to the crop growth stages (such as jointing stage, filling stage) and soil basic fertility.

[0061] 4. Irrigation Amount Adjustment (S4)

[0062] Core model construction

[0063] Disease - water and fertilizer relationship model

[0064] Data input: Collect historical disease data (types, severity levels), water and fertilizer data (irrigation amount, fertilization amount, fertilizer types), and environmental data (temperature, humidity).

[0065] Modeling method: Through correlation analysis, regression analysis, etc., establish the mathematical relationship between the disease severity (dependent variable y) and factors such as irrigation amount (x1) and fertilization amount (x2). The formula is:

[0066] ;

[0067] y is the dependent variable of disease severity, x1 is the irrigation amount, x2 is the fertilization amount, is the regression coefficient, is the error term, used to quantify the association between diseases and water-fertilizer.

[0068] Adaptive water-fertilizer adjustment model

[0069] Irrigation amount calculation:

[0070] ;

[0071] I is the irrigation amount, k1 is the adjustment coefficient of the irrigation amount, ET d is the evapotranspiration of crops, P is the precipitation, SW is the set target soil water content, which is dynamically adjusted according to crop water requirements and environmental factors.

[0072] Fertilization amount calculation:

[0073] ;

[0074] F is the fertilization amount, k2 is the adjustment coefficient of the fertilization amount, U d is the nutrient uptake amount, M is the mineralization amount of organic fertilizer, N f is the biological nitrogen fixation amount, N is the set target nitrogen content in the soil, combined with the impact of diseases on nutrient uptake and soil nutrient balance.

[0075] Real-time adjustment process

[0076] S41 Data transmission: Field sensors transmit real-time data to the central control system through wireless communication (such as 4G, LoRa).

[0077] S42 Model calculation: Input disease data and environmental data, and calculate the water-fertilizer adjustment plan for the diseased area and non-diseased area through the above model (such as reducing the irrigation amount by 10% - 20% in the diseased area and adjusting the nitrogen-potassium ratio).

[0078] S43 Equipment control: Remotely control irrigation equipment (drip irrigation, sprinkler valves) and fertilization equipment (fertilizer pumps, fertilizer tanks) to achieve precise irrigation in zones (such as reducing water volume and increasing potassium fertilizer in the diseased area; normal supply in the non-diseased area).

[0079] S44 Dynamic Feedback: Continuously monitor the changes in the growth and diseases of the adjusted crops. If the actual effect does not match the model prediction (such as the disease getting worse), automatically correct the model parameters (such as adjusting the coefficients k1 and k2).

[0080] 5. Growth Data Feedback (S5)

[0081] Data Collection: Regularly collect plant morphological data (plant height, leaf area, ear length), physiological indicators (chlorophyll content, transpiration rate), and soil data (nutrient residues, pH value).

[0082] Analysis and Feedback: Use machine learning algorithms (such as regression analysis, neural networks) to correlate the fertilizer application rate, fertilizer application time, fertilizer type with crop growth indicators (such as the growth rate of plant height), find the quantitative relationship (such as excessive nitrogen fertilizer causing excessive leaf growth), form a feedback signal, and drive the system to automatically optimize the subsequent fertilization strategy (such as reducing the proportion of nitrogen fertilizer).

[0083] II. System Principle

[0084] Core Principle

[0085] Zonal Precision Regulation: Distinguish the diseased and non-diseased areas through disease location. Calculate the water and fertilizer requirements for different areas according to the physiological state of the crops in different areas (such as the root absorption ability decreasing in the diseased area) and the soil environment (such as the humidity being relatively high in the diseased area), and avoid "one-size-fits-all" irrigation and fertilization.

[0086] Model-Driven Decision Making: Use a mathematical model to quantify the relationship between diseases and water and fertilizers, and dynamically adjust the strategy in combination with real-time environmental data (such as increasing the irrigation amount in the area with wheat powdery mildew during high temperature and drought to relieve drought stress), rather than relying on fixed experience.

[0087] Closed-Loop Feedback Optimization: Through growth data feedback, the system can automatically learn the historical adjustment effects (such as the disease being alleviated after increasing the potassium fertilizer once), iteratively optimize the model parameters (such as correcting the regression coefficient of the disease-water and fertilizer relationship model), and improve the long-term regulation accuracy.

[0088] Example 2: Refer to Figure 1 As shown: A method for adaptive control of water and fertilizer for corn and wheat includes the following steps:

[0089] Step 1. Data Collection: Real-time collect the image information, soil humidity, nutrient data, and meteorological data of corn and wheat through image acquisition devices, soil sensors, and weather stations. Take images of the leaves and stems of corn and wheat through the image acquisition device, and real-time collect the soil humidity and nutrient content data through the soil sensor.

[0090] Step 2: Disease Monitoring and Diagnosis: Set up detection points in the planting areas of corn and wheat, identify and analyze diseases for the data collected at the detection points. Use image recognition technology and machine learning algorithms to analyze the collected crop images, identify whether there are diseases, the types and severity of the diseases, and combine soil sensor data and meteorological data to comprehensively judge the causes of disease occurrence;

[0091] Step 3: Nutrient Requirement Analysis: Divide the entire planting area, mark the disease areas, and analyze the nutrient requirements of the disease areas and non-disease areas respectively by combining the data in Step 1 and Step 2;

[0092] Step 4: Irrigation Quantity Adjustment: Establish a disease-water and fertilizer relationship model and an adaptive water and fertilizer regulation model, and adjust the water and fertilizer irrigation quantities of the disease areas and non-disease areas in real time. When corn has leaf spot disease, since the photosynthesis of the leaves is affected, the nutrient requirement of the crops will decrease. At this time, the fertilization amount should be appropriately reduced; at the same time, to avoid excessive field humidity aggravating the disease, the irrigation amount also needs to be appropriately reduced. For wheat powdery mildew caused by drought, while preventing and controlling the disease, the irrigation amount needs to be increased to improve the growth environment of the crops;

[0093] When establishing the disease-water and fertilizer relationship model, collect disease data, water and fertilizer data, and environmental data, sort out and preprocess the collected data, use methods such as correlation analysis to find out the potential relationships between diseases and water and fertilizer factors as well as environmental factors, and construct a model according to the analysis results. The relevant calculation expressions are as follows:

[0094] ;

[0095] In the formula, y is the dependent variable of the disease severity, x1 is the irrigation amount, x2 is the fertilization amount, is the regression coefficient, is the error term;

[0096] The relevant expression of the adaptive water and fertilizer regulation model is as follows:

[0097] ;

[0098] In the formula, I is the irrigation amount, k1 is the regulation coefficient of the irrigation amount, ET d is the crop evapotranspiration, P is the precipitation, SW is the set target soil water content, F is the fertilization amount, k2 is the regulation coefficient of the fertilization amount, U d is the nutrient absorption amount, M is the mineralization amount of organic fertilizer, N f is the biological nitrogen fixation amount, and N is the set target nitrogen content of the soil.

[0099] When adjusting the water and fertilizer irrigation quantity in real time, it also includes the following content:

[0100] 41. Real-time data collection and transmission: Use soil moisture sensors, nutrient sensors, weather stations, and image acquisition devices installed in the field to collect data on the growth environment and disease status of crops in real time, and transmit the data to the central control system through a wireless communication network;

[0101] 42. Model calculation and decision-making: After receiving the real-time data, the central control system inputs it into the disease-water and fertilizer relationship model and the adaptive water and fertilizer regulation model for calculation. According to the disease-water and fertilizer relationship model, analyze the theoretical water and fertilizer requirements of crops under the current disease conditions. Then, combined with the adaptive water and fertilizer regulation model, comprehensively consider factors such as crop growth stage, soil conditions, and meteorological conditions, and calculate specific water and fertilizer irrigation amount adjustment plans for disease areas and non-disease areas;

[0102] 43. Irrigation equipment control: According to the decision results obtained from the model calculation, adjust the water and fertilizer irrigation amounts of disease areas and non-disease areas precisely by controlling the valves, water pumps of the drip irrigation system and sprinkler irrigation system of the irrigation equipment, and the fertilizer pumps, switches of fertilizer tanks, and flow controllers of the fertilization equipment. For disease areas, if the model determines that the irrigation amount and nitrogen fertilizer application amount need to be reduced and the potassium fertilizer application amount needs to be increased, then correspondingly control the irrigation valve to reduce the water output, and at the same time adjust the flow of the fertilizer pump to reduce the nitrogen fertilizer supply and increase the potassium fertilizer supply. For non-disease areas, also make appropriate water and fertilizer adjustments according to the suggestions of the model to meet the overall growth needs of crops;

[0103] 44. Dynamic detection and feedback adjustment: After implementing the water and fertilizer adjustment, continuously monitor the growth status of crops and the development of diseases, and feedback the new data to the central control system. If it is found that the actual situation does not match the model prediction, promptly correct and optimize the model, adjust the parameters or structure of the model, so that the model can more accurately reflect the actual needs of crops, thereby achieving more precise adaptive water and fertilizer regulation.

[0104] Step Five. Growth data feedback: Regularly collect the plant morphology data, physiological index data, and soil data of crops, analyze the collected growth data, and feedback the analysis results to the adaptive control system. The system automatically adjusts the fertilization strategy according to the feedback information, uses data analysis methods and machine learning algorithms to analyze the collected growth data, and conducts correlation analysis on the fertilization amount, fertilization time, fertilization type, and crop growth indicators to find out the quantitative relationship and change law.

[0105] Example 3: Refer to Figure 2 As shown: A water and fertilizer adaptive control system for corn and wheat includes a data collection module 1, a disease identification unit 2, an adaptive adjustment unit 3, and a feedback collection module 4;

[0106] The data acquisition module 1 collects crop data in real time through an image acquisition device, soil sensors, and a weather station, and transmits the collected data to the disease identification unit 2;

[0107] The disease identification unit 2 is used to identify whether there are diseases in the crops, diagnose the type and degree of the diseases, and mark the disease areas; the disease identification unit 2 includes a data processing module 21, a diagnostic analysis module 22, and a disease location module 23;

[0108] The data processing module 21 analyzes and processes the collected data, and conveys the processed data to the diagnostic analysis module 22;

[0109] For image data, an image filtering algorithm is used to remove noise and enhance the clarity and contrast of the images; image segmentation technology is adopted to separate the crops from the background. The soil and meteorological data are processed through data cleaning and denoising to remove outliers and incorrect data, and are standardized so that data from different sources are comparable.

[0110] The diagnostic analysis module 22 uses image recognition algorithms and disease diagnostic models to determine whether the crops have diseases and the type and severity of the diseases, and analyzes the nutrient requirements of the crops according to the diagnostic results;

[0111] Deep learning algorithms are used to analyze crop images. A convolutional neural network model is trained through a large number of labeled disease images so that it can accurately identify various common disease types, such as northern leaf blight of corn, wheat rust, etc., and evaluate the severity of the diseases. Combining soil moisture, nutrient data, and meteorological conditions, data mining algorithms and expert systems are used to analyze the causes of disease occurrence, considering factors such as the existing nutrient content in the soil, the nutrient absorption efficiency of the crops, and the fertilizer utilization rate, to accurately determine the fertilization amount.

[0112] The disease location module 23 accurately locates the diseased crops with the help of global positioning system (GPS) and geographic information system (GIS) technologies, and marks them on an electronic map. Through the positioning device and image acquisition system carried by the unmanned aerial vehicle, the distribution of diseases in a large-scale planting area can be quickly obtained, and the disease areas can be accurately divided.

[0113] The adaptive adjustment unit 3 combines the crop disease data in the disease identification unit 2 and adaptively adjusts the irrigation amount of water and fertilizer; the adaptive adjustment unit 3 includes a control decision module 31 and a fertilization execution module 32;

[0114] The control decision module 31 generates control instructions according to the diagnostic results of the diagnostic analysis module 22 and sends them to the irrigation and fertilization equipment;

[0115] The disease-water and fertilizer relationship model analyzes historical disease data, water and fertilizer management data, and environmental data to find the correlation rules between diseases and water and fertilizer. The adaptive water and fertilizer adjustment model dynamically adjusts the water and fertilizer irrigation amount according to the real-time collected data, such as soil humidity, meteorological conditions, and the growth status of crops;

[0116] The fertilization execution module 32 receives the instructions sent by the control decision-making module 31 and conducts zoned water and fertilizer irrigation for the crops.

[0117] The feedback collection module 4 is used to receive the growth data of the crops and transmit the feedback information to the adaptive adjustment unit 3.

[0118] The working principle of the present invention: First, image information, soil humidity, nutrient data, and meteorological data of crops (corn and wheat) are obtained through data collection. Disease diagnosis is performed on the crops based on the obtained data. According to the diagnosis results, the disease types and severity of the crops are obtained, and the diseased crops are located and marked. According to the marks, the diseased areas and non-diseased areas can be distinguished, realizing the division of the planting area. The nutrient requirements of the crops in different areas are analyzed, and the analysis results are combined with the disease-water and fertilizer relationship model and the adaptive water and fertilizer adjustment model to adjust the water and fertilizer irrigation amounts in different areas. After the stage irrigation is completed, the plant morphology data, physiological index data, and soil data of the crops are collected, the growth data of the crops are analyzed, and the analysis results are obtained. The analysis results are fed back to the adaptive control system, and the system automatically adjusts the subsequent fertilization strategy according to the feedback information. Through the analysis of a large amount of historical data, the disease diagnosis model, nutrient requirement analysis model, and water and fertilizer adjustment model are improved to improve the accuracy and reliability of the models. The entire solution can form a closed loop of "data collection - diagnosis - adjustment - feedback" to continuously optimize the system performance. As time goes by and data accumulates, the system continuously learns and optimizes its own performance. Through this closed-loop system, the precise monitoring and control of the growth process of corn and wheat are realized, personalized water and fertilizer management plans can be provided according to the actual conditions of different areas, the water and fertilizer utilization efficiency is improved, resource waste is reduced, timely and accurate disease diagnosis and targeted water and fertilizer adjustment help to reduce the impact of diseases on crops, promote the recovery and growth of crops, and thus improve the yield and quality of crops.

[0119] Although the present invention has been described in detail with reference to the foregoing embodiments, for those skilled in the art, they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for self-adaptive control of water and fertilizer for corn and wheat, characterized in that: It includes the following steps: S1. Data collection: Real-time collect the image information, soil humidity, nutrient data, and meteorological data of corn and wheat through image acquisition devices, soil sensors, and weather stations; S2. Disease monitoring and diagnosis: Set detection points in the planting areas of corn and wheat, and identify and analyze the diseases in the data collected at the detection points; S3. Nutrient demand analysis: Divide the entire planting area, mark the disease areas, and analyze the nutrient demands of the disease areas and non-disease areas respectively by combining the data in S1 and S2; S4. Irrigation amount adjustment: Establish a disease-water and fertilizer relationship model and an adaptive water and fertilizer adjustment model, and adjust the water and fertilizer irrigation amounts of the disease areas and non-disease areas in real time; S5. Growth data feedback: Regularly collect the plant morphology data, physiological index data, and soil data of crops, analyze the collected growth data, and feedback the analysis results to the adaptive control system. The system automatically adjusts the fertilization strategy according to the feedback information.

2. The corn and wheat water and fertilizer self-adaptive control method according to claim 1, characterized in that: In S1, use the image acquisition device to take images of the leaves and stems of corn and wheat, and use the soil sensor to collect the soil humidity and nutrient content data in real time.

3. The corn and wheat water and fertilizer self-adaptive control method according to claim 1, wherein: In S2, use image recognition technology and machine learning algorithms to analyze the collected crop images, identify whether there are diseases and the types and severity of the diseases, and comprehensively judge the causes of the diseases by combining the soil sensor data and meteorological data.

4. The corn and wheat water and fertilizer self-adaptive control method according to claim 1, characterized in that: In S4, when establishing the disease-water and fertilizer relationship model, collect the disease data, water and fertilizer data, and environmental data, sort out and preprocess the collected data, use methods such as correlation analysis to find the potential relationships between diseases and water and fertilizer factors and environmental factors, and construct a model according to the analysis results. The relevant calculation expressions are as follows: ； where y is the disease severity as the dependent variable, x1 is the irrigation amount, x2 is the fertilization amount, is the regression coefficient, is the error term.

5. The corn and wheat water and fertilizer self-adaptive control method according to claim 1, characterized in that: The relevant expressions of the adaptive water and fertilizer adjustment model are as follows: ； Where, I is the irrigation amount, k1 is the adjustment coefficient of the irrigation amount, ET d is the evapotranspiration of crops, P is the precipitation, SW is the set target soil water content, F is the fertilization amount, k2 is the adjustment coefficient of the fertilization amount, U d is the nutrient absorption amount, M is the mineralization amount of organic fertilizer, N f is the biological nitrogen fixation amount, and N is the set target nitrogen content of the soil.

6. The corn and wheat water and fertilizer self-adaptive control method according to claim 1, characterized in that: In S4, when adjusting the water and fertilizer irrigation amount in real time, it also includes the following content: S41. Real-time data collection and transmission: Use the sensors installed in the field to collect the data of the crop growth environment and disease conditions in real time, and transmit the data to the central control system through the wireless communication network; S42. Model calculation and decision-making: After receiving the real-time data, the central control system inputs it into the disease-water and fertilizer relationship model and the adaptive water and fertilizer adjustment model for calculation, and calculates the specific water and fertilizer irrigation amount adjustment plans for the disease areas and non-disease areas; S43. Irrigation equipment control: According to the decision-making results calculated by the model, adjust the water and fertilizer irrigation amounts of the disease areas and non-disease areas precisely by controlling the irrigation equipment and fertilization equipment; S44. Dynamic detection and feedback adjustment: After implementing the water and fertilizer adjustment, continuously monitor the growth conditions of the crops and the development of diseases, and feedback the new data to the central control system.

7. The corn and wheat water and fertilizer self-adaptive control method according to claim 1, wherein: In S5, use data analysis methods and machine learning algorithms to analyze the collected growth data, conduct correlation analysis on the fertilization amount, fertilization time, fertilization type, and crop growth indicators, and find the quantitative relationships and changing rules.

8. A corn and wheat water and fertilizer self-adaptive control system, characterized in that: A method for self - adapting control of water and fertilizer for corn and wheat as described in any one of claims 1 - 7 is used, which includes a data acquisition module (1), a disease identification unit (2), an adaptive adjustment unit (3), and a feedback collection module (4); The data acquisition module (1) collects crop data in real - time through image acquisition devices, soil sensors, and weather stations, and transmits the collected data to the disease identification unit (2); the disease identification unit (2) is used to identify whether there are diseases in the crops, diagnose the types and degrees of the diseases, and mark the disease areas; the adaptive adjustment unit (3) combines the crop disease data in the disease identification unit (2) and changes the irrigation amount of water and fertilizer through adaptive adjustment; the feedback collection module (4) is used to receive the growth data of the crops and transmit the feedback information to the adaptive adjustment unit (3).

9. The corn and wheat water and fertilizer self-adaptive control system according to claim 8, wherein: The disease identification unit (2) includes a data processing module (21), a diagnostic analysis module (22), and a disease localization module (23); The data processing module (21) analyzes and processes the collected data and conveys the processed data to the diagnostic analysis module (22); The diagnostic analysis module (22) uses image recognition algorithms and disease diagnosis models to determine whether the crops have diseases, the types and severities of the diseases, and analyzes the nutrient requirements of the crops according to the diagnostic results; The disease localization module (23) locates and marks the diseased crops in the planting area after diagnosis.

10. The corn and wheat water and fertilizer self-adaptive control system according to claim 8, wherein: The adaptive adjustment unit (3) includes a control decision - making module (31) and a fertilization execution module (32); The control decision - making module (31) generates control instructions according to the diagnostic results of the diagnostic analysis module (22) and sends them to the irrigation and fertilization equipment; The fertilization execution module (32) receives the instructions sent by the control decision - making module (31) and conducts zoned water and fertilizer irrigation for the crops.

Images