Intelligent self-adaptive agricultural irrigation servo ball valve control system

Abstract

The invention provides an intelligent self-adaptive agricultural irrigation servo ball valve control system, which belongs to the technical field of irrigation control, and comprises a sensing layer, a control layer and an execution layer, the sensing layer is connected with the control layer, the control layer is connected with the execution layer, and the sensing layer comprises a soil parameter monitoring unit, a crop physiology monitoring unit and a space environment monitoring and prediction unit. The non-linear mapping relation between the light-temperature-humidity three-dimensional parameter space and the irrigation amount is established through the control layer, the water demand quantity of crops is accurately matched, meanwhile, the control precision of + / -2.5% of the irrigation amount is achieved, water data needed by plant growth are accurately analyzed by collecting the growth state, soil data and environment data of plants, and the water quality of the crops is improved. The water demand quantity control is more accurate, meanwhile, effect evaluation is carried out after irrigation, feedback data and timely adjustment opportunities are provided for later-stage control, and plant data of corresponding types can be set for learning to form a self-adaptive function of at least three types of crop growth models.

Description

Technical Field

[0001] The present invention relates to the technical field of irrigation control, and particularly to an intelligent adaptive agricultural irrigation servo ball valve control system. Background Art

[0002] Traditional agricultural irrigation methods are often inefficient, resulting in serious waste of water resources. With the increasingly severe global water shortage problem, how to use water resources efficiently has become one of the important challenges faced by modern agriculture. Although some existing automatic irrigation systems can alleviate this problem to a certain extent, their flexibility and accuracy still need to be improved. The single-piece, two-piece, and three-piece ball valves controlled by ordinary solenoid valves only detect soil humidity, with a single detection parameter, a large error in precision control, and a high energy consumption level. Therefore, it is necessary to design an intelligent adaptive agricultural irrigation servo ball valve control system to achieve higher-precision control. Summary of the Invention

[0003] The purpose of the present invention is to provide an intelligent adaptive agricultural irrigation servo ball valve control system to solve the technical problems of existing solenoid valve control that only detects soil humidity, has a single detection parameter, a large error in precision control, and a high energy consumption level.

[0004] Combined with sensor technology, PLC industrial control technology, and servo motor control technology, it realizes the precise regulation of the crop growth environment. Solve the problems of traditional irrigation systems relying on manual experience and lacking quantitative analysis of environmental parameters, overcome the problem of inaccurate irrigation caused by single environmental parameter control, reduce agricultural water waste (expected to save 30%-50% of water compared with traditional irrigation), and build a modular control system that can adapt to the growth needs of different crops.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is as follows:

[0006] An intelligent adaptive agricultural irrigation servo ball valve control system includes a perception layer, a control layer, and an execution layer. The perception layer is connected to the control layer, and the control layer is connected to the execution layer. The perception layer includes a soil parameter monitoring unit, a crop physiological monitoring unit, and a spatial environment monitoring and prediction unit. The soil parameter monitoring unit is used to detect the environmental data of the soil in real time and transmit it to the control layer. The crop physiological monitoring unit is used to detect the growth status data of the crops in real time and transmit it to the control layer. The spatial environment monitoring and prediction unit is used to detect the data of the spatial environment and the real-time weather forecast data in real time and transmit it to the control layer;

[0007] The execution layer includes an execution control unit and an actuator state perception unit. The execution control unit is used to control the servo ball valve in real time according to instructions and return the state data of the control. The control layer notifies the start of the irrigation effect evaluation according to the returned state. The actuator state perception unit is used to perceive the state and flow data of the servo ball valve in real time and transmit it to the control layer.

[0008] Furthermore, the soil parameter monitoring unit includes a soil moisture sensor module, a soil temperature sensor module, and a soil EC value sensor module. The soil moisture sensor module uses electromagnetic pulses along a waveguide rod. When high-frequency electromagnetic pulses encounter the interface of media with different dielectric constants, reflection will occur. By measuring the pulse propagation time and wave speed, and combining with the length of the waveguide rod, the volumetric water content of the soil can be calculated. The electromagnetic pulses are arranged in three layers along the waveguide rod, namely the surface layer of 0 - 10 cm, the middle layer of 10 - 30 cm, and the deep layer of 30 - 50 cm, to monitor the soil volumetric water content and water tension in real time. The soil temperature sensor module is used to track the temperature changes in the root active layer and determine the plant water evaporation rate according to different root active layers. The soil EC value sensor module is used to detect the soil conductivity and indirectly reflect the salt concentration to prevent salinization.

[0009] Furthermore, the crop physiological monitoring unit includes a leaf surface moisture sensor module, a stem diameter sensor module, and a multispectral camera health recognition module. The leaf surface moisture sensor module analyzes the degree of leaf water stress through infrared spectroscopy. Infrared light is emitted to irradiate the leaf sample, and the reflected or transmitted light signal is collected. The vibration absorption of different chemical bonds will produce absorption peaks at specific wavenumbers. The O - H stretching vibration related to water will have absorption in a specific region. Under normal water conditions, the infrared spectrum of the leaf has a specific characteristic peak pattern. When water stress occurs, water deficiency causes cell water loss. The stem diameter sensor module is used to continuously monitor the crop growth rate and reflect the water use efficiency. The multispectral camera health recognition module is used to remotely evaluate the crop health index. The health index includes the normalized difference vegetation index and the soil adjusted vegetation index. The normalized difference vegetation index is calculated by the ratio of the reflectance in the near-infrared band to the reflectance in the red band. The formula is: NDVI = (NIR - R) / (NIR + R), where NIR is the reflectance in the near-infrared band and R is the reflectance in the red band. The soil adjusted vegetation index accurately evaluates the vegetation condition.

[0010] Furthermore, the space environment monitoring and prediction unit includes a real-time weather forecast acquisition module, a rain gauge module, a solar radiation sensor module, an evaporation pan actual data detection module, a space temperature and humidity sensor module, and a wind speed sensor module. The real-time weather forecast acquisition module is used to obtain real-time weather forecast data of the corresponding area of the crops in real time. The rain gauge module is used to obtain real-time rainfall data. The solar radiation sensor module is used to detect the ultraviolet band, visible light band, and near-infrared band, detect the ultraviolet band of the solar radiation intensity, and detect the degree of harm to the crops. The visible light band is used to reflect the photosynthesis of the crops. Since plants have specific reflection characteristics in the near-infrared band, the near-infrared band is used to understand the vegetation health status and chlorophyll content. The evaporation pan actual data detection module is used to set water on the evaporation pan, and a weight sensor is set at the bottom of the evaporation pan to detect the evaporation rate of water in real-time experiments. The space temperature and humidity sensor module is used to detect the space temperature and humidity data of the crops. The wind speed sensor module is used to detect the wind speed in the crop area in real time, and the wind speed is then used in the later evaporation of the crops.

[0011] Furthermore, a data processing and control unit is provided in the control layer. The data processing and control unit includes a spatio-temporal compensation analysis module, a feature extraction module, an irrigation demand analysis module, and a control strategy module. The spatio-temporal compensation analysis module is used to fuse sensor data using Kalman filtering and correct temperature drift using time series analysis. Based on the previous data, a state model is used to predict the state data of the sensor at the next moment. Then, the residual processing is performed on the collected actual data and the predicted data. The process of correcting temperature drift is as follows: Temperature measurement data within a fixed period of time needs to be collected. Through time series analysis, the long-term trend in the data is identified. If the trend indicates the existence of temperature drift, according to the characteristics of the data, a state space model is selected to describe the dynamic changes of the data. The established model is used to detect the temperature drift and perform correction through model prediction to improve the measurement accuracy. The feature extraction module is used to calculate the crop evapotranspiration and generate the crop water stress index. The crop evapotranspiration ETc = ETo × Kc, where ETo is the reference crop evapotranspiration and Kc is the crop coefficient. The crop coefficient is the coefficient for adjusting the reference crop evapotranspiration to the actual crop evapotranspiration. By multiplying the reference crop evapotranspiration by the crop coefficient, the water consumption of the reference crop under ideal conditions is converted into the water consumption of the actual crop, which can more accurately estimate the actual water requirements of different crops at different growth stages. The crop water stress index CWSI = (Ts - Tair) / (Ts - Tdew), where Ts is the crop canopy temperature, Tair is the air temperature, and Tdew is the dew point temperature. The crop water stress index is used to analyze the relationship between the crop canopy temperature and the water status. When the crop has sufficient water, transpiration is normal and the canopy temperature is close to the air temperature. When the crop is water-deficient and stressed, transpiration weakens and the canopy temperature rises. The irrigation demand analysis module is used to calculate the irrigation demand index using weighted decision-making. The irrigation demand index = α · light intensity + β · temperature gradient + γ · humidity deviation, where α, β, and γ are coefficients related to the crop type. α is taken as 0.7, β is taken as 0.02, and γ is taken as 0.3. The control strategy module is used to establish the transfer function between the valve opening and the flow rate. The transfer function is Q = Kv · √(ΔP) · sin(θ / 2), where Kv is the flow coefficient, ΔP is the pressure difference, θ is the valve plate rotation angle, and √(ΔP) · sin(θ / 2) represents the square root of the product of (ΔP) and sin(θ / 2).

[0012] Further, the execution control unit includes a servo ball valve control module, a valve real-time positioning module, and an irrigation feedback notification module. The servo ball valve control module is used to control the rotation of the servo ball valve. The servo ball valve control module sets feedforward compensation, establishes a valve resistance model T = k·θ˙+c·θ based on historical torque data, and compensates for the frictional torque in advance, where k is the viscous friction coefficient, θ is the angle, c is the frictional torque, and θ˙ is the angular velocity. The valve real-time positioning module is used to real-time locate the specific position of each valve, and then the later irrigation effect can be real-time located and informed to the user. The irrigation feedback notification module is used to, after the servo ball valve finishes irrigating an area, inform the control layer of the completion message, and then the control layer starts the irrigation effect evaluation.

[0013] Further, the actuator state perception unit includes a servo ball valve state monitoring module, a flow meter module, and a water pressure sensor module. The servo ball valve state monitoring module is used to real-time detect the state data of the servo ball valve, specifically which position it is in. The flow meter module is used to real-time detect the flow data. The water pressure sensor module is used to detect the water pressure data of the water pipe.

[0014] Further, after the irrigation is completed, the control layer conducts an irrigation effect evaluation. After setting a fixed time, the soil data is collected, and through the feedback correction of the soil permeability, the evaluation of the irrigation effect needs to quantify the indicators of water use efficiency, soil moisture distribution uniformity, and crop yield water response: Water use efficiency = crop transpiration / irrigation volume. The soil moisture distribution uniformity measures the soil moisture at different depths through a sensor network and analyzes the uniformity of water infiltration. The crop yield water response is to establish a regression model between crop yield and cumulative irrigation volume.

[0015] The present invention has the following beneficial effects due to adopting the above technical solutions:

[0016] The present invention establishes a non-linear mapping relationship between the light-temperature-humidity three-dimensional parameter space and the irrigation volume through the control layer, accurately matches the water demand of crops, and at the same time realizes a control accuracy of ±2.5% for the irrigation volume. By collecting the growth state of plants, soil data, and environmental data, the water data required for plant growth is accurately analyzed, and the water demand control is more accurate. At the same time, the effect evaluation is carried out after irrigation, providing feedback data and timely adjustment opportunities for later control, and it is also possible to set corresponding types of plant data for learning to form at least three crop growth model self-adaptation functions. Description of the Drawings

[0017] Figure 1 is the schematic diagram of the system structure of the present invention;

[0018] Figure 2 is the block diagram of the sensing layer module of the present invention;

[0019] Figure 3It is the block diagram of the control layer module of the present invention;

[0020] Figure 4 It is the block diagram of the execution layer module of the present invention. Specific embodiments

[0021] To make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the following provides preferred embodiments with reference to the accompanying drawings to further elaborate on the present invention in detail. However, it should be noted that many details listed in the specification are only for enabling the reader to have a thorough understanding of one or more aspects of the present invention, and these aspects of the present invention can be implemented even without these specific details.

[0022] As Figure 1 shown, the intelligent adaptive agricultural irrigation servo ball valve control system includes a sensing layer, a control layer and an execution layer. The sensing layer is connected to the control layer, and the control layer is connected to the execution layer.

[0023] As Figure 2 shown, the sensing layer includes a soil parameter monitoring unit, a crop physiological monitoring unit, and a spatial environment monitoring and prediction unit. The soil parameter monitoring unit is used to detect the environmental data of the soil in real time and transmit it to the control layer. The crop physiological monitoring unit is used to detect the growth state data of the crops in real time and transmit it to the control layer. The spatial environment monitoring and prediction unit is used to detect the data of the spatial environment and the real-time weather forecast data in real time and transmit it to the control layer.

[0024] As Figure 4 shown, the execution layer includes an execution control unit and an actuator state sensing unit. The execution control unit is used to control the servo ball valve in real time according to the instruction and return the control status data. The control layer notifies the start of the irrigation effect evaluation according to the returned status. The actuator state sensing unit is used to sense the state and flow data of the servo ball valve in real time and transmit it to the control layer.

[0025] In the embodiment of the present invention, as Figure 2As shown in the figure, the soil parameter monitoring unit includes a soil moisture sensor module, a soil temperature sensor module, and a soil EC value sensor module. The soil moisture sensor module uses electromagnetic pulses along a waveguide rod. When a high-frequency electromagnetic pulse encounters a dielectric interface with different dielectric constants, it will be reflected. By measuring the pulse propagation time and wave velocity and combining with the length of the waveguide rod, the volumetric water content of the soil can be calculated. The electromagnetic pulses are arranged in three layers along the waveguide rod, namely the surface layer of 0 - 10 cm, the middle layer of 10 - 30 cm, and the deep layer of 30 - 50 cm, to monitor the volumetric water content rate and water tension of the soil in real time. The soil temperature sensor module is used to track the temperature changes in the root activity layer and determine the plant water evaporation rate according to different root activity layers. The soil EC value sensor module is used to detect the soil conductivity and indirectly reflect the salt concentration to prevent salinization. The temperature sensors are arranged using the hexagonal grid method, and the sensor spacing is ≤50 m to avoid placing the temperature sensors next to metal objects (radiation error < ±2°C).

[0026] In the embodiment of the present invention, as Figure 2 shown in the figure, the crop physiological monitoring unit includes a leaf surface moisture sensor module, a stem diameter sensor module, and a multi-spectral camera health identification module. The leaf surface moisture sensor module analyzes the degree of leaf water stress through infrared spectroscopy. Infrared spectroscopy emits infrared light to irradiate the leaf sample and collects the reflected or transmitted light signals. The vibration absorption of different chemical bonds will produce absorption peaks at specific wavenumbers, and the O - H stretching vibration related to water will have absorption in a specific region. Under normal water conditions, the infrared spectrum of the leaf has a specific characteristic peak pattern. When water stress occurs, water shortage causes the cells to lose water. The stem diameter sensor module is used to continuously monitor the crop growth rate and reflect the water use efficiency. The multi-spectral camera health identification module is used to remotely evaluate the crop health index, and the health index includes the normalized difference vegetation index and the soil adjusted vegetation index. The normalized difference vegetation index is calculated by the ratio of the reflectance in the near-infrared band to the reflectance in the red band, and the formula is: NDVI = (NIR - R) / (NIR + R), where NIR is the reflectance in the near-infrared band and R is the reflectance in the red band. The soil adjusted vegetation index accurately evaluates the vegetation condition.

[0027] In the embodiment of the present invention, as Figure 2As shown, the space environment monitoring and prediction unit includes a real-time weather forecast acquisition module, a rain gauge module, a solar radiation sensor module, an evaporation pan actual data detection module, a space temperature and humidity sensor module, and a wind speed sensor module. The real-time weather forecast acquisition module is used to obtain real-time weather forecast data of the corresponding area of the crops in real time. The rain gauge module is used to obtain real-time rainfall data. The solar radiation sensor module is used to detect the ultraviolet band, visible light band, and near-infrared band, detect the ultraviolet band of the solar radiation intensity, and detect the degree of harm to the crops. The visible light band is used to reflect the photosynthesis of the crops. Since plants have specific reflection characteristics in the near-infrared band, the near-infrared band is used to understand the vegetation health status and chlorophyll content. The evaporation pan actual data detection module is used to set water on the evaporation pan, and a weight sensor is set at the bottom of the evaporation pan to detect the evaporation rate of water in real-time experiments. The space temperature and humidity sensor module is used to detect the space temperature and humidity data of the crops. The wind speed sensor module is used to detect the wind speed of the crop area in real time, and then the wind speed is used in the later evaporation of the crops.

[0028] In the embodiment of the present invention, as Figure 3As shown in the figure, a data processing and control unit is provided in the control layer. The data processing and control unit includes a spatio-temporal compensation analysis module, a feature extraction module, an irrigation demand analysis module, and a control strategy module. The spatio-temporal compensation analysis module is used to fuse sensor data using Kalman filtering and correct temperature drift using time series analysis. Based on the previous data, a state model is used to predict the state data of the sensor at the next moment. Then, the residual processing is performed on the collected actual data and the predicted data. The process of correcting temperature drift is as follows: Temperature measurement data within a fixed period of time needs to be collected. Through time series analysis, the long-term trend in the data is identified. If the trend indicates the existence of temperature drift, according to the characteristics of the data, a state space model is selected to describe the dynamic changes of the data. The established model is used to detect the temperature drift and perform correction through model prediction to improve the measurement accuracy. The feature extraction module is used to calculate the crop evapotranspiration and generate the crop water stress index. The crop evapotranspiration ETc = ETo × Kc, where ETo is the reference crop evapotranspiration and Kc is the crop coefficient. The crop coefficient is the coefficient for adjusting the reference crop evapotranspiration to the actual crop evapotranspiration. By multiplying the reference crop evapotranspiration by the crop coefficient, the water consumption of the reference crop under ideal conditions is converted into the water consumption of the actual crop, enabling more accurate estimation of the actual water requirements of different crops at different growth stages. The crop water stress index CWSI = (Ts - Tair) / (Ts - Tdew), where Ts is the crop canopy temperature, Tair is the air temperature, and Tdew is the dew point temperature. The crop water stress index is used to analyze the relationship between the crop canopy temperature and the water status. When the crop has sufficient water, transpiration is normal and the canopy temperature is close to the air temperature. When the crop is water-deficient and stressed, transpiration weakens and the canopy temperature rises. The irrigation demand analysis module is used to calculate the irrigation demand index using weighted decision-making. The irrigation demand index = α · light intensity + β · temperature gradient + γ · humidity deviation, where α, β, and γ are coefficients related to the crop type. α is taken as 0.7, β is taken as 0.02, and γ is taken as 0.3. The control strategy module is used to establish the transfer function between the valve opening and the flow rate. The transfer function is Q = Kv · √(ΔP) · sin(θ / 2), where Kv is the flow coefficient, ΔP is the pressure difference, and θ is the valve plate rotation angle. √(ΔP) · sin(θ / 2) represents the square root of the product of (ΔP) and sin(θ / 2).

[0029] The data processing and control unit is also equipped with an AD / DA module and an HMI human-machine interface. The HMI human-machine interface can view the data in real time, which is more convenient.

[0030] In the embodiment of the present invention, as Figure 3As shown in the figure, the execution control unit includes a servo ball valve control module, a valve real-time positioning module, and an irrigation feedback notification module. The servo ball valve control module is used to control the rotation of the servo ball valve. The servo ball valve control module is set with feedforward compensation. A valve resistance model T = k·θ˙ + c·θ is established based on historical torque data to compensate for the frictional torque in advance, where k is the viscous friction coefficient, θ is the angle, c is the frictional torque, and θ˙ is the angular velocity. The valve real-time positioning module is used to real-time locate the specific position of each valve, and then the later irrigation effect can be real-time located and informed to the user. The irrigation feedback notification module is used to, when the servo ball valve finishes irrigating an area, inform the control layer of the completion message, and then the control layer starts the irrigation effect evaluation. The servo motor is equipped with an absolute encoder, and a two-piece ball valve is used with real-time flow feedback. Precise flow control is achieved through the 0.1° resolution of the servo motor. After collecting the data, data preprocessing, moving average filtering, and outlier removal are performed first. The motion control instruction is generated using the existing S-shaped acceleration and deceleration curve planning.

[0031] In the embodiment of the present invention, as Figure 4 shown, the actuator state perception unit includes a servo ball valve state monitoring module, a flowmeter module, and a water pressure sensor module. The servo ball valve state monitoring module is used to real-time detect the state data of the servo ball valve, specifically which position it is in. The flowmeter module is used to real-time detect the flow data. The water pressure sensor module is used to detect the water pressure data of the water pipe. Valve real-time positioning, full closed-loop feedback control. The valve double eccentric structure and servo motor torque fluctuation monitoring are adopted.

[0032] In the embodiment of the present invention, after the irrigation is completed, the control layer conducts the irrigation effect evaluation. After setting a fixed time, the soil data is collected, and through the feedback correction of the soil permeability, the indicators for evaluating the irrigation effect need to quantify the water use efficiency, the uniformity of soil moisture distribution, and the crop yield water response: Water use efficiency = crop transpiration amount / irrigation amount. The uniformity of soil moisture distribution is measured by a sensor network to measure the soil moisture at different depths and analyze the uniformity of water infiltration. The crop yield water response is to establish a regression model between the crop yield and the cumulative irrigation amount.

[0033] This system realizes precise regulation: achieves a control accuracy of ±2.5% for the irrigation amount; energy-saving characteristics: standby power consumption < 5W, saving about 68% energy compared with the traditional solenoid valve system; reliable guarantee: IP67 protection level, adapting to the complex agricultural environment; intelligent learning: has the self-adaptation function of 3 crop growth models; convenient maintenance: supports OTA remote firmware upgrade.

[0034] Matters not covered by the present invention are well-known technologies.

[0035] The above are only the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. The intelligent adaptive agricultural irrigation servo ball valve control system includes a sensing layer, a control layer, and an execution layer. The sensing layer is connected to the control layer, and the control layer is connected to the execution layer. It is characterized in that: The perception layer includes a soil parameter monitoring unit, a crop physiological monitoring unit, and a spatial environment monitoring and prediction unit. The soil parameter monitoring unit is used to detect the environmental data of the soil in real time and transmit it to the control layer. The crop physiological monitoring unit is used to detect the growth status data of the crops in real time and transmit it to the control layer. The spatial environment monitoring and prediction unit is used to detect the data of the spatial environment and the real-time weather forecast data in real time and transmit it to the control layer; The execution layer includes an execution control unit and an actuator status perception unit. The execution control unit is used to control the servo ball valve in real time according to the instruction and return the status data of the control. The control layer notifies the start of the irrigation effect evaluation according to the returned status. The actuator status perception unit is used to perceive the status and flow data of the servo ball valve in real time and transmit it to the control layer.

2. The intelligent adaptive agricultural irrigation servo ball valve control system according to claim 1, characterized in that: The soil parameter monitoring unit includes a soil moisture sensor module, a soil temperature sensor module, and a soil EC value sensor module. The soil moisture sensor module uses electromagnetic pulses along the waveguide rod. When the high-frequency electromagnetic pulse encounters the dielectric interface with different dielectric constants, it will be reflected. By measuring the pulse propagation time and wave velocity and combining the length of the waveguide rod, the volumetric water content of the soil can be calculated. The electromagnetic pulse is arranged in three layers along the waveguide rod, namely the surface layer of 0-10 cm, the middle layer of 10-30 cm, and the deep layer of 30-50 cm, to monitor the soil volumetric water content and water tension in real time. The soil temperature sensor module is used to track the temperature change of the root activity layer and determine the plant water evaporation rate according to different root activity layers. The soil EC value sensor module is used to detect the soil conductivity and indirectly reflect the salt concentration to prevent salinization.

3. The intelligent adaptive agricultural irrigation servo ball valve control system according to claim 1, wherein: The crop physiological monitoring unit includes a leaf surface moisture sensor module, a stem diameter sensor module, and a multispectral camera health identification module. The leaf surface moisture sensor module analyzes the degree of leaf water stress through infrared spectroscopy. The infrared spectroscopy emits infrared light to irradiate the leaf sample and collects the reflected or transmitted light signal. The vibration absorption of different chemical bonds will produce absorption peaks at specific wavenumbers. The O-H stretching vibration related to water will have absorption in a specific region. Under normal water conditions, the infrared spectrum of the leaf has a specific characteristic peak pattern. When water stress occurs, water shortage causes cell water loss. The stem diameter sensor module is used to continuously monitor the crop growth rate and reflect the water use efficiency. The multispectral camera health identification module is used to remotely evaluate the crop health index. The health index includes the normalized difference vegetation index and the soil-adjusted vegetation index. The normalized difference vegetation index is calculated by the ratio of the reflectance of the near-infrared band to the red band. The formula is: NDVI=(NIR - R) / (NIR + R), where NIR is the reflectance of the near-infrared band and R is the reflectance of the red band. The soil-adjusted vegetation index accurately evaluates the vegetation condition.

4. The intelligent adaptive agricultural irrigation servo ball valve control system according to claim 1, wherein: The space environment monitoring and prediction unit includes a real-time weather forecast acquisition module, a rain gauge module, a solar radiation sensor module, an actual data detection module for evaporation pans, a space temperature and humidity sensor module, and a wind speed sensor module. The real-time weather forecast acquisition module is used to obtain real-time weather forecast data for the corresponding areas of crops in real time. The rain gauge module is used to obtain real-time rainfall data. The solar radiation sensor module is used to detect the ultraviolet band, visible light band, and near-infrared band, detect the ultraviolet band of solar radiation intensity, and detect the degree of harm to crops. The visible light band is used to reflect the photosynthesis of crops. Since plants have specific reflection characteristics in the near-infrared band, the near-infrared band is used to understand the vegetation health status and chlorophyll content. The actual data detection module for evaporation pans is used to set water on the evaporation pan, and a weight sensor is set at the bottom of the evaporation pan to detect the evaporation rate of water in real-time experiments. The space temperature and humidity sensor module is used to detect the space temperature and humidity data of crops. The wind speed sensor module is used to detect the wind speed in the crop area in real time, and the wind speed is then used in the later evaporation of crops.

5. The intelligent adaptive agricultural irrigation servo ball valve control system according to claim 1, wherein: There is a data processing control unit in the control layer. The data processing control unit includes a spatio-temporal compensation analysis module, a feature extraction module, an irrigation demand analysis module, and a control strategy module. The spatio-temporal compensation analysis module is used to fuse sensor data using Kalman filtering and correct temperature drift using time series analysis. Based on the previous data, a state model is used to predict the state data of the sensor at the next moment. Then, the residual processing is performed on the collected actual data and the predicted data. The process of correcting temperature drift is as follows: It is necessary to collect temperature measurement data within a fixed period of time. Through time series analysis, the long-term trend in the data is identified. If the trend indicates the existence of temperature drift, according to the characteristics of the data, a state space model is selected to describe the dynamic changes of the data. The established model is used to detect the temperature drift and perform correction through model prediction to improve the measurement accuracy. The feature extraction module is used to calculate the combined evapotranspiration and generate the crop water stress index. The combined evapotranspiration ETc = ETo × Kc, where ETo is the reference crop evapotranspiration and Kc is the crop coefficient. The crop coefficient is the coefficient for adjusting the reference crop evapotranspiration to the actual crop evapotranspiration. By multiplying the reference crop evapotranspiration by the crop coefficient, the water consumption of the reference crop under ideal conditions is converted into the water consumption of the actual crop, which can more accurately estimate the actual water requirements of different crops at different growth stages. The crop water stress index CWSI = (Ts - Tair) / (Ts - Tdew), where Ts is the crop canopy temperature, Tair is the air temperature, and Tdew is the dew point temperature. The crop water stress index is used to analyze the relationship between the crop canopy temperature and the water status. When the crop has sufficient water, transpiration is normal and the canopy temperature is close to the air temperature. When the crop is water-deficient and stressed, transpiration weakens and the canopy temperature rises. The irrigation demand analysis module is used to calculate the irrigation demand index using weighted decision-making. The irrigation demand index = α · light intensity + β · temperature gradient + γ · humidity deviation, where α, β, and γ are coefficients related to the crop type. α is taken as 0.7, β is taken as 0.02, and γ is taken as 0.

3. The control strategy module is used to establish the transfer function between the valve opening and the flow rate. The transfer function is Q = Kv · √(ΔP) · sin(θ / 2), where Kv is the flow coefficient, ΔP is the pressure difference, θ is the valve plate rotation angle, and √(ΔP) · sin(θ / 2) represents the square root of the product of (ΔP) and sin(θ / 2).

6. The intelligent adaptive agricultural irrigation servo ball valve control system according to claim 1, wherein: The execution control unit includes a servo ball valve control module, a valve real-time positioning module, and an irrigation feedback notification module. The servo ball valve control module is used to control the rotation of the servo ball valve. The servo ball valve control module sets feedforward compensation and establishes a valve resistance model T = k·θ˙ + c·θ based on historical torque data to compensate for the frictional torque in advance, where k is the viscous friction coefficient, θ is the angle, c is the frictional torque, and θ˙ is the angular velocity. The valve real-time positioning module is used to real-time position the specific location of each valve, and then the later irrigation effect can be real-time positioned and notified to the user. The irrigation feedback notification module is used to notify the control layer of the completion message when the servo ball valve finishes irrigating an area, and then the control layer starts the irrigation effect evaluation.

7. The intelligent adaptive agricultural irrigation servo ball valve control system according to claim 1, characterized in that: The actuator state perception unit includes a servo ball valve state monitoring module, a flow meter module, and a water pressure sensor module. The servo ball valve state monitoring module is used to real-time detect the state data of the servo ball valve, specifically which position it is in. The flow meter module is used to real-time detect the flow data. The water pressure sensor module is used to detect the water pressure data of the water pipe.

8. The intelligent adaptive agricultural irrigation servo ball valve control system according to claim 1, characterized in that: After irrigation is completed, the control layer conducts an irrigation effect evaluation. After setting a fixed time, soil data is collected, and through feedback correction of soil permeability, the indicators for evaluating the irrigation effect need to quantify the water use efficiency, the uniformity of soil moisture distribution, and the water response of crop yield: Water use efficiency = crop transpiration / irrigation volume. The uniformity of soil moisture distribution measures the soil moisture at different depths through a sensor network and analyzes the uniformity of water infiltration. The water response of crop yield is to establish a regression model between crop yield and cumulative irrigation volume.

Images