Adaptive intelligent monitoring and decision-making method of agricultural water spray sensor

Abstract

The invention relates to the technical field of intelligent agricultural irrigation, and discloses a self-adaptive intelligent monitoring and decision-making method for an agricultural water spray sensor, and the method comprises the steps: S1, carrying out the real-time collection and preprocessing of multi-source data; s2, obtaining the basic water demand of crops; s3, correcting in combination with environmental stress to obtain an actual water demand; s4, constructing a water spray decision model and dynamically optimizing the water spray decision model; s5, executing the final water spraying instruction and uploading feedback data; through the step S3 and the step S4, the limitation of traditional single judgment depending on soil humidity is broken through through collected multi-source data, the actual water demand is corrected, so that the real water demand of crops is quantified, meanwhile, a soil water stress coefficient and a meteorological correction factor are introduced, and the accuracy of the water demand is improved. The dynamic influence of environmental factors on water demand of crops is quantified, a water spray decision model is optimized, and a decision-execution-optimization closed-loop feedback mechanism is formed.

Description

Technical Field

[0001] This invention relates to the field of smart agricultural irrigation technology, and more specifically to an adaptive intelligent monitoring and decision-making method for agricultural spray sensors. Background Technology

[0002] With the development of agricultural modernization, precision irrigation technology has become the key to solving the contradiction between water waste and crop water demand. In existing technologies, agricultural sprinkler systems mainly rely on two modes: one is timed irrigation, which sets a fixed spraying cycle based on experience, but cannot adapt to sudden weather changes and changes in water demand at different growth stages of crops; the other is threshold-triggered irrigation, which monitors the soil moisture content at a single depth through soil moisture sensors, and starts spraying when it is lower than a fixed threshold until the upper threshold is reached.

[0003] However, existing technologies have some shortcomings: they do not consider the dynamic impact of environmental parameters on crop transpiration, relying solely on soil moisture can easily lead to "over-irrigation" or "under-irrigation", the threshold setting lacks crop specificity, the differences in water requirements between different crops and different growth stages of the same crop are not quantified, and there is a lack of adaptive adjustment mechanisms, making it impossible to optimize subsequent decisions based on historical irrigation effects and real-time environmental changes.

[0004] In view of this, the present invention proposes an adaptive intelligent monitoring and decision-making method for agricultural water spraying sensors, which dynamically senses crop needs, integrates multi-source environmental data, and performs autonomous optimization. Summary of the Invention

[0005] To overcome the aforementioned shortcomings of existing technologies, this invention provides an adaptive intelligent monitoring and decision-making method for agricultural spray sensors. By fusing multi-source environmental data, dynamically calculating crop water requirements, and optimizing adaptive models, it achieves accurate and efficient spray decision-making, solving the problems of water waste and inaccurate irrigation in traditional methods.

[0006] The present invention provides the following technical solution: an adaptive intelligent monitoring and decision-making method for agricultural spray sensors, comprising the following steps: Step S1, real-time acquisition and preprocessing of multi-source data: real-time acquisition of multi-source data through a deployed sensor network, and preprocessing thereof.

[0007] Step S2: Obtain the basic water requirement of crops: Obtain the reference crop evapotranspiration and then combine it with the crop coefficient to obtain the basic water requirement of crops.

[0008] Step S3: Correct the actual water demand by combining environmental stress: Combine the soil moisture stress coefficient and the meteorological correction factor to obtain the corrected actual water demand.

[0009] Step S4: Construct and dynamically optimize the water spraying decision model: Construct a water spraying decision model based on the corrected actual water demand, obtain the relationship between the target water spraying duration and the water spraying flow rate, and output the initial water spraying command if the corrected water shortage exceeds the warning threshold. Then, determine whether the initial water spraying command needs to be adjusted, and output the final water spraying command. At the same time, receive the feedback data to optimize the model parameters.

[0010] Step S5: Execute the final water spray command and upload feedback data: After executing the final water spray command, start the water spraying, obtain the feedback data after executing the final water spray command, upload the feedback data and send it back to step S4.

[0011] Preferably, the multi-source data includes soil parameter data, meteorological parameter data, and crop parameter data; the soil parameter data includes volumetric water content at soil depth, soil thermal energy, and electrical conductivity; the meteorological parameter data includes air temperature, relative humidity, light intensity, wind speed, and rainfall; and the crop parameter data includes crop canopy temperature and leaf area index; the canopy temperature is obtained by measuring with an infrared sensor, and the leaf area index is obtained by image recognition technology.

[0012] The preprocessing includes filtering the data and removing outliers, and unifying the sampling frequency through time synchronization; the filtering process uses Kalman filtering to remove high-frequency noise, and the outlier removal marks data that exceeds a reasonable range as invalid and removes them.

[0013] Preferably, the reference crop evapotranspiration is expressed by the formula: ;in, Represents reference crop evapotranspiration; This represents the slope of the saturated water vapor pressure curve; Indicates net radiation; Indicates soil heat flux; Represents the wet / dry constant; Indicates average temperature; express Wind speed at high altitudes; Indicates saturated water vapor pressure; The actual water vapor pressure is represented; the basic water requirement for crops is expressed as: ;in, Indicates the basic water requirement of crops; This represents the crop coefficient.

[0014] Preferably, the soil moisture stress coefficient is expressed by the formula: ;in, Indicates the soil moisture stress coefficient; This indicates the current average soil moisture content in the crop's root zone. Indicates the crop wilting coefficient. The field water holding capacity is represented; the corrected actual water requirement is expressed as: ;in, This indicates the corrected actual water demand; Indicates the weather correction factor. Indicates temperature. Indicates humidity.

[0015] Preferably, the water spraying decision model is expressed as: ;in, Indicates the duration of water spraying. This indicates the corrected water shortage. This indicates the density of water. This represents the water spray efficiency coefficient; The water flow rate is indicated; the corrected water shortage is expressed as: ;in, This indicates taking the maximum value between the first and second terms; This indicates the target value for the current soil moisture content in the crop's root zone; Indicates the decision-making cycle; Indicates the current root zone depth of the crop. This indicates the planting area per crop plant; the first item is... This indicates the current soil moisture deficit, that is, the amount of water that needs to be added to reduce the soil moisture content from [previous level]. Restore to The second item is... ; indicates the future Soil water storage corresponding to the crop's water requirement within a given time period.

[0016] Preferably, determining whether the initial water spraying command needs adjustment specifically involves: acquiring weather data; the weather data is future... Probability of rainfall within an hour.

[0017] If the weather data shows the future If the probability of rainfall within the hour is greater than or equal to a preset probability threshold, the initial water spraying command needs to be adjusted, and the adjusted initial water spraying command should be output as the final water spraying command; if the weather data indicates future... If the probability of rainfall within an hour is less than a preset probability threshold, then there is no need to adjust the initial water spraying command; the initial water spraying command is directly output as the final water spraying command. The adjustment of the initial water spraying command specifically includes: delaying the water spraying time point: delaying the water spraying time point until after the rainfall ends; reducing the water spraying duration: ;in, This indicates the new water spray duration, which is the water spray duration in the final water spray command; This indicates the duration of water spraying in the initial water spraying command.

[0018] Preferably, the process of receiving and transmitting feedback data to optimize model parameters specifically involves: obtaining feedback data after the final water spraying command is executed; optimizing the model parameters of the water spraying decision model using the feedback data before the next final water spraying command is output, thereby updating the final water spraying command, and then executing the new final water spraying command. Based on the crop variety and its corresponding growth stage, the expected growth effect of the crop is preset. The expected growth effect is then compared with the actual growth effect to obtain the error signal. The PID algorithm is used to adjust the model parameters to reduce the value of the error signal, i.e., to reduce the error; the model parameters are mainly crop coefficients. ;in, This represents the adjusted crop coefficient. This represents the crop coefficient before adjustment. This indicates the adjustment amount for the crop coefficient.

[0019] Preferably, the method for determining whether the corrected water shortage exceeds the warning threshold is as follows: if the corrected water shortage exceeds the warning threshold... If the threshold is exceeded, it is determined that the warning threshold has been exceeded; otherwise, it is determined that the warning threshold has not been exceeded. This is represented as the warning threshold.

[0020] Preferably, the feedback data includes crop response data and post-irrigation data. The soil condition data within one hour includes soil moisture, soil heat energy, and volumetric water content at soil depth; the crop response data includes crop growth indicators such as plant height growth rate, leaf water content, and leaf area.

[0021] The technical effects and advantages of this invention are as follows: By incorporating steps S3 and S4, this invention overcomes the limitations of traditional methods that rely solely on soil moisture for judgment by collecting multi-source data. It quantifies the actual water demand of crops by correcting for actual water requirements. Furthermore, it introduces soil moisture stress coefficients and meteorological correction factors to quantify the dynamic impact of environmental factors on crop water demand. The invention also optimizes the spraying decision model, forming a closed-loop feedback mechanism of decision-making, execution, and optimization. This enables continuous model adaptation, effectively improving the water-saving rate of the spraying system, avoiding over-irrigation and under-irrigation, and making it applicable to different growth stages of different crops. It can effectively increase crop yield, significantly reduce human intervention, and promote the development of smart agriculture. Attached Figure Description

[0022] Figure 1 This is a flowchart of the adaptive intelligent monitoring and decision-making method for agricultural water spraying sensors according to the present invention. Detailed Implementation

[0023] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. In addition, the forms of the various structures described in the following embodiments are merely illustrative. The adaptive intelligent monitoring and decision-making method of agricultural spray sensor involved in the present invention is not limited to the structures described in the following embodiments. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0024] like Figure 1 As shown, the present invention provides an adaptive intelligent monitoring and decision-making method for agricultural spray sensors, including the following steps: Step S1, real-time acquisition and preprocessing of multi-source data: multi-source data is acquired in real time through a deployed sensor network and preprocessed; the purpose is to avoid the limitations of judgment caused by single soil moisture by acquiring multi-source data and combining soil, meteorological and crop parameters.

[0025] Step S2: Obtain the basic water requirement of crops: Obtain the reference crop evapotranspiration and then combine it with the crop coefficient to obtain the basic water requirement of crops.

[0026] Step S3: Correct the actual water demand by combining environmental stress: Combine the soil moisture stress coefficient and the meteorological correction factor to obtain the corrected actual water demand.

[0027] Step S4: Construct and dynamically optimize the water spraying decision model: Construct a water spraying decision model based on the corrected actual water demand, obtain the relationship between the target water spraying duration and the water spraying flow rate, and output the initial water spraying command if the corrected water shortage exceeds the warning threshold. Then, determine whether the initial water spraying command needs to be adjusted, and output the final water spraying command. At the same time, receive the feedback data to optimize the model parameters.

[0028] Step S5: Execute the final water spray command and upload feedback data: After executing the final water spray command, start the water spraying, obtain the feedback data after executing the final water spray command, upload the feedback data and send it back to step S4.

[0029] In this embodiment, it should be specifically noted that the multi-source data includes soil parameter data, meteorological parameter data, and crop parameter data; the soil parameter data includes, but is not limited to, the volumetric water content at soil depth, soil thermal energy, and electrical conductivity, etc.; the meteorological parameter data includes, but is not limited to, air temperature, relative humidity, light intensity, wind speed, and rainfall, etc.; the crop parameter data includes, but is not limited to, crop canopy temperature and leaf area index, etc.; the canopy temperature can be obtained by measuring with an infrared sensor, and the leaf area index is obtained by image recognition technology.

[0030] The preprocessing includes, but is not limited to, filtering the data and removing outliers, and unifying the sampling frequency through time synchronization; the filtering can use Kalman filtering to remove high-frequency noise, and the outlier removal involves marking data that exceeds a reasonable range as invalid and removing it.

[0031] In this embodiment, it should be specifically noted that the reference crop evapotranspiration is expressed by the formula: ;in, This represents the reference crop evapotranspiration, reflecting the amount of water evaporation and transpiration under standard conditions. This represents the slope of the saturated water vapor pressure curve; Indicates net radiation; Indicates soil heat flux; Represents the wet / dry constant; Indicates average temperature; express Wind speed at high altitudes; Indicates saturated water vapor pressure; The actual water vapor pressure is represented; the basic water requirement for crops is expressed as: ;in, Indicates the basic water requirement of crops; This represents the crop coefficient, which is obtained by querying the corresponding table based on the crop type and growth stage. For example, the crop coefficient for the flowering stage of tomatoes is... The crop coefficient during the tomato fruiting period is The corresponding table can be a crop standard crop coefficient table recommended by the Food and Agriculture Organization of the United Nations, or a table dynamically updated in a local agricultural database.

[0032] In this embodiment, it should be specifically noted that the soil moisture stress coefficient is used to reflect the inhibitory effect of soil moisture deficit on crop transpiration, and the formula is expressed as: ;in, This represents the soil moisture stress coefficient, and its value range satisfies the following conditions: ; This indicates the current average soil moisture content in the crop's root zone. Indicates the crop wilting coefficient. The soil moisture stress coefficient reflects the degree of inhibition of crop transpiration rate by soil moisture deficit in the root zone, quantifying the inhibition of crop transpiration by soil water shortage and effectively correcting the actual water requirement. The crop wilting coefficient is the soil volumetric water content when the crop roots cannot absorb water from the soil, resulting in permanent wilting that cannot be reversed. It can be obtained by consulting the soil texture reference table provided by the local agricultural department or FAO. The field water holding capacity is the maximum amount of capillary suspended water in the soil. When the soil is saturated, excess gravitational water will seep into groundwater or drainage ditches, and the remaining water held by capillary force is the field water holding capacity. The field water holding capacity can be determined experimentally. The corrected actual water requirement is expressed as follows: ;in, This indicates the corrected actual water demand; Indicates the weather correction factor. Indicates temperature. Indicates humidity; the meteorological correction factor is used to correct for the short-term effects of extreme weather on crop transpiration; when or At this time, crop transpiration intensifies, and even if the soil is not short of water, irrigation needs to be increased. ;when and At this time, low temperature and high humidity slow down transpiration, so it is advisable to take [the sample]. In other cases, take No correction is required; the meteorological correction factor can compensate for short-term meteorological fluctuations that the soil moisture stress coefficient cannot cover.

[0033] In this embodiment, it should be specifically noted that the water spraying decision model is represented as follows: ;in, Indicates the duration of water spraying. This indicates the corrected water shortage. This indicates the density of water. This represents the water spray efficiency coefficient, which is selected in this embodiment. ; This represents the water flow rate; the spraying duration is adaptively adjusted based on the water flow rate, applicable to various water flow rate scenarios. When the water flow rate is adjusted, the spraying duration is adjusted accordingly, effectively ensuring irrigation results; the corrected water shortage is expressed as: ;in, This means taking the maximum value between the first and second terms to ensure that the current soil moisture deficit is compensated for, while also covering future soil moisture needs; This represents the target value for the current soil moisture content in the crop's root zone. In this embodiment, we select... ; The decision cycle is defined as the period during which crops are guaranteed to have sufficient water. For example, if crops are guaranteed to have sufficient water for the next 24 hours, then the decision cycle is 24 hours. Indicates the current root zone depth of the crop. This indicates the planting area per crop plant; the first item is... This indicates the current soil moisture deficit, that is, the amount of water that needs to be added to reduce the soil moisture content from [previous level]. Restore to The second item is... ; indicates the future The soil water storage capacity corresponding to the crop's water requirement within a certain time period; the execution of the final water spraying command means starting the water spraying by controlling the solenoid valve through a relay. After the water spraying is completed, the time point, duration, water flow rate, and feedback data of this irrigation are uploaded to the cloud platform for long-term model training and optimization; the content of the water spraying command includes the water spraying duration and water flow rate.

[0034] In this embodiment, it should be specifically explained that determining whether the initial water spraying command needs to be adjusted specifically involves: acquiring weather data; the weather data is future data. Probability of rainfall within an hour; if the weather data indicates future... If the probability of rainfall within the hour is greater than or equal to a preset probability threshold, the initial water spraying command needs to be adjusted, and the adjusted initial water spraying command should be output as the final water spraying command; if the weather data indicates future... If the probability of rainfall within an hour is less than a preset probability threshold, then there is no need to adjust the initial water spraying command; the initial water spraying command is directly output as the final water spraying command. The preset probability threshold ranges from greater than or equal to... Those skilled in the art can determine the appropriate values ​​based on the actual conditions of different crops; the adjustment of the initial water spraying command specifically includes: delaying the water spraying time point: delaying the water spraying time point until after the rainfall ends; reducing the water spraying duration: ;in, This indicates the new water spray duration, which is the water spray duration in the final water spray command; This indicates the duration of water spraying in the initial water spraying command; delaying water spraying time to avoid rainfall, reducing water spraying duration to avoid excessive soil moisture after rainfall; and utilizing weather forecasts to predict the weather and avoid "ineffective irrigation".

[0035] In this embodiment, it should be specifically explained that the optimization of model parameters by receiving the feedback data specifically involves: obtaining the feedback data after the final water spraying command is executed; the feedback data includes crop response data and post-irrigation data. The data includes, but is not limited to, soil moisture, soil heat energy, and volumetric water content at soil depth within an hour; crop response data includes, but is not limited to, crop growth indicators such as plant height growth rate, leaf water content, and leaf area; the crop response data is the data from the execution of the current final spraying command to the issuance of the next final spraying command. Before the next final spraying command is issued, the model parameters of the spraying decision model are optimized using feedback data to update the final spraying command, and the new final spraying command is then executed; based on the crop variety and corresponding growth stage, the expected crop growth effect is preset, and the expected crop growth effect is compared with the actual growth effect to obtain an error signal. The growth effect can be indicated by crop growth rate or plant height growth rate, and crop height can be detected using a plant height measuring instrument; the error signal value can be the difference between the actual growth effect and the expected growth effect. If the error signal value is negative, it indicates that the model underestimates the crop's water requirement, resulting in slow growth; the PID algorithm is used to adjust the model parameters to reduce the error signal value, i.e., reduce the error; the model parameters are mainly crop coefficients. ;in, This represents the adjusted crop coefficient. This represents the crop coefficient before adjustment. This indicates the adjustment amount of the crop coefficient; the crop coefficient can be updated in real time in the corresponding table after it is updated; the adjustment amount of the crop coefficient... It can be obtained through the PID algorithm.

[0036] In this embodiment, it should be specifically explained that the method for determining whether the corrected water shortage exceeds the warning threshold is as follows: if the corrected water shortage exceeds the warning threshold... If the threshold is exceeded, it is determined that the warning threshold has been exceeded; otherwise, it is determined that the warning threshold has not been exceeded. The threshold value is represented as the warning threshold and can be set by those skilled in the art according to actual conditions; this embodiment does not impose specific limitations on it. If the crop is severely affected by water shortage, the warning threshold value can be appropriately lowered; if the crop is less affected by water shortage, the warning threshold value can be appropriately increased. The adjustment amount of the crop coefficient... The formula obtained through the PID algorithm is expressed as: ;in, This represents the proportional term, which directly responds to the current error. The larger the value, the more drastic the adjustment. This represents the integral term, used to eliminate steady-state error, specifically targeting long-term accumulated deviations. This represents the differential term, used to suppress overshoot and prevent over-adjustment.

[0037] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

[0038] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. An adaptive intelligent monitoring and decision making method for agricultural water spraying sensors, characterized in that: The method comprises the following steps: step S1, real-time acquisition and preprocessing of multi-source data: real-time acquisition of multi-source data through a deployed sensor network, and preprocessing; step S2, obtaining the basic water requirement of crops: obtaining the reference crop evapotranspiration, and then obtaining the basic water requirement of crops in combination with the crop coefficient; step S3, obtaining the actual water requirement by combining environmental stress: obtaining the corrected actual water requirement in combination with the soil moisture stress coefficient and the meteorological correction factor; step S4, constructing a water spraying decision model and dynamically optimizing: constructing a water spraying decision model based on the corrected actual water requirement, obtaining the relationship between the target water spraying time and the water spraying flow, outputting the initial water spraying instruction if the corrected water shortage exceeds the warning threshold, then determining whether the initial water spraying instruction needs to be adjusted, thereby outputting the final water spraying instruction, and simultaneously receiving the feedback data to optimize the model parameters; step S5, executing the final water spraying instruction and uploading feedback data: starting water spraying after executing the final water spraying instruction, obtaining the feedback data after executing the final water spraying instruction, uploading the feedback data and simultaneously feeding back to step S4.

2. The adaptive intelligent monitoring and decision making method for agricultural sprinkler sensor according to claim 1, wherein: The multi-source data includes soil parameter data, meteorological parameter data and crop parameter data; the soil parameter data includes the volume water content of soil layer depth, soil thermal energy and electrical conductivity, the meteorological parameter data includes air temperature, relative humidity, light intensity, wind speed and rainfall, and the crop parameter data includes crop canopy temperature and leaf area index; the canopy temperature is measured by an infrared sensor, and the leaf area index is obtained by image recognition technology; the preprocessing includes filtering and removing outliers, and the sampling frequency is unified through time synchronization; the filtering adopts Kalman filtering to remove high-frequency noise, and the outliers are marked as invalid and removed if they exceed a reasonable range.

3. The adaptive intelligent monitoring and decision making method for agricultural sprinkler sensor according to claim 2, wherein: The reference crop evapotranspiration is expressed by a formula: ; wherein, represents the reference crop evapotranspiration; represents the slope of the saturation vapor pressure curve; represents the net radiation; represents the soil heat flux; represents the psychrometric constant; represents the average air temperature; represents the wind speed at a high level; represents the saturation vapor pressure; represents the actual vapor pressure; the crop basal water requirement is represented by: ; wherein, represents the crop basal water requirement; represents the crop coefficient.

4. The adaptive intelligent monitoring and decision making method for agricultural sprinkler sensor according to claim 3, wherein: The soil water stress coefficient is expressed by the formula: ; wherein, represents the soil water stress coefficient; represents the current average soil water content in the root zone of the crop, represents the wilting coefficient of the crop, represents the field water holding capacity; the corrected actual water requirement is expressed by: ; wherein, represents the corrected actual water requirement; represents the meteorological correction factor, represents the temperature, represents the humidity.

5. The adaptive intelligent monitoring and decision making method for agricultural sprinkler sensor according to claim 4, wherein: The water spraying decision model is represented as: ; wherein, represents the water spraying duration, represents the corrected water deficit, represents the density of water, represents the water spraying efficiency coefficient; represents the water spraying flow; the corrected water deficit is represented as: ; wherein, represents taking the maximum value in the first term and the second term; represents the current root zone soil moisture target value of the crop; represents the decision cycle; represents the current root zone depth of the crop, represents the planting area of a single crop; the first term is ; represents the current soil moisture deficit, i.e., the amount of water needed to restore the soil moisture from to ; the second term is ; represents the soil water storage corresponding to the crop water requirement in the future time.

6. The adaptive intelligent monitoring and decision making method of agricultural sprinkler sensor according to claim 5, wherein: The determination of whether the initial water spray command needs adjustment specifically involves: acquiring weather data; the weather data is future data. Probability of rainfall within an hour; if the weather data indicates future... If the probability of rainfall within the hour is greater than or equal to a preset probability threshold, the initial water spraying command needs to be adjusted, and the adjusted initial water spraying command should be output as the final water spraying command; if the weather data indicates future... If the probability of rainfall within an hour is less than a preset probability threshold, then there is no need to adjust the initial water spraying command; the initial water spraying command is directly output as the final water spraying command. The adjustment of the initial water spraying command specifically includes: delaying the water spraying time point: delaying the water spraying time point until after the rainfall ends; reducing the water spraying duration: ;in, This indicates the new water spray duration, which is the water spray duration in the final water spray command; This indicates the duration of water spraying in the initial water spraying command.

7. The adaptive intelligent monitoring and decision making method of agricultural sprinkler sensor according to claim 6, wherein: The receiving the feedback data of the return is used for optimizing the model parameters, specifically: obtaining feedback data after the final water spraying instruction is executed; before the next final water spraying instruction is output, the feedback data is used to optimize the model parameters of the water spraying decision model, so as to update the final water spraying instruction, and execute the new final water spraying instruction after the new final water spraying instruction is output; according to the crop variety and the corresponding growth stage, the expected growth effect of the crop is preset, the expected growth effect of the crop is compared with the actual growth effect, and an error signal is obtained ; the PID algorithm is used to adjust the model parameters to reduce the value of the error signal, that is, to reduce the error; the model parameters are mainly crop coefficients; ; wherein, represents the adjusted crop coefficient, represents the crop coefficient before adjustment, represents the adjustment amount of the crop coefficient.

8. The adaptive intelligent monitoring and decision making method of agricultural sprinkler sensor according to claim 7, wherein: The determination manner that the modified water shortage amount exceeds the early warning threshold is: if the modified water shortage amount exceeds the early warning threshold, it is determined that the early warning threshold is exceeded; otherwise, it is determined that the early warning threshold is not exceeded; the is represented as the early warning threshold.

9. The adaptive intelligent monitoring and decision making method of agricultural sprinkler sensor according to claim 8, wherein: The feedback data includes crop response data and soil state data within hours after irrigation The crop response data includes crop growth indicators such as plant height growth rate, leaf water content, and leaf area.

Images