Intelligent irrigation system based on oil shale reservoir stress regulation and control

Abstract

The invention discloses an intelligent irrigation system based on oil shale reservoir stress regulation and control, and relates to the technical field of intelligent irrigation, and the system comprises a data acquisition end, a stress analysis end and an irrigation decision end. According to the invention, the first irrigation unit uses an SVM classification model to decide the irrigation opportunity, accurately discriminates the critical state of vegetation water demand based on multi-source features, avoids the blindness of the traditional irrigation decision based on experience or a fixed period, and enables the irrigation start to adapt to the ecological water demand rhythm, and the second irrigation unit calculates the irrigation water amount through neural network regression. The water demand and multi-factor mapping are accurately quantified by utilizing the learning ability of the model for the complex nonlinear relationship, meanwhile, the water amount is dynamically adjusted by calculating the irrigation target value from the water-saving and ecological two-dimensional power generation, the water-saving coefficient and the ideal humidity are adjusted in combination with the stress change rate, and the water-saving effect is improved while vegetation growth is guaranteed through irrigation. The method is adaptive to the stress environment of the oil shale reservoir, and the balance of efficient utilization of water resources and ecological protection is realized.

Description

Technical Field

[0001] The present invention relates to the field of smart irrigation technology, and in particular to a smart irrigation system based on oil shale reservoir stress regulation. Background Art

[0002] As an important unconventional energy source, oil shale will cause changes in the reservoir stress field during its mining process, which in turn affects the surrounding geological environment and vegetation growth. Oil shale is usually buried at a depth of 300-700 meters, and the shallowest is 100 meters. The stress disturbance caused by mining activities will cause surface subsidence, soil moisture loss and other problems, seriously threatening the ecological environment of the mining area.

[0003] At present, the stress redistribution caused by oil shale mining will cause surface subsidence and the development of soil cracks. Traditional irrigation systems are unable to perceive these subtle geological structure changes and continue to irrigate according to the preset mode, causing a large amount of water to seep into the cracks, resulting in ineffective loss of water resources. For example, in stress concentration areas, soil permeability is enhanced, and the original irrigation water volume may far exceed the actual absorption and demand capacity of the soil and vegetation, resulting in a large amount of water resources leaking deep underground and unable to be effectively used by vegetation, resulting in waste of water resources.

[0004] Therefore, an intelligent irrigation system based on oil shale reservoir stress regulation is proposed to solve the above problems. Summary of the Invention

[0005] The main purpose of the present invention is to provide an intelligent irrigation system based on oil shale reservoir stress regulation to solve the problems raised in the above background.

[0006] To achieve the above objectives, the technical solution adopted by the present invention is: a smart irrigation system based on oil shale reservoir stress regulation, the system including a data acquisition end, a stress analysis end and an irrigation decision end; The data acquisition end is used to arrange high-precision stress monitoring sensors in layers to collect reservoir stress changes in the oil shale mining area, soil moisture sensors to monitor the moisture content of soil at different depths in real time, and meteorological stations to collect meteorological data in real time, and transmit the collected data in real time to the data processing center; The stress analysis terminal is used to pre-process the real-time collected data, construct the stress constitutive equation of the oil shale reservoir based on Biot's poroelasticity theory, and calculate the stress change rate by derivatizing the stress constitutive equation with respect to time t; The irrigation decision-making end is used to construct a five-dimensional feature vector, use a support vector machine to decide the irrigation timing based on the five-dimensional feature vector, calculate the irrigation water volume through neural network regression, optimize the irrigation water volume based on water-saving needs and irrigation needs, and dynamically adjust the water-saving adjustment coefficient and the ideal soil moisture value based on the stress change rate.

[0007] Preferably, the data acquisition terminal includes an acquisition unit and a transmission unit; The data collection unit detects reservoir stress changes in real time by placing high-precision stress monitoring sensors every 50 meters in and around the oil shale mining area. Soil moisture sensors are rationally distributed in the oil shale mining area and surrounding vegetation planting areas to monitor soil moisture content at different depths in real time. Through the weather station, wind speed, wind direction, temperature, precipitation, and sunshine duration data are collected in real time. The transmission unit transmits the collected data to the data processing center based on the Wi-Fi module.

[0008] Specifically, high-precision stress monitoring sensors are arranged every 50 meters in and around the oil shale mining area. These sensors can cover stress-sensitive areas at a higher spatial scale, such as mining boundaries or geologically weak zones, to accurately capture the range of stress disturbances. Soil moisture sensors in vegetation planting areas are arranged in layers according to depth, for example, in the surface layer, root layer and deep soil, respectively, to reflect the differences in water holding capacity of different soil layers in real time. Data such as wind speed and temperature collected by meteorological stations can be combined with stress and humidity data to analyze the impact of environmental factors such as evaporation rate and precipitation infiltration on irrigation demand. The collection unit establishes a comprehensive input basis for subsequent stress analysis and irrigation decision-making through multi-source data fusion.

[0009] Preferably, the stress analysis end includes a preprocessing unit, a constitutive unit and a prediction unit; The pre-processing unit is used to perform filtering, denoising, outlier processing and normalization on the data collected in real time.

[0010] Preferably, the constitutive unit is based on Biot's poroelasticity theory to construct the stress constitutive equation of the oil shale reservoir: ; in, represents the stress state of a point in the oil shale reservoir, G represents the shear modulus, represents the strain tensor, represents the Lamé constant, represents the volumetric strain, represents the Kronecker symbol, represents the Biot effective stress coefficient, and p represents the pore pressure.

[0011] During the oil shale mining process, by collecting reservoir stress, pore pressure and other parameters in real time, and substituting variables such as strain tensor and volume strain into the stress constitutive equation, the stress state of each point in the reservoir can be dynamically calculated. For example, when the pore pressure changes due to mining activities, the stress state of each point in the reservoir can be dynamically calculated through the equation. Its impact on reservoir stress can be quantified, and the stress concentration area can be determined. This stress analysis method based on physical models can accurately reflect the temporal and spatial evolution of reservoir stress under mining disturbance, and provide a mechanical basis for subsequent irrigation decisions.

[0012] Preferably, the prediction unit calculates the stress change rate by taking the derivative of the stress constitutive equation with respect to time t, and the calculation formula is: ; in, represents the rate of change of stress, represents the strain rate tensor, represents the volumetric strain rate, Represents the rate of change of pore pressure.

[0013] Specifically, the prediction unit obtains the strain rate tensor, volume strain rate and pore pressure change rate data in real time, substitutes the three sets of parameters into the stress change rate calculation formula, and dynamically outputs the real-time change rate of the reservoir stress state. During the calculation process, the strain rate tensor reflects the spatial distribution characteristics of the deformation rate in all directions of the reservoir, the volume strain rate quantifies the severity of the overall volume change of the reservoir, and the pore pressure change rate represents the fluid pressure fluctuation caused by mining activities. The three are coupled through the physical relationship of the derivatives of the constitutive equation to form a complete description of the dynamic response of the reservoir stress.

[0014] Preferably, the irrigation decision-making end includes a feature unit, a first irrigation unit, a second irrigation unit and an optimization unit.

[0015] Preferably, the feature unit is used to construct a five-dimensional feature vector: ; in, represents the five-dimensional feature vector, represents temperature, Represents the air humidity, represents the probability of rainfall, represents soil moisture, Represents reservoir stress.

[0016] Preferably, the first irrigation unit decides the irrigation timing through an SVM classification model based on a five-dimensional feature vector.

[0017] Specifically, the five-dimensional feature vector provides the input feature space for the SVM classification model by integrating meteorological, soil and reservoir stress data. The model constructs a classification decision function based on historical training data. For example, when the rainfall probability and the reservoir stress change rate are in a specific range, the model outputs an irrigation trigger signal. In actual applications, when the reservoir stress change rate is low and meteorological data predicts no precipitation in the short term, the model can determine that irrigation should be performed immediately; if the reservoir stress is in a state of violent fluctuation, irrigation may be postponed to avoid the risk of water leakage.

[0018] Preferably, the second irrigation unit calculates the irrigation water volume through neural network regression based on the five-dimensional feature vector.

[0019] Specifically, the five-dimensional feature vector is passed as the input layer node to the hidden layer of the neural network. The hidden layer nodes perform nonlinear transformation on the input signal through the activation function, and the final output layer generates the irrigation water volume prediction value. During the training process, the historical soil moisture and irrigation records are used to construct a data set, and the network parameters are optimized by the gradient descent method to minimize the error between the predicted value and the actual water demand. In the deployment stage, the five-dimensional feature data collected in real time is preprocessed and input into the trained network model to output the recommended irrigation water volume value.

[0020] Preferably, the optimization unit includes a correction unit and a dynamic unit; The correction unit optimizes the irrigation water volume based on the water-saving demand and the irrigation demand, and the steps are as follows: Step 1: Calculate the irrigation target value based on water-saving requirements and irrigation requirements. The calculation formula is as follows: ; in, represents the irrigation target value, represents the water-saving regulation coefficient, Actual irrigation water consumption, represents the ideal soil moisture value, Represents the actual soil moisture value, Proportional coefficient, represents the normalized base; Step 2: Set the target threshold. When the target threshold is less than the irrigation target value, the irrigation water volume is reduced proportionally. When the target threshold is greater than or equal to the irrigation target value, the irrigation water volume remains unchanged. The dynamic unit sets a stress threshold. When the stress threshold is greater than the stress change rate, When the water-saving adjustment coefficient β is increased and the ideal soil moisture value is lowered , if the stress threshold is less than the stress change rate When , the water-saving adjustment coefficient β is reduced and the ideal soil moisture value is increased .

[0021] Specifically, the water-saving target is first quantified into a calculation parameter of the irrigation target value through the water-saving adjustment coefficient, and the irrigation target value is generated by combining the difference between the actual soil moisture and the ideal value. When the target threshold is lower than the irrigation target value, the irrigation water volume is proportionally reduced to avoid waste; when it is higher than or equal to the target value, the current water volume is maintained to ensure the water demand of vegetation. The dynamic unit adjusts the water-saving adjustment coefficient and the ideal soil moisture value according to the comparison results of the reservoir stress change rate and the stress threshold: if the stress change rate is lower than the threshold, it indicates that the reservoir stress disturbance is small. At this time, the water-saving coefficient is reduced and the ideal humidity value is increased to increase the irrigation water volume; if it is higher than the threshold, the water-saving coefficient is increased and the ideal humidity value is reduced to reduce the irrigation water volume to prevent water from being lost through the cracks formed by the stress disturbance.

[0022] The present invention has the following beneficial effects: 1. In the present invention, the acquisition unit captures stress changes, soil moisture migration and meteorological data caused by oil shale mining in real time, providing dynamic raw data for the system. The constitutive unit constructs a stress constitutive equation based on Biot's poroelasticity theory, associates the multimodal key parameters of the oil shale reservoir, and analyzes the coupling mechanism of geomechanics and hydrological processes from a theoretical level. The prediction unit calculates the stress change rate by deriving the constitutive equation, dynamically captures the evolution trend of reservoir stress, and predicts the impact of stress changes on soil moisture and vegetation water demand, providing a geomechanical basis for irrigation decision-making, avoiding water resource waste or ecological damage caused by traditional irrigation due to ignoring the impact of geological stress.

[0023] 2. In the present invention, the feature unit constructs a five-dimensional feature vector, integrating multi-dimensional information such as temperature, humidity, rainfall probability, soil moisture, and reservoir stress, and comprehensively considering the complex influencing factors of ecological water demand in the oil shale mining area. The first irrigation unit uses the SVM classification model to decide the irrigation timing, and accurately judges the critical state of vegetation water demand based on multi-source characteristics, avoiding the blindness of traditional irrigation decisions based on experience or fixed cycles, so that the irrigation start is adapted to the rhythm of ecological water demand. The second irrigation unit calculates the irrigation water volume through neural network regression, and uses the model's ability to learn complex nonlinear relationships to accurately quantify the mapping between water demand and multiple factors. At the same time, it works from the dual dimensions of water saving and ecology, dynamically adjusts the water volume by calculating the irrigation target value, and adjusts the water saving coefficient and ideal humidity in combination with the stress change rate, so that irrigation can adapt to the stress environment of the oil shale reservoir while ensuring vegetation growth, thereby achieving a balance between efficient use of water resources and ecological protection. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 This is a flow chart of the smart irrigation system based on oil shale reservoir stress regulation of the present invention; Figure 2 This is a flowchart of the irrigation decision-making end of the smart irrigation system based on oil shale reservoir stress regulation of the present invention. DETAILED DESCRIPTION

[0025] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0026] See also Figure 1 and Figure 2 , the present invention provides a technical solution: an intelligent irrigation system based on oil shale reservoir stress regulation, the system includes a data acquisition end, a stress analysis end and an irrigation decision end; The data acquisition end is used to layer high-precision stress monitoring sensors to collect reservoir stress changes in the oil shale mining area, soil moisture sensors to monitor the moisture content of soil at different depths in real time, and weather stations to collect meteorological data in real time and transmit the collected data to the data processing center; The stress analysis end is used to pre-process the real-time collected data. Based on Biot's poroelasticity theory, it constructs the stress constitutive equation of the oil shale reservoir and calculates the stress change rate by derivatizing the stress constitutive equation with respect to time t. The irrigation decision-making end is used to construct a five-dimensional feature vector, and use a support vector machine to decide the irrigation timing based on the five-dimensional feature vector. The irrigation water volume is calculated through neural network regression, and the irrigation water volume is optimized based on water-saving needs and irrigation needs. The water-saving adjustment coefficient and ideal soil moisture value are dynamically adjusted based on the stress change rate.

[0027] The data acquisition end includes an acquisition unit and a transmission unit; The collection unit arranges high-precision stress monitoring sensors every 50 meters in and around the oil shale mining area to sense reservoir stress changes in real time. Soil moisture sensors are rationally distributed in the oil shale mining area and surrounding vegetation planting areas to monitor the moisture content of soil at different depths in real time. Wind speed, wind direction, temperature, precipitation and sunshine duration data are collected in real time through the meteorological station.

[0028] The stress analysis end includes pre-processing units, constitutive units and prediction units; The preprocessing unit is used to filter, denoise, process outliers and normalize the data collected in real time.

[0029] The constitutive unit is based on Biot's poroelasticity theory to construct the stress constitutive equation of the oil shale reservoir: ; in, represents the stress state of a point in the oil shale reservoir, G represents the shear modulus, represents the strain tensor, represents the Lamé constant, represents the volumetric strain, represents the Kronecker symbol, represents the Biot effective stress coefficient, and p represents the pore pressure.

[0030] The prediction unit calculates the stress change rate based on the stress constitutive equation by taking the derivative of time t. The calculation formula is: ; in, represents the rate of change of stress, represents the strain rate tensor, represents the volumetric strain rate, Represents the rate of change of pore pressure.

[0031] Specifically, the strain rate tensor By describing the rock deformation rate, the pore pressure change rate is obtained through the time derivative of the displacement field. By derivation of the pressure sensor time series data, the volume strain rate is the diagonal sum of the strain rate tensor.

[0032] The irrigation decision end includes a feature unit, a first irrigation unit, a second irrigation unit and an optimization unit.

[0033] The feature unit is used to construct a five-dimensional feature vector: ; in, represents the five-dimensional feature vector, represents temperature, Represents the air humidity, represents the probability of rainfall, represents soil moisture, Represents reservoir stress.

[0034] The first irrigation unit decides the irrigation timing based on the five-dimensional feature vector through the SVM classification model.

[0035] Specifically, the steps for deciding the irrigation timing using the SVM classification model are as follows: ; Constraints: ; in, represents the hyperplane normal vector, represents the bias term, Representative vector The square of the Euclidean norm, represents the penalty coefficient, represents the slack variable, represents the kernel function mapping, represents the sample label, represents the five-dimensional feature vector; The second irrigation unit calculates the irrigation water volume based on the five-dimensional feature vector through neural network regression.

[0036] Specifically, the amount of irrigation water is calculated through neural network regression: ; in, represents the ReLU activation function, represents the linear activation of the output layer, represents the amount of irrigation water, represents the weight of the jth neuron in the output layer, Represents the input of the jth neuron in the hidden layer The weight of represents the kth component of the input feature vector, represents the bias term of the jth neuron in the hidden layer, Represents the total number of neural network layers.

[0037] The optimization unit includes the correction unit and the dynamic unit; The correction unit optimizes the irrigation water volume based on water-saving requirements and irrigation requirements. The steps are as follows: Step 1: Calculate the irrigation target value based on water-saving requirements and irrigation requirements. The calculation formula is as follows: ; in, represents the irrigation target value, represents the water-saving regulation coefficient, Actual irrigation water consumption, represents the ideal soil moisture value, Represents the actual soil moisture value, Proportional coefficient, represents the normalized base; Step 2: Set the target threshold. When the target threshold is less than the irrigation target value, the irrigation water volume is reduced proportionally. When the target threshold is greater than or equal to the irrigation target value, the irrigation water volume remains unchanged. Specifically: The formula for reducing irrigation water volume is: ; in, represents the corrected irrigation water volume, represents the actual irrigation water consumption, represents the irrigation target value, represents the target threshold, represents the learning rate; Dynamic units set stress thresholds. When the stress threshold is greater than the stress change rate, When the water-saving adjustment coefficient β is increased and the ideal soil moisture value is lowered , if the stress threshold is less than the stress change rate When , the water-saving adjustment coefficient β is reduced and the ideal soil moisture value is increased ; Specifically, the stress change rate linkage adjustment is dynamically adjusted using the following formula: ; in, represents the stress threshold, and represents the adjustment gain coefficient, determined by experiment, represents the water-saving regulation coefficient, represents the adjusted water-saving adjustment coefficient, Represents the ideal soil moisture value after adjustment, represents the ideal soil moisture value, Represents the rate of change of stress.

[0038] In this invention, the intelligent irrigation system based on oil shale reservoir stress regulation uses layered high-precision stress monitoring sensors at the data acquisition end, adapted to the burial depth of oil shale of 300-700 meters (the shallowest is about 100 meters). At reasonable intervals of 50 meters, these sensors can capture reservoir stress changes in a comprehensive and fine-grained manner, allowing the system to accurately grasp the disturbance of mining on the geological stress field. Soil moisture sensors are rationally distributed in the vegetation area to monitor soil moisture content at different depths in real time, making up for the shortcoming of traditional irrigation that cannot perceive vertical differences in soil moisture, providing a foundation for subsequent precise water replenishment. The weather station collects multi-dimensional meteorological data, incorporating changes in the atmospheric environment into the system, and transmits the data to the processing center. The preprocessing unit filters and denoises multi-source data, eliminating interference and ensuring input data quality, laying a solid foundation for accurate analysis. The constitutive unit constructs a stress constitutive equation based on Biot's poroelasticity theory, correlating key parameters of the oil shale reservoir, such as stress, strain, and pore pressure, to theoretically analyze the coupling mechanism between geomechanics and hydrological processes. The prediction unit calculates the stress change rate by differentiating the constitutive equation, dynamically capturing the evolution trend of reservoir stress. This allows the system to not only understand the current stress state but also predict the impact of stress changes on soil moisture and vegetation water demand, providing a geomechanical basis for irrigation decisions and enabling irrigation strategies to move beyond superficial hydrological responses. The feature unit constructs a five-dimensional feature vector, integrating multi-dimensional information such as temperature, humidity, rainfall probability, soil moisture, and reservoir stress. This breaks the limitation of traditional irrigation driven by single hydrological or meteorological factors and comprehensively considers the complex influencing factors of ecological water demand in oil shale mining areas. The first irrigation unit uses the SVM classification model to decide the irrigation timing and accurately judges the critical state of vegetation water demand based on multi-source characteristics, avoiding the blindness of traditional irrigation decision-making based on experience or fixed cycles, so that irrigation start-up is adapted to the rhythm of ecological water demand. The second irrigation unit uses neural network regression to calculate the irrigation water volume. The model's ability to learn complex nonlinear relationships is used to accurately quantify the mapping between water demand and multiple factors. The optimization unit works from the dual dimensions of water conservation and ecology. It dynamically adjusts the water volume by calculating the irrigation target value and adjusts the water-saving coefficient and ideal humidity based on the stress change rate. This allows irrigation to adapt to the stress environment of the oil shale reservoir while ensuring vegetation growth, achieving a balance between efficient water resource utilization and ecological protection.

[0039] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0040] Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and variations may be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

Claims

1. The intelligent irrigation system based on oil shale reservoir stress regulation is characterized by: The system includes a data acquisition terminal, a stress analysis terminal and an irrigation decision terminal; The data acquisition end is used to arrange high-precision stress monitoring sensors in layers to collect reservoir stress changes in the oil shale mining area, soil moisture sensors to monitor the moisture content of soil at different depths in real time, and meteorological stations to collect meteorological data in real time, and transmit the collected data in real time to the data processing center; The stress analysis terminal is used to pre-process the real-time collected data, construct the stress constitutive equation of the oil shale reservoir based on Biot's poroelasticity theory, and calculate the stress change rate by derivatizing the stress constitutive equation with respect to time t; The irrigation decision-making end is used to construct a five-dimensional feature vector, use a support vector machine to decide the irrigation timing based on the five-dimensional feature vector, calculate the irrigation water volume through neural network regression, optimize the irrigation water volume based on water-saving needs and irrigation needs, and dynamically adjust the water-saving adjustment coefficient and the ideal soil moisture value based on the stress change rate.

2. The smart irrigation system based on oil shale reservoir stress regulation according to claim 1 is characterized in that: The data acquisition end includes an acquisition unit and a transmission unit; The data collection unit detects reservoir stress changes in real time by placing high-precision stress monitoring sensors every 50 meters in and around the oil shale mining area. Soil moisture sensors are rationally distributed in the oil shale mining area and surrounding vegetation planting areas to monitor soil moisture content at different depths in real time. Through the weather station, wind speed, wind direction, temperature, precipitation, and sunshine duration data are collected in real time. The transmission unit transmits the collected data to the data processing center based on the Wi-Fi module.

3. The smart irrigation system based on oil shale reservoir stress regulation according to claim 1 is characterized in that: The stress analysis end includes a preprocessing unit, a constitutive unit and a prediction unit; The pre-processing unit is used to filter, remove noise, process outliers and normalize the data collected in real time; The constitutive unit is based on Biot's poroelasticity theory to construct the stress constitutive equation of the oil shale reservoir: ； in, represents the stress state of a point in the oil shale reservoir, G represents the shear modulus, represents the strain tensor, represents the Lamé constant, represents the volumetric strain, represents the Kronecker symbol, represents the Biot effective stress coefficient, and p represents the pore pressure; The prediction unit calculates the stress change rate based on the stress constitutive equation by taking the derivative of time t. The calculation formula is: ； in, represents the rate of change of stress, represents the strain rate tensor, represents the volumetric strain rate, Represents the rate of change of pore pressure.

4. The smart irrigation system based on oil shale reservoir stress regulation according to claim 1 is characterized in that: The irrigation decision end includes a feature unit, a first irrigation unit, a second irrigation unit and an optimization unit; The feature unit is used to construct a five-dimensional feature vector: ； in, represents the five-dimensional feature vector, represents temperature, Represents the air humidity, represents the probability of rainfall, represents soil moisture, represents reservoir stress; The first irrigation unit determines the irrigation timing through an SVM classification model based on the five-dimensional feature vector; The second irrigation unit calculates the irrigation water volume through neural network regression based on the five-dimensional feature vector; The optimization unit includes a correction unit and a dynamic unit; The correction unit optimizes the irrigation water volume based on the water-saving demand and the irrigation demand, and the steps are as follows: Step 1: Calculate the irrigation target value based on water-saving requirements and irrigation requirements. The calculation formula is as follows: ； in, represents the irrigation target value, represents the water-saving regulation coefficient, Actual irrigation water consumption, represents the ideal soil moisture value, Represents the actual soil moisture value, Proportional coefficient, represents the normalized base; Step 2: Set the irrigation target threshold. When the actual irrigation target threshold is less than the irrigation target value, the irrigation water volume is reduced proportionally. When the target threshold is greater than or equal to the irrigation target value, the irrigation water volume remains unchanged. The dynamic unit sets a stress threshold. When the stress threshold is greater than the stress change rate, When the water-saving adjustment coefficient β is increased and the ideal soil moisture value is lowered , if the stress threshold is less than the stress change rate When , the water-saving adjustment coefficient β is reduced and the ideal soil moisture value is increased .

Images