An intelligent monitoring and control method and system for soil moisture

Abstract

The present invention relates to the technical field of soil physical property detection, and particularly to an intelligent monitoring and control method and system for soil moisture content, including: multi-modal sensor data acquisition, deploying a multi-modal sensor array in the soil area to be measured; interference compensation and correction; adaptive calibration; moisture phase differentiation and soil moisture content index calculation; soil moisture content assessment, comprehensively evaluating the actual water content, available water content, soil moisture content index and moisture phase information obtained in S4, setting different grade thresholds to obtain the soil moisture content assessment result; intelligent control decision-making and execution, using the soil moisture content assessment result as input to generate corresponding control decisions. The intelligent monitoring and control system for soil moisture content can not only monitor the soil moisture status in real time, but also improve the accuracy and efficiency of agricultural irrigation through intelligent compensation, calibration and decision optimization, so as to achieve the goals of water conservation and efficient crop management.

Description

Technical Field

[0001] The present invention relates to the technical field of soil physical property detection, and particularly to an intelligent monitoring and control method and system for soil moisture content. Background Art

[0002] Soil moisture content monitoring plays a crucial role in fields such as agricultural production, water resource management, and ecological environment protection. However, there are still many problems to be solved in the existing soil moisture content monitoring technologies. On the one hand, when traditional capacitive sensors measure soil water content, they are extremely susceptible to interference from environmental factors such as soil salinity and temperature, resulting in a significant decrease in measurement accuracy, and thus affecting the accurate assessment of the actual soil water content. On the other hand, most of the existing monitoring systems can only obtain the total soil water content and are difficult to effectively distinguish different phases of water in the soil, such as liquid water, solid water, and gaseous water, etc. This makes it lack detailed information on water phases when analyzing the dynamic changes of soil moisture and the water requirements of crops, thereby limiting the comprehensiveness and accuracy of soil moisture content monitoring.

[0003] In addition, the calibration parameters of traditional soil moisture content monitoring systems are usually fixed and cannot be automatically adjusted according to different soil types and environmental conditions, which leads to an increase in measurement errors of the system under different regions and different soil types, and the applicability and reliability are severely restricted. At the same time, the existing soil moisture content assessment methods mainly rely on a single water content index and lack a comprehensive assessment of soil moisture status, making it difficult to comprehensively consider the actual state of soil moisture and the water requirements of crops, easily resulting in inaccurate irrigation decisions and affecting the growth and yield of crops.

[0004] Finally, the intelligence level of existing monitoring systems is generally low. Most of them can only perform simple data collection and display, lacking intelligent data processing and decision support functions. When facing complex soil environments and changing meteorological conditions, they cannot automatically perform data compensation, calibration, and analysis, nor can they generate scientific irrigation decisions in real time according to soil moisture content, resulting in low irrigation efficiency and serious waste of water resources. Summary of the Invention

[0005] Based on the above purposes, the present invention provides an intelligent monitoring and control method for soil moisture content, including the following steps:

[0006] S1: Multi-modal sensor data collection. Deploy a multi-modal sensor array in the soil area to be measured. The multi-modal sensor array includes a capacitive sensor, a time domain reflectometry sensor, and a heat pulse sensor. The collected parameters include capacitance value C, dielectric constant , temperature T, thermal conductivity λ, soil salinity content S;

[0007] S2: Interference compensation and correction. Input the capacitance value C, dielectric constant collected in S1 and the temperature T and the soil salt content S, and obtain the compensated capacitance value C through the compensation formula corrected , compensated dielectric constant ;

[0008] S3: Adaptive calibration, take the compensated capacitance value C corrected , compensated dielectric constant , temperature T and thermal conductivity λ as the inputs of the Bayesian optimization algorithm, and use the Bayesian optimization algorithm to output the optimized calibration parameter P opt ;

[0009] S4: Moisture phase discrimination and soil moisture index calculation, take the compensated capacitance value C corrected , compensated dielectric constant , temperature T, the optimized calibration parameter P opt as the inputs of the fuzzy logic algorithm, distinguish the moisture phase information in the soil based on the fuzzy logic algorithm, and according to the discrimination result, combine the optimized calibration parameter to calculate the actual water content θ, effective water content θ eff and soil moisture index SI;

[0010] S5: Soil moisture assessment, comprehensively evaluate the actual water content θ, effective water content θ eff and soil moisture index SI and moisture phase information obtained in S4, set different grade thresholds to obtain the soil moisture assessment result;

[0011] S6: Intelligent control decision-making and execution, take the soil moisture assessment result as the input to generate the corresponding control decision.

[0012] Preferably, in S2, the compensation formula is as follows:

[0013] ;

[0014] where C corrected is the compensated capacitance value;

[0015] C is the capacitance value obtained by initial measurement;

[0016] T is the temperature of the soil, in degrees Celsius (°C);

[0017] S is the soil salt content;

[0018] a is the compensation coefficient for the interference of temperature on the capacitance value, indicating the amount of capacitance value to be compensated when the temperature changes by 1 unit;

[0019] b is the compensation coefficient for the interference of soil salt on the capacitance value, indicating the amount of capacitance value to be compensated when the soil salt changes by 1 unit;

[0020] c is the comprehensive compensation coefficient, which is used to compensate for the interference caused by other unknown factors except temperature and salinity to the measurement of capacitance value;

[0021] The dielectric constant compensation formula is:

[0022] ;

[0023] Wherein, is the compensated dielectric constant;

[0024] is the dielectric constant obtained from the initial measurement;

[0025] T is the temperature of the soil, in degrees Celsius (°C).

[0026] Preferably, in S3, it specifically includes the following steps:

[0027] S3.1: Set the initial calibration parameter P0;

[0028] S3.2: Construct the likelihood function L(D|P), where D is the measurement data, including the capacitance value C, the dielectric constant , the temperature T, the thermal conductivity λ, and the soil salinity content S, and P represents the calibration parameter. The likelihood function is the probability of obtaining the measurement data D given the calibration parameter P. The likelihood function is as follows:

[0029] ;

[0030] Wherein, is the i-th group of measurement data, is a function of the calibration parameter P, which maps the calibration parameter to the predicted value of the measurement data, is the noise variance of the i-th group of data, and n is the total amount of measurement data;

[0031] S3.3: Determine the prior probability P(P), and its expression is as follows:

[0032] ;

[0033] Wherein, m is the number of calibration parameters;

[0034] j is the index parameter, is the calibration parameter of the j-th group;

[0035] S3.4: Update the posterior probability P(P∣D) through the Bayesian formula. The formula is as follows:

[0036] ;

[0037] S3.5: Traverse the posterior probability distribution samples obtained by sampling, and find the distribution sample with the largest corresponding posterior probability, that is, the calibration parameter P that maximizes the posterior probability. opt , in this process, continuously repeat S3.2 - S3.5, and finally output the optimized calibration parameter P. opt .

[0038] Preferably, in S4, it specifically includes the following:

[0039] S4.1: The input variables are the compensation capacitance value C corrected , the compensation dielectric constant and the temperature T, and the output variable is the phase state information of soil moisture, including free water, transitional water, and bound water;

[0040] S4.2: Define the membership function of the compensation capacitance value C corrected , the membership function of the compensation dielectric constant and the membership function of the temperature T;

[0041] S4.3: Formulate fuzzy rules:

[0042] Rule 1: If the compensation capacitance value is high, the compensation dielectric constant is large, and the temperature is high, then the soil mainly contains free water;

[0043] Rule 2: If the compensation capacitance value is low, the compensation dielectric constant is small, and the temperature is low, then the soil mainly contains bound water;

[0044] Rule 3: If the compensation capacitance value is medium, the compensation dielectric constant is medium, and the temperature is medium, then the soil mainly contains transitional water;

[0045] S4.4: Convert C corrected , ϵ corrected and T into fuzzy sets, calculate the membership values of each input variable, and then calculate the activation degree of each fuzzy rule, and finally obtain the proportion of free water;

[0046] S4.5: Calculate the actual water content θ of the soil, the available water content θ eff and the soil moisture index SI.

[0047] In S4.4, the proportion y of free water is obtained by the following formula:

[0048] ;

[0049] where α1 is the activation degree of Rule 1; α2 is the activation degree of Rule 2, and α3 is the activation degree of Rule 3;

[0050] The calculation formula for the actual water content θ is as follows:

[0051] ;

[0052] where C corrected is the compensation capacitance value, is the compensation dielectric constant, T is the temperature, P opt is the optimized calibration parameter, and y is the proportion of free water;

[0053] The calculation formula for the effective water content θ eff is as follows:

[0054] ;

[0055] where θ res is the residual water content; the residual water content can be estimated by empirical methods (including model fitting methods), can also be obtained by natural air-drying method and mercury intrusion method, and can also be determined according to the water content calculation formula established based on the microscopic structure of montmorillonite interlayer hydration (the water content when the first layer of montmorillonite is hydrated is the residual water content);

[0056] The calculation formula for the soil moisture index SI is as follows:

[0057] ;

[0058] where θ fc is the field capacity, and θ wp is the wilting coefficient.

[0059] The method for measuring the field capacity is the core cutter method: collect undisturbed soil from the experimental plot, bring it back to the laboratory, saturate the soil sample with water, place it on the air-dried soil to drain the gravitational water, and then use the artificial drying method to measure the soil gravimetric water content, which is the field capacity. The method for measuring the wilting coefficient: plant the plant in a container, seal the soil surface with a mixture of paraffin and vaseline, and when the plant leaves wilt, place it in a place with appropriate air humidity. At this time, the percentage of soil moisture in the air-dried soil weight is the wilting coefficient.

[0060] Preferably, in S5, the evaluation grades of the soil moisture include the following:

[0061] Good: When the following conditions are met, the soil moisture is determined to be "good":

[0062] SI≥0.8;

[0063] The actual water content θ is between 80% - 100% of the field capacity θ fc ;

[0064] The effective water content θ eff is sufficient to meet the growth requirements of the crop, that is, θ eff ≥θmin , θ min is the minimum effective water content determined according to the crop type;

[0065] Suitable: When the following conditions are met, the soil moisture is determined to be "suitable":

[0066] 0.5 ≤ SI < 0.8;

[0067] The actual water content θ is between 50% - 80% of the field capacity θ fc ;

[0068] The effective water content θ eff basically meets the crop growth, that is, θ min < θ eff ≤ θ opt , θ opt is the optimal effective water content determined according to the crop type;

[0069] Mild drought: When the following conditions are met, the soil moisture is determined to be "mild drought":

[0070] 0.2 ≤ SI < 0.5;

[0071] The actual water content θ is between 20% - 50% of the field capacity θ fc ;

[0072] The effective water content θ eff begins to be insufficient, that is, θ eff < θ min；

[0073] Severe drought: When any of the following conditions is met, the soil moisture is determined to be "severe drought":

[0074] SI < 0.2;

[0075] The actual water content θ is lower than 20% of the field capacity θ fc .

[0076] Preferably, in S6, it specifically includes the following strategies:

[0077] When the soil moisture is "mild drought", if it is a field crop and the water source is sufficient, select drip irrigation or sprinkler irrigation methods, send an opening instruction to the irrigation equipment (such as the controller of the drip irrigation system, the water pump control unit of the sprinkler irrigation system), and set the irrigation duration or irrigation volume at the same time;

[0078] When the soil moisture is "severe drought", regardless of the crop type, preferably adopt flood irrigation or a combination of rapid drip irrigation / sprinkler irrigation to quickly replenish soil moisture, send an opening instruction to the irrigation equipment, and set the irrigation duration or irrigation volume.

[0079] An intelligent monitoring and control system for soil moisture includes a multimodal data acquisition module, an interference compensation and correction module, an adaptive calibration module, a moisture phase differentiation and index calculation module, a soil moisture assessment module, and an intelligent control decision-making and execution module. These modules are connected through a data bus and a control bus to achieve data transmission and instruction execution;

[0080] The multimodal data acquisition module includes a sensor integration unit and a data preliminary perception unit; the interference compensation and correction module includes an interference analysis unit and a compensation and correction unit; the adaptive calibration module includes an initial parameter setting unit and an optimization adjustment unit; the moisture phase differentiation and index calculation module includes a moisture phase differentiation unit and an index calculation unit; the soil moisture assessment module includes a threshold setting unit and a comprehensive assessment unit; the intelligent control decision-making and execution module includes a decision generation unit and an instruction execution unit.

[0081] Preferably, in the multimodal data acquisition module, the sensor integration unit integrates multiple types of sensors, including a capacitive sensor, a time domain reflectometry (TDR) sensor, and a heat pulse sensor. These sensors are installed at different depths in the soil and can synchronously collect the capacitance value, dielectric constant, temperature, thermal conductivity, and soil salinity content S of the soil. The capacitive sensor is installed 10 cm below the soil surface for real-time monitoring of changes in soil capacitance; the time domain reflectometry sensor is installed 20 cm below the soil surface for measuring the propagation characteristics of electromagnetic waves in the soil to obtain the soil dielectric constant; the heat pulse sensor is installed 30 cm below the soil surface for monitoring changes in soil thermal conductivity;

[0082] In the data preliminary perception unit, the capacitive sensor makes a preliminary judgment on soil water content by sensing changes in soil capacitance; the time domain reflectometry sensor obtains the soil dielectric constant by measuring the propagation characteristics of electromagnetic waves in the soil, and then calculates the soil water content; the heat pulse sensor assists in judging the soil moisture state by monitoring changes in soil thermal conductivity and differentiates the liquid water and solid water components therein.

[0083] Preferably, it further includes a residual water content and field capacity acquisition module. Among them, the residual water content and field capacity acquisition module includes a sample drying and weighing unit and a control and operation unit. The control and operation unit controls the sample drying and weighing unit to dry the soil sample and then weighs it to calculate the residual water content and field capacity.

[0084] The beneficial effects of the present invention:

[0085] 1. By introducing multi-modal sensors and intelligent data processing modules, the problem that "traditional capacitive sensors are easily affected by soil salinity and temperature, thus affecting the measurement accuracy" is overcome. By combining multiple sensors such as soil moisture, temperature, pH value, and microbial activity, the present invention can comprehensively evaluate soil moisture conditions from multiple angles, avoiding the influence of interference from external factors (such as salinity and temperature) on a single sensor. The intelligent data processing module can also filter and correct sensor data, further improving the measurement accuracy of soil water content.

[0086] 2. Existing systems often adopt a single measurement method and cannot effectively distinguish different phases of water in the soil (such as liquid water and solid water). The present invention adopts multi-modal measurement technology, combining multiple modules such as capacitive, moisture sensors, temperature sensors, and soil microbial activity sensors to achieve multi-dimensional monitoring of the water state in the soil. By comprehensively analyzing the soil moisture, temperature, and microbial activity, liquid water and solid water can be more accurately distinguished, thereby improving the comprehensiveness and accuracy of soil moisture monitoring.

[0087] 3. The fixed calibration parameters of traditional soil moisture monitoring systems have poor applicability under different regions and soil types, resulting in increased measurement errors. The present invention introduces an intelligent adaptive calibration mechanism to automatically adjust and optimize calibration parameters for different soil types and environmental conditions. This enables the system to perform personalized calibration according to the actual conditions of the soil, achieving efficient application across regions and soil types, and improving the accuracy and reliability of the system in different environments.

[0088] 4. Considering multi-dimensional factors such as moisture, temperature, and soil health comprehensively, the system can provide refined management solutions to help agricultural producers make better decisions on irrigation, fertilization, etc., improve the health status of the soil and crops, and thus increase crop yield and quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0089] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only those of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0090] Figure 1 is the step flow chart of the method of the present invention;

[0091] Figure 2 is the step flow chart of step S3 of the method of the present invention;

[0092] Figure 3 is the system block diagram of the system of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0093] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it should be noted here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments. For some well-known technologies, those skilled in the art can also adopt other alternative methods for implementation; moreover, the accompanying drawings are only for more specifically describing the embodiments and are not intended to specifically limit the present invention.

[0094] Please refer to Figures 1 - 3 , an embodiment of the present invention provides a method for intelligent monitoring and control of soil moisture. Through the mutual cooperation of each step, accurate monitoring and intelligent control of soil moisture are achieved, optimizing the effect of agricultural irrigation.

[0095] First, deploy a multi-modal sensor array in the soil area to be measured. This array includes a capacitive sensor, a time-domain reflectometry sensor, and a heat pulse sensor. Each sensor is responsible for collecting different parameters, such as capacitance value C, dielectric constant , temperature T, thermal conductivity λ, and soil salinity content S. By simultaneously collecting different types of soil data, these sensors provide multi-dimensional basic data for subsequent analysis. The diversity of the data can ensure a comprehensive understanding of the soil moisture state.

[0096] Due to factors such as changes in the external environment and differences in soil properties, the sensor data may be subject to certain interference, affecting the measurement accuracy. Therefore, in step S2, the input raw data (capacitance value C, dielectric constant , temperature T, and soil salinity content S) is corrected through a preset compensation formula to obtain more accurate capacitance value Ccorrected, dielectric constant , temperature T, and soil salinity content S. This step ensures the stability and reliability of the data, laying a foundation for subsequent calibration and analysis.

[0097] Next, the corrected data (Ccorrected, , T) and the thermal conductivity λ are input into the adaptive calibration module. Using the Bayesian optimization algorithm, the system automatically adjusts the calibration parameters and outputs the optimized calibration parameters Popt. Bayesian optimization can automatically adjust according to data samples, avoiding manual intervention and improving the accuracy and flexibility of calibration, especially suitable for diverse environments with different soil types and moisture states.

[0098] The corrected data and optimized calibration parameters will be input into the soil moisture phase differentiation and soil moisture index calculation module. This module uses a fuzzy logic algorithm to distinguish different moisture phases in the soil and calculates the actual water content θ, effective water content θeff, and soil moisture index SI of the soil in combination with the optimized calibration parameters. The fuzzy logic algorithm can handle the complex laws of soil moisture changes and improve the accuracy of soil moisture assessment.

[0099] Based on the soil moisture indicators obtained in step S4, the system comprehensively evaluates the actual water content θ, effective water content θeff, and moisture index SI with the moisture phase information. By setting different thresholds, different soil moisture levels will be generated for the evaluation results. For example, if the actual water content is lower than the set threshold, it is determined to be drought, otherwise it is suitable for irrigation. This evaluation result provides a basis for subsequent intelligent control decisions.

[0100] Finally, based on the soil moisture assessment results obtained in step S5, the system generates corresponding control decisions. According to the soil moisture level, the intelligent control system will activate the automated irrigation equipment for irrigation to ensure the water requirements of crops at different growth stages. Through this module, the system can control irrigation efficiently and accurately, avoiding over-irrigation or water shortage.

[0101] Preferably, in S2, the compensation formula is as follows:

[0102] ;

[0103] where C corrected is the compensation capacitance value;

[0104] C is the capacitance value obtained from the initial measurement;

[0105] T is the temperature of the soil, in degrees Celsius (°C);

[0106] S is the soil salt content;

[0107] a is the compensation coefficient for the interference of temperature on the capacitance value, indicating the amount of capacitance value that needs to be compensated when the temperature changes by 1 unit;

[0108] b is the compensation coefficient for the interference of soil salt on the capacitance value, indicating the amount of capacitance value that needs to be compensated when the soil salt changes by 1 unit;

[0109] c is the comprehensive compensation coefficient, used to compensate for the interference of other unknown factors on the capacitance value measurement except for temperature and salt;

[0110] The dielectric constant compensation formula is:

[0111] ;

[0112] wherein, is the compensation dielectric constant;

[0113] is the dielectric constant obtained from the initial measurement;

[0114] T is the temperature of the soil, in degrees Celsius (°C).

[0115] Preferably, in S4, the calculation formula for the actual water content θ is as follows:

[0116] ;

[0117] wherein, C corrected is the compensation capacitance value, is the compensation dielectric constant, T is the temperature, P opt is the optimized calibration parameter;

[0118] The calculation formula for the effective water content θ eff is as follows:

[0119] ;

[0120] wherein, θ res is the residual water content;

[0121] The calculation formula for the soil moisture index SI is as follows:

[0122] ;

[0123] wherein, θ fc is the field capacity, and θ wp is the wilting coefficient.

[0124] In a possible implementation manner, in step S3, the Bayesian optimization algorithm is used for adaptive calibration of soil moisture monitoring. Specifically, first, an initial calibration parameter set P0 is set, and these parameters are selected based on previous experience or experimental data, aiming to provide a starting point for the optimization process. The initial calibration parameter P0 may include relevant physical characteristic parameters such as capacitance value, dielectric constant, temperature, etc., which play a key role in actual soil measurement.

[0125] In S3.2, a likelihood function L(D|P) is constructed to measure the probability of the actual measurement data D (including capacitance value C, dielectric constant , the probability of occurrence of (e.g., temperature T, thermal conductivity λ, soil salinity content S). Specifically, this function evaluates the quality of the calibration parameter P by comparing the difference between the model predicted values and the actual observed data. The noise variance σi in the formula characterizes the uncertainty of each group of measurement data, and n is the total amount of measurement data. The role of this step is to provide a correction direction for the parameter in a data-driven manner. The likelihood function is as follows:

[0126] ;

[0127] is the i-th group of measurement data, is a function of the calibration parameter P that maps the calibration parameter to the predicted value of the measurement data, is the noise variance of the i-th group of data, and n is the total amount of measurement data.

[0128] In step S3.3, based on the prior knowledge of the calibration parameter, set the prior probability P(P) of the parameter. This probability reflects the likelihood distribution of the parameter P in the absence of any measurement data and is usually determined based on experience or historical data. The prior distribution P(P) can take forms such as uniform distribution, Gaussian distribution, etc., where m is the number of calibration parameters and j is the index parameter. Through this step, the initial likelihood of each calibration parameter can be reasonably estimated, providing a basis for subsequent Bayesian updates.

[0129] The prior probability P(P), and its expression is as follows:

[0130] ;

[0131] where m is the number of calibration parameters;

[0132] j is the index parameter.

[0133] In step S3.4, apply Bayes' formula to update the posterior probability P(P|D), that is, calculate the probability distribution of the calibration parameter P under the condition of the given measurement data D. Bayes' formula combines the prior probability P(P) and the likelihood function L(D|P) to obtain a new posterior probability distribution. The core of this process is to continuously correct the understanding of the calibration parameter according to the new measurement data, making the parameter more accurately reflect the actual soil moisture state. The formula is as follows:

[0134] .

[0135] In S3.5, by traversing multiple candidate samples sampled from the posterior probability distribution, find the distribution sample that maximizes the posterior probability, that is, obtain the final optimized calibration parameter P opt . To ensure the final calibration parameter P optAccurate and reliable. In this process, the steps from S3.2 to S3.4 need to be repeated continuously until the posterior probability stabilizes. Finally, the optimized calibration parameter P opt will be used as the basis for further system analysis and control.

[0136] In a possible implementation, in S4, it specifically includes the following:

[0137] S4.1: The input variables are the compensation capacitance value C corrected , the compensation dielectric constant and the temperature T, and the output variable is the phase state information of soil moisture, including free water, transitional water, and bound water;

[0138] S4.2: Define the membership function of the compensation capacitance value C corrected , the membership function of the compensation dielectric constant and the membership function of the temperature T;

[0139] S4.3: Formulate fuzzy rules:

[0140] Rule 1: If the compensation capacitance value is high, the compensation dielectric constant is large, and the temperature is high, then the soil mainly contains free water;

[0141] Rule 2: If the compensation capacitance value is low, the compensation dielectric constant is small, and the temperature is low, then the soil mainly contains bound water;

[0142] Rule 3: If the compensation capacitance value is medium, the compensation dielectric constant is medium, and the temperature is medium, then the soil mainly contains transitional water;

[0143] S4.4: Convert C corrected , ϵ corrected and T into fuzzy sets, calculate the membership values of each input variable, then calculate the activation degree of each rule, and finally obtain the proportion of free water;

[0144] S4.5: Calculate the actual water content θ of the soil, the available water content θ eff and the soil moisture index SI.

[0145] In S4.4, the proportion of free water y is obtained through the following formula:

[0146] ;

[0147] where, α1 is the activation degree of Rule 1; α2 is the activation degree of Rule 2, and α3 is the activation degree of Rule 3.

[0148] The calculation formula for the actual water content θ is as follows:

[0149] ;

[0150] Among them, C corrected is the compensation capacitance value, is the compensation dielectric constant, T is the temperature, P opt is the optimized calibration parameter, and y is the proportion of free water;

[0151] The effective water content θ eff is calculated as follows:

[0152] ;

[0153] Among them, θ res is the residual water content;

[0154] The calculation formula of the soil moisture index SI is as follows:

[0155] ;

[0156] Among them, θ fc is the field capacity, and θ wp is the wilting coefficient.

[0157] In a possible implementation manner, in step S5, the evaluation level of the soil moisture is based on multiple key parameters, such as the soil moisture index (SI), the actual water content (θ), and the effective water content (θ eff ). These parameters reflect the wetness of the soil and the suitability of crop growth. Therefore, it is necessary to comprehensively analyze these factors to determine the specific level of the soil moisture.

[0158] Specifically, the SI value, as the core index to measure the soil moisture state, determines the basic level division of the soil moisture. According to the SI value, the soil moisture can be divided into "good" (SI≥0.8), "suitable" (0.5≤SI<0.8), "mild drought" (0.2≤SI<0.5), and "severe drought" (SI<0.2). The SI value is obtained by comprehensively considering various factors, such as soil moisture, temperature, humidity, etc. A higher SI value indicates sufficient water supply in the soil, which is suitable for crop growth; a lower SI value means insufficient soil moisture, which may affect crop growth.

[0159] θ (actual water content) refers to the existing water in the soil, while θ fc is the field capacity, that is, the maximum amount of water that the soil can retain. When the actual water content θ is between 80% - 100% of the field capacity, the soil moisture is determined to be "good"; when θ is between 50% - 80%, the soil moisture is "suitable"; if the actual water content θ is less than 20% of the field capacity, it is determined to be "severe drought".

[0160] [[ID=eff The (available water content) is the water that is crucial for crop growth and generally considers the part of soil water that can be absorbed by plant roots.

[0161] When assessing soil moisture conditions, it is necessary to pay attention to whether the available water content is sufficient to meet the growth needs of crops:

[0162] "Good" soil moisture conditions require the available water content θ eff ≥θ min (minimum available water content), which can ensure the water requirements of crops.

[0163] "Suitable" soil moisture conditions require the available water content to be between θ min and θ opt , where θ opt is the optimal available water content for crops.

[0164] When the available water content θ eff is lower than θ min , the soil moisture condition is determined as "mild drought" or "severe drought".

[0165] In a possible implementation, in step S6 of the intelligent monitoring and control method for soil moisture conditions, the key is to adopt different irrigation strategies according to different soil moisture states (such as "mild drought" and "severe drought") to ensure effective replenishment of soil water and thus guarantee the healthy growth of crops.

[0166] Specifically, when the soil moisture condition is evaluated as "mild drought", first judge according to the crop type and water source conditions. If the crop is a field crop and the water source is sufficient, select a suitable irrigation method. Among field crops, drip irrigation or sprinkler irrigation is considered a more efficient irrigation method. Drip irrigation can supply water precisely to the roots, reducing water waste; sprinkler irrigation can cover a larger area and is suitable for larger fields. Once the irrigation method is determined, send an opening instruction to the irrigation equipment through the intelligent system and set an appropriate irrigation duration or irrigation volume at the same time. The set irrigation volume is adjusted according to soil humidity, crop requirements and environmental conditions to avoid over-irrigation or insufficient water.

[0167] When the soil moisture condition is evaluated as "severe drought", regardless of the crop type, priority should be given to quickly replenishing water to the soil. In this case, the selection of the irrigation method aims to quickly restore soil moisture. In the case of severe drought, it is more efficient to use flood irrigation or a combination of rapid drip irrigation / sprinkler irrigation. Flood irrigation can quickly cover a large area of land and rapidly increase soil moisture; while the combination of rapid drip irrigation or sprinkler irrigation can accurately supplement water in a short time, avoiding excessive evaporation. The system automatically sets the corresponding irrigation duration or irrigation volume according to the irrigation method. Since the soil water content is extremely low in the case of severe drought, a larger irrigation volume is required to ensure that the soil moisture can be restored as soon as possible.

[0168] Flexibly adjust the irrigation method and irrigation volume according to the changes in soil moisture. When the soil moisture is relatively sufficient but slightly water-deficient, adopt precise and water-saving drip irrigation or sprinkler irrigation; while in severe drought conditions, flood irrigation or combined methods for quickly replenishing water are the preferred choices. The intelligent monitoring system automatically selects the irrigation plan based on the real-time data of soil moisture assessment, thereby achieving intelligent control.

[0169] Correspondingly, the embodiment of the present invention also provides an intelligent monitoring and control system for soil moisture. Through the close cooperation between various modules, precise monitoring and efficient control of soil moisture are achieved.

[0170] The multi-modal data acquisition module consists of a sensor integration unit and a data preliminary perception unit. The sensor integration unit is responsible for collecting moisture data at different layers in the soil (such as humidity, temperature, conductivity, etc.) and transmitting these raw data to other modules of the system through the data bus. The data preliminary perception unit then conducts a preliminary analysis of the collected raw data to judge the accuracy and reliability of the data. After the data is collected, the sensor module transmits the information to the interference compensation and correction module for subsequent processing.

[0171] The interference compensation and correction module consists of an interference analysis unit and a compensation and correction unit. The interference analysis unit analyzes the interference factors (such as environmental changes, equipment errors, etc.) in the raw data obtained from the acquisition module and evaluates them. The compensation and correction unit compensates and corrects the data according to the results of the interference analysis to ensure the accuracy and reliability of the data. The corrected data is then transmitted to the adaptive calibration module. The corrected data transmitted from the interference compensation and correction module will be sent to the adaptive calibration module to further calibrate the system.

[0172] The adaptive calibration module consists of an initial parameter setting unit and an optimization and adjustment unit. The initial parameter setting unit sets the preliminary soil parameters according to historical data or experience. The optimization and adjustment unit adaptively optimizes the initial parameters according to the real-time collected data to achieve precise soil moisture assessment. The optimized and calibrated parameters are transmitted to the moisture phase differentiation and index calculation module. The optimized calibrated parameters provide data support for subsequent soil assessment.

[0173] The moisture phase differentiation and index calculation module includes a moisture phase differentiation unit and an index calculation unit. The moisture phase differentiation unit judges the phase of soil moisture (such as liquid, gaseous or solid) according to the optimized and calibrated data, providing a basis for subsequent moisture assessment. The index calculation unit then calculates relevant soil moisture indexes based on the moisture phase data, such as soil moisture storage, available water volume, etc. The calculated moisture indexes and moisture phase data will be transmitted to the soil moisture assessment module.

[0174] The soil moisture assessment module consists of a threshold setting unit and a comprehensive assessment unit. The threshold setting unit sets different soil moisture assessment criteria and determines various soil moisture states (such as wet, dry, etc.) according to the moisture index. The comprehensive assessment unit comprehensively assesses the soil moisture based on the set thresholds and combines various index data, and outputs the assessment results. The assessment results are transmitted to the intelligent control decision-making and execution module for corresponding control decisions to be made.

[0175] The intelligent control decision-making and execution module includes a decision generation unit and an instruction execution unit. The decision generation unit generates control instructions such as irrigation and fertilization according to the soil moisture assessment results and makes decisions according to the priorities set by the system. The instruction execution unit receives the decision instructions and executes corresponding operations (such as starting irrigation equipment, adjusting water flow, etc.). The instruction execution unit sends the instructions to the irrigation control equipment or other execution units through the control bus to achieve the automated operation of the system.

[0176] In a possible implementation manner, the multi-modal data acquisition module can comprehensively and accurately acquire data closely related to the soil moisture state by integrating a capacitive sensor, a time domain reflectometry sensor, and a heat pulse sensor, providing basic data for the intelligent monitoring and analysis of soil moisture. These sensors are installed in the soil at different depths to form a three-dimensional monitoring network, capable of synchronously obtaining multi-dimensional data of the soil.

[0177] Specifically, the capacitive sensor is installed 10 cm below the soil surface and is mainly used to monitor the change of the soil capacitance value in real time. The capacitance value of the soil is closely related to the moisture content. Therefore, the capacitive sensor can directly reflect the soil moisture content by sensing the change of the soil capacitance. The capacitive sensor transmits the acquired capacitance data to the data preliminary perception unit, which performs preliminary processing and provides a data basis for subsequent moisture assessment.

[0178] The time domain reflectometry sensor is installed 20 cm below the soil surface and is mainly used to measure the propagation characteristics of electromagnetic waves in the soil, and then obtain the dielectric constant of the soil. The dielectric constant of the soil is closely related to the moisture content in the soil, especially the change of the dielectric constant can reflect the soil moisture state. The time domain reflectometry sensor calculates the dielectric constant of the soil by measuring the propagation speed of electromagnetic waves and the characteristics of the reflected wave and provides it to the data preliminary perception unit for further moisture calculation.

[0179] The thermal pulse sensor is installed 30 cm below the soil surface and is used to monitor the change of soil thermal conductivity. The thermal conductivity of the soil is closely related to its water content and water state (liquid water and solid water). The thermal pulse sensor calculates the soil thermal conductivity and judges the soil water state by heating pulses and measuring the response change of temperature. This data is also transmitted to the data preliminary perception unit and combined with the data of other sensors to further improve the judgment of the soil water state.

[0180] In the data preliminary perception unit, the raw data collected by the capacitive sensor, time domain reflectometry sensor and thermal pulse sensor will be preliminarily processed. Through the data of the capacitive sensor, the system can preliminarily judge the water content of the soil. The data calculated by the time domain reflectometry sensor through the dielectric constant can further confirm the change of the soil water content. The thermal pulse sensor assists in judging the state of soil moisture and differentiates the components of liquid water and solid water. The role of this module is to integrate the data of each sensor and provide a preliminary assessment of the soil water state and its changes.

[0181] In a possible implementation manner, it further includes a residual water content and field capacity acquisition module. Among them, the residual water content and field capacity acquisition module includes a sample drying and weighing unit and a control and operation unit. The control and operation unit controls the drying and weighing unit to dry the soil sample and then weigh it to calculate the residual water content and field capacity.

[0182] The present invention covers any substitutions, modifications, equivalent methods and solutions made within the spirit and scope of the present invention. In order to enable the public to have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention. However, those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion to the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0183] 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. An intelligent monitoring and control method for soil moisture content, characterized in that It includes the following steps: S1: Multimodal sensor data acquisition. Deploy a multimodal sensor array in the soil area to be measured. The multimodal sensor array includes a capacitive sensor, a time domain reflectometry sensor, and a heat pulse sensor. The parameters collected include capacitance value C, dielectric constant , temperature T, thermal conductivity λ, and soil salt content S; S2: Interference compensation and correction, input the capacitance value C, dielectric constant , temperature T, and soil salt content S collected in S1, and obtain the compensated capacitance value Ccorrected and compensated dielectric constant through the compensation formula; S3: Adaptive calibration, taking the compensated capacitance value Ccorrected, compensated dielectric constant , temperature T, and thermal conductivity λ as the inputs of the Bayesian optimization algorithm, and using the Bayesian optimization algorithm to output the optimized calibration parameter Popt; S4: Moisture phase differentiation and soil moisture index calculation. The compensated capacitance value Ccorrected, compensated dielectric constant , temperature T, and optimized calibration parameter Popt are used as the inputs of the fuzzy logic algorithm. Based on the fuzzy logic algorithm, the moisture phase information in the soil is differentiated. According to the differentiation result, the residual water content and field capacity obtained from the test, and combined with the optimized calibration parameter, the actual water content θ, available water content θeff, and soil moisture index SI of the soil are calculated; Specifically, S4 includes the following: S4.1: The input variables are the compensated capacitance value Ccorrected, the compensated dielectric constant and the temperature T, and the output variable is the moisture phase information in the soil, including free water, transitional water, and bound water; S4.2: Define the membership functions of the compensated capacitance value Ccorrected, the compensated dielectric constant and the membership function of the temperature T; S4.3: Formulate fuzzy rules: Rule 1: If the compensated capacitance value is high, the compensated dielectric constant is large, and the temperature is high, then the main component in the soil is free water; Rule 2: If the compensated capacitance value is low, the compensated dielectric constant is small, and the temperature is low, then the main component in the soil is bound water; Rule 3: If the compensated capacitance value is medium, the compensated dielectric constant is medium, and the temperature is medium, then the main component in the soil is transitional water; S4.4: Convert Ccorrected, ϵcorrected, and T into fuzzy sets, calculate the membership degree values of each input variable, then calculate the activation degree of each fuzzy rule, and finally obtain the proportion of free water; S4.5: Calculate the actual water content θ of the soil, the available water content θeff, and the soil moisture index SI; S5: Soil moisture assessment. Integrate and evaluate the actual water content θ, the available water content θeff, the soil moisture index SI, and the water phase state information obtained in S4, set different grade thresholds, and obtain the soil moisture assessment result; S6: Intelligent control decision-making and execution. Use the soil moisture assessment result as the input to generate corresponding control decisions.

2. The intelligent monitoring and control method for soil moisture content according to claim 1, characterized in that, In S2, the capacitance value compensation formula is as follows: ； Where, Ccorrected is the compensated capacitance value; C is the capacitance value obtained from the initial measurement; T is the temperature of the soil, in degrees Celsius (°C); S is the soil salt content; a is the compensation coefficient for the interference of temperature on the capacitance value, indicating the amount of capacitance value to be compensated when the temperature changes by 1 unit; b is the compensation coefficient for the interference of soil salt content on the capacitance value, indicating the amount of capacitance value to be compensated when the soil salt changes by 1 unit; c is the comprehensive compensation coefficient, used to compensate for the interference on the capacitance value measurement caused by other factors except temperature and salt; The dielectric constant compensation formula is: ； wherein, is the compensation dielectric constant; is the dielectric constant obtained from the initial measurement; T is the temperature of the soil, in degrees Celsius (°C).

3. The intelligent monitoring and control method for soil moisture content according to claim 2, characterized in that, In S3, it specifically includes the following steps: S3.1: Set the initial calibration parameter P0; S3.2: Construct the likelihood function L(D|P), where D is the measured data, including capacitance value C, dielectric constant , temperature T, thermal conductivity λ, soil salt content S, and P represents the calibration parameters. The likelihood function is the probability of obtaining the measured data D given the calibration parameters P. The likelihood function is as follows: ； wherein, is the i-th set of measurement data, is a function of the calibration parameter P that maps the calibration parameter to the predicted value of the measurement data, is the noise variance of the i-th set of measurement data, and n is the total amount of measurement data; S3.3: Determine the prior probability P(P), and its expression is as follows: ； Where, m is the number of calibration parameters; j is an index parameter, which is the calibration parameter for the j-th group; S3.4: Update the posterior probability P(P∣D) through Bayes' formula. The formula is as follows ； S3.5: Traverse and sample to obtain the distribution sample corresponding to the posterior probability, find the distribution sample with the largest corresponding posterior probability, that is, the calibration parameter Popt that makes the posterior probability the largest. In this process, continuously repeat S3.2 - S3.5, and finally output the optimized calibration parameter Popt.

4. The intelligent monitoring and control method for soil moisture content according to claim 3, characterized in that, In S4.4, the proportion y of free water is obtained through the following formula: ； Where, α1 is the activation degree of Rule 1; α2 is the activation degree of Rule 2, and α3 is the activation degree of Rule 3; The calculation formula for the actual water content θ is as follows: ； Among them, Ccorrected is the compensated capacitance value, is the compensated dielectric constant, T is the temperature, Popt is the optimized calibration parameter, and y is the proportion of free water; The calculation formula for the available water content θeff is as follows: ； Where, θres is the residual water content; The calculation formula for the soil moisture index SI is as follows: ； Where, θfc is the field capacity, and θwp is the wilting coefficient.

5. A method for intelligent monitoring and control of soil moisture content according to claim 4, characterized in that In S5, the evaluation grades of soil moisture include the following: Good: When the following conditions are met, the soil moisture is determined to be "good": SI≥0.8; The actual water content θ is between 80% and 100% of the field capacity θfc; The available water content θeff is sufficient to meet the crop growth requirements, i.e., θeff≥θmin, where θmin is the minimum available water content determined according to the crop type; Suitable: When the following conditions are met, the soil moisture condition is determined to be "suitable": 0.5≤SI<0.8; The actual water content θ is between 50% and 80% of the field capacity θfc; The available water content θeff basically meets the crop growth, i.e., θmin<θeff≤θopt, where θopt is the optimal available water content determined according to the crop type; Mild drought: When the following conditions are met, the soil moisture condition is determined to be "mild drought": 0.2≤SI<0.5; The actual water content θ is between 20% and 50% of the field capacity θfc; The available water content θeff begins to be insufficient, i.e., θeff<θmin; Severe drought: When any of the following conditions is met, the soil moisture condition is determined to be "severe drought": SI<0.2; The actual water content θ is lower than 20% of the field capacity θfc.

6. The intelligent monitoring and control method for soil moisture content according to claim 5, wherein, In S6, it specifically includes the following strategies: When the soil moisture condition is "mild drought", if it is a field crop and the water source is sufficient, select the drip irrigation or sprinkler irrigation method, send an opening instruction to the irrigation equipment, and at the same time set the irrigation duration or irrigation volume; When the soil moisture condition is "severe drought", regardless of the crop type, preferentially adopt the flood irrigation or the combination of rapid drip irrigation / sprinkler irrigation method to quickly supplement the soil moisture, send an opening instruction to the irrigation equipment, and set the irrigation duration or irrigation volume.

7. An intelligent soil moisture monitoring and control system, which is applied to the intelligent soil moisture monitoring and control method described in any one of claims 1-6, and is characterized in that, It includes a multi-modal data acquisition module, an interference compensation and correction module, an adaptive calibration module, a water phase differentiation and index calculation module, a soil moisture condition assessment module, and an intelligent control decision-making and execution module. These modules are connected through a data bus and a control bus to realize data transmission and instruction execution; The multi-modal data acquisition module includes a sensor integration unit and a data preliminary perception unit; The interference compensation and correction module includes an interference analysis unit and a compensation and correction unit; The adaptive calibration module includes an initial parameter setting unit and an optimization and adjustment unit; The water phase differentiation and index calculation module includes a water phase differentiation unit and an index calculation unit; The soil moisture condition assessment module includes a threshold setting unit and a comprehensive assessment unit; The intelligent control decision-making and execution module includes a decision generation unit and an instruction execution unit.

8. The intelligent monitoring and control system for soil moisture content according to claim 7, characterized in that, In the multi-modal data acquisition module, the sensor integration unit integrates various types of sensors, including a capacitive sensor, a time domain reflectometry sensor, and a heat pulse sensor. These sensors are installed at different depths in the soil and can synchronously collect the capacitance value, dielectric constant, temperature, thermal conductivity, and soil salinity content S of the soil. Among them, the capacitive sensor is installed 10 cm below the soil surface for real-time monitoring of the change in soil capacitance; the time domain reflectometry sensor is installed 20 cm below the soil surface for measuring the propagation characteristics of electromagnetic waves in the soil to obtain the dielectric constant of the soil; the heat pulse sensor is installed 30 cm below the soil surface for monitoring the change in the thermal conductivity of the soil; In the data preliminary perception unit, the capacitive sensor makes a preliminary judgment on the soil moisture content by sensing the change of soil capacitance; the time domain reflectometry sensor obtains the soil dielectric constant by measuring the propagation characteristics of electromagnetic waves in the soil, and then calculates the soil moisture content; the heat pulse sensor assists in judging the soil moisture state and differentiates the components of liquid water and solid water in the soil by monitoring the change of soil thermal conductivity.

9. The intelligent monitoring and control system for soil moisture content according to claim 8, characterized in that, It further includes a residual moisture content and field capacity acquisition module. Among them, the residual moisture content and field capacity acquisition module includes a sample drying and weighing unit and a control and operation unit. The control and operation unit controls the sample drying and weighing unit to dry the soil sample, and then weighs it to calculate the residual moisture content and field capacity.

Images