Monitoring system and method for saline-alkali soil conditioner blanking

Abstract

The invention relates to the technical field of agricultural soil improvement, and discloses a monitoring system and method for saline-alkali soil conditioner blanking, and the monitoring system comprises a data collection layer, a data processing and analysis layer, a control execution layer and a user interface layer, the data acquisition layer comprises a soil humidity sensor, a salinity and alkalinity sensor, a temperature sensor and a meteorological sensor, the soil humidity sensor is used for measuring the moisture content of soil, and the salinity and alkalinity sensor is used for detecting the salinity and alkalinity of the soil. Through a real-time feedback mechanism, the application process of the soil conditioner can be adjusted in time according to the actual change condition of soil, the system can dynamically adjust the application strategy according to soil data and external meteorological data collected in real time, it is ensured that the soil improvement process continuously conforms to the target state, and the soil improvement efficiency is improved. The effect of an application strategy capable of adapting to complex change of saline-alkali soil is obtained.

Description

Technical Field

[0001] The present invention relates to the technical field of agricultural soil improvement, and in particular to a monitoring system and method for feeding a soil conditioner into saline-alkali land. Background Art

[0002] Saline-alkali soils, due to their high salinity and low fertility, severely impact crop growth and agricultural productivity. To improve soil structure in saline-alkali lands, soil conditioners are often applied to reduce salinity, optimize soil structure, and increase water-holding capacity. However, existing soil conditioner application methods rely primarily on empirical judgment and fixed application rates, lacking real-time monitoring and intelligent control. These methods are unable to adapt to dynamic changes in soil conditions, resulting in both over- and under-application rates, impacting soil conditioner effectiveness and resource utilization efficiency.

[0003] Currently, research on monitoring and controlling the application of soil amendments has involved using soil sensors to monitor parameters such as soil moisture, salinity, and temperature, and combining them with remote sensing image analysis to assess soil conditions. However, traditional soil monitoring systems have many limitations in data processing and feedback, primarily manifested in the following:

[0004] Lack of real-time feedback mechanism: Most monitoring systems only conduct periodic sampling and cannot reflect changes in soil conditions in a timely manner, resulting in delayed application strategies and inability to adapt to the dynamic characteristics of the soil.

[0005] Insufficiently optimized control strategies: Existing application control methods mainly rely on static rules and simple empirical models, and fail to fully utilize optimization control theory to dynamically adjust application strategies, making it impossible to achieve accurate and efficient application of improvers.

[0006] Insufficient soil status prediction capabilities: Traditional soil monitoring methods rely on single-point data and lack a systematic soil status simulation and prediction mechanism. They are unable to predict soil improvement effects in advance, resulting in delayed adjustments to application strategies.

[0007] In view of the above problems, the present invention proposes a monitoring system and method for the feeding of saline-alkali land soil conditioner to solve the above problems. Summary of the Invention

[0008] In view of the deficiencies in the prior art, the present invention provides a monitoring system and method for discharging a soil conditioner in saline-alkali land, so as to solve the problems raised in the above background technology.

[0009] To achieve the above objectives, the present invention is implemented through the following technical solutions: a monitoring system for discharging soil conditioners in saline-alkali land, the monitoring system comprising a data acquisition layer, a data processing and analysis layer, a control execution layer, and a user interface layer:

[0010] The data acquisition layer is used to obtain various soil and environmental data in real time. The data acquisition layer includes a soil moisture sensor, a salinity sensor, a temperature sensor, and a meteorological sensor. The soil moisture sensor is used to measure the moisture content of the soil, the salinity sensor is used to detect the salinity of the soil, the temperature sensor is used to monitor soil temperature changes, and the meteorological sensor is used to obtain external climate data. The collected soil and environmental data are then transmitted to the data processing and analysis layer.

[0011] The data processing and analysis layer is used to preprocess and analyze the transmitted soil and environmental data in real time to form an application strategy. The data processing and analysis layer includes a data preprocessing module, a digital twin model, and an optimization control module. The data preprocessing module denoises and standardizes the collected raw data. The digital twin model simulates the dynamic changes of the soil based on the relationship between the physical and chemical properties of the soil and the application amount of the amendment. The optimization control module generates an application strategy based on the data analysis results and model output.

[0012] The control execution layer adjusts the application amount of the soil conditioner according to the application strategy provided by the data processing and analysis layer to achieve the soil improvement goal;

[0013] The user interface layer provides users with real-time soil status monitoring and application strategy adjustment functions. The user interface layer includes a display interface module and a decision support module. The display interface module is used to display real-time data on soil moisture, salinity, and temperature and the progress of soil improvement. The decision support module automatically recommends application strategies based on information provided by the data processing and analysis layer, allowing users to adjust them according to actual needs.

[0014] Preferably, the data preprocessing module uses a Kalman filter to remove noise from the collected soil and environmental data and standardize the data to ensure the accuracy of subsequent data analysis. The formula of the Kalman filter is:

[0015] x predicted (t)=F·x(t-1)+B·u(t),

[0016] P predicted (t) = F·P(t-1)·F T +Q,

[0017] K(t)=P predicted (t)·H T ·(H·P predicted (t)·H T +R) - ,

[0018] x(t)=x predicted(t)+K(t)·(z(t)-H·x predicted (t)),

[0019] P(t)=(IK(t)·H)·P predicted (t),

[0020] Among them, x(t) is the soil state variable at time t, x predicted (t) is the soil state estimated at the previous moment and predicted by the control input, P(t) is the error covariance matrix at the current moment, and H T is the transpose of the observation matrix, F T is the transpose of the state transition matrix,

[0021] P predicted (t) is the error covariance matrix of the previous moment and the error covariance matrix of the current moment predicted by the state transfer matrix F,

[0022] u(t) is the applied modification dose, F is the state transfer matrix, B is the control input matrix, Q is the process noise covariance matrix, K(t) is the Kalman gain, H is the observation matrix, z(t) is the observation value, R is the observation noise covariance matrix, I is the identity matrix, P(t-1) is the error covariance matrix at the previous moment, and x(t-1) is the soil state variable at moment t-1.

[0023] Preferably, the digital twin model simulates the dynamic relationship between soil and amendment application amount by finite difference method, and the finite difference formula is:

[0024] x i (t+Δt)=x i (t)+(f i (x(t),u(t)))Δt,

[0025] Among them, x i (t) represents the i-th characteristic of the soil state at time t, Δt represents the time step, and f i (x(t),u(t)) represents the function of soil property changes,

[0026] x i (t+Δt) represents the i-th characteristic of the soil state at time t+Δt,

[0027] x(t) is the soil state variable at time t, and u(t) is the applied amendment dosage.

[0028] Preferably, the optimization control module calculates the application strategy through optimal control theory, and the objective function is:

[0029]

[0030] Among them, J is the objective function, λ1 is the weight coefficient, λ2 is the weight coefficient,

[0031] x(t) is the soil state variable at time t, x target is the target soil state,

[0032] u(t) is the modified dose administered,

[0033] T represents the time range of the system optimization process,

[0034] ||x(t)-x target || 2 Represents soil state x(t) and target soil state x target The squared difference between ||u(t)|| 2 represents the square of the applied soil improvement dose u(t),

[0035] dt represents the time differential element in the integral.

[0036] Preferably, the optimization control module predicts the future application strategy based on a model predictive control method, and the model predictive control optimization problem is expressed as:

[0037]

[0038] Among them, u * (t) represents the amount of soil conditioner to be applied at time t, t is the time variable, λ1 is the weight coefficient, λ2 is the weight coefficient, x(t) is the soil state variable at time t, x target is the target soil state, u(t) is the applied improvement dosage, T is the optimization period,

[0039] ||x(t)-x target || 2 Represents soil state x(t) and target soil state x target The squared difference between ||u(t)|| 2 represents the square of the applied soil improvement dose u(t),

[0040] dt represents the time differential element in the integral.

[0041] Preferably, the digital twin model of the data processing and analysis layer dynamically updates the soil state according to the collected soil data and external meteorological data, and the update formula is:

[0042] x(t)=f(x(t-1),u(t))+η(t),

[0043] Where x(t) is the soil state variable at time t, x(t-1) is the soil state at time t-1, η(t) is the external disturbance, and t is the time variable.

[0044] f(x(t-1),u(t)) is a function that describes the change in soil state, and u(t) is the applied amendment dosage.

[0045] Preferably, the user interface layer displays real-time data of soil status, including humidity, salinity, and temperature, through a display interface module, and provides real-time feedback to help users make decisions. The real-time feedback is calculated using the following formula:

[0046] feedback(t)=f feedback (x(t),u(t)),

[0047] Among them, feedback(t) is the real-time feedback value, f feedback (x(t),u(t)) is the feedback function, x(t) is the soil state variable at time t, u(t) is the applied amendment dosage, and t is the time variable.

[0048] Preferably, the decision support module automatically recommends an application plan based on the soil state information and application strategy provided by the data processing and analysis layer. The recommended strategy is generated by the following optimization formula:

[0049]

[0050] Among them, u recommended (t) is the recommended application strategy, t is the time variable, λ1 is the weight coefficient, λ2 is the weight coefficient, x(t) is the soil state variable at time t, x target is the target soil state, u(t) is the applied improvement dosage,

[0051] ||x(t)-x target || 2 Represents soil state x(t) and target soil state x target The squared difference between ||u(t)|| 2 represents the square of the applied soil improvement dose u(t),

[0052] dt represents the time differential element in the integral.

[0053] Preferably, the control execution layer adjusts the application amount through the automated application equipment according to the application strategy provided by the data processing and analysis layer. The automated application equipment adjusts the flow rate, position and pressure according to the control signal. The adjustment process is calculated according to the following formula:

[0054] u(t)=K·x(t)+P,

[0055] Where u(t) is the applied amendment dosage, K is the adjustment factor of the application equipment, x(t) is the soil state variable at time t, and P is a constant;

[0056] The monitoring system connects the data acquisition layer, the data processing and analysis layer and the control execution layer through wireless communication, and the wireless communication uses the LoRa protocol, the Wi-Fi protocol and the Bluetooth protocol for data transmission.

[0057] A method for monitoring the dispensing of a soil conditioner in saline-alkali land comprises the following steps:

[0058] Step 1: Real-time soil and environmental data is acquired through the data acquisition layer. This includes soil moisture sensors to collect soil moisture content, salinity sensors to detect soil salinity, temperature sensors to monitor soil temperature changes, and meteorological sensors to obtain external climate data. The collected soil and environmental data will be transmitted to the data processing and analysis layer via a wireless communication system for subsequent processing.

[0059] Step 2: Preprocess the transmitted soil and environmental data in real time. The preprocessing includes denoising and standardization. A Kalman filter is used to remove noise from the collected data.

[0060] Step 3: The digital twin model simulates the dynamic changes of the soil based on the relationship between the physical and chemical properties of the soil and the amount of amendment applied. The digital twin model simulates the changes in soil properties using the finite difference method and is dynamically updated based on real-time soil data and external climate data to predict future changes in soil conditions.

[0061] Step 4: Based on the data analysis results and the output of the digital twin model, the optimization control module generates an application strategy. The application strategy is calculated using optimal control theory. The optimization goal is to minimize the balance between the soil salinity error and the amount of amendment applied. When calculating the objective function, the difference between the current soil state and the target state, as well as the resource consumption of the applied amendment dosage, are considered;

[0062] Step 5: According to the application strategy provided by the optimization control module, the control execution layer adjusts the application amount of the soil conditioner through the automated application equipment;

[0063] Step 6: During the application process, the user interface layer provides real-time monitoring functions, displaying soil status and application progress. The real-time feedback system compares the current application status with the target soil status, calculates and displays feedback information, and the user can view the feedback data through the display interface module and adjust the application strategy as needed;

[0064] Step 7: The decision support module of the user interface layer automatically recommends an application plan based on the soil state information and application strategy provided by the data processing and analysis layer. The recommended plan is based on real-time data analysis and takes into account the difference between the current soil state and the target state. The system makes real-time adjustments to the application strategy generated by the optimal control algorithm and displays the adjusted strategy recommendations to the user, allowing the user to intervene and optimize.

[0065] Step 8. During system operation, the digital twin model is dynamically updated based on the collected soil data and external environmental data. At this time, the system adjusts the application strategy based on the feedback information to optimize the usage and distribution of soil conditioners.

[0066] The present invention provides a monitoring system and method for dispensing soil conditioners in saline-alkali land. It has the following beneficial effects:

[0067] 1. The present invention uses a real-time feedback mechanism to enable the application process of soil conditioners to be adjusted in a timely manner according to the actual changes in the soil. The system can dynamically adjust the application strategy based on the real-time collected soil data and external meteorological data to ensure that the soil improvement process continues to meet the target state, and obtain the effect of an application strategy that can adapt to the complex changes in saline-alkali soil.

[0068] 2. The present invention generates an optimal amendment application strategy through optimal control theory and model predictive control methods, minimizes the error in soil salinity and the cost of amendment application, achieves efficient use of resources, avoids the problems of over-application and under-application, and obtains accurate, efficient and energy-saving soil improvement effects.

[0069] 3. The present invention uses a digital twin model to simulate and dynamically update the soil state according to the physical and chemical properties of the soil and external meteorological data, and predict the changing trend of the soil in real time, so as to achieve the effect of quickly responding to changes in the saline-alkali land environment and providing accurate application recommendations. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Figure 1 is a system diagram of the present invention;

[0071] Figure 2 Flowchart of the present invention. DETAILED DESCRIPTION

[0072] To help those skilled in the art understand the present invention, the following will provide a clear and complete description of the technical solutions in the embodiments of the present invention, in conjunction with the accompanying drawings. Obviously, the described embodiments are only partial embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0073] The present invention is described in detail below with reference to the accompanying drawings:

[0074] Example:

[0075] Please see the attached Figure 1 The embodiment of the present invention provides a monitoring system for discharging a soil conditioner in saline-alkali land. The monitoring system includes a data acquisition layer, a data processing and analysis layer, a control execution layer, and a user interface layer.

[0076] The data collection layer is used to obtain various soil and environmental data in real time. The data collection layer includes soil moisture sensors, salinity sensors, temperature sensors, and meteorological sensors. The soil moisture sensor is used to measure the moisture content of the soil, the salinity sensor is used to detect the salinity of the soil, the temperature sensor is used to monitor the temperature change of the soil, and the meteorological sensor is used to obtain external climate data. The collected soil and environmental data are then transmitted to the data processing and analysis layer.

[0077] The data processing and analysis layer is used to preprocess and analyze the transmitted soil and environmental data in real time to form an application strategy. The data processing and analysis layer includes a data preprocessing module, a digital twin model, and an optimization control module. The data preprocessing module denoises and standardizes the collected raw data. The digital twin model simulates the dynamic changes of the soil based on the relationship between the physical and chemical properties of the soil and the application amount of the amendment. The optimization control module generates an application strategy based on the data analysis results and model output;

[0078] The control execution layer adjusts the application amount of soil conditioner according to the application strategy provided by the data processing and analysis layer to achieve the soil improvement goal;

[0079] The user interface layer provides users with real-time soil status monitoring and application strategy adjustment functions. The user interface layer includes a display interface module and a decision support module. The display interface module is used to display real-time data on soil moisture, salinity, temperature and soil improvement progress. The decision support module automatically recommends application strategies based on the information provided by the data processing and analysis layer, allowing users to adjust according to actual needs.

[0080] The data collection layer provides real-time, accurate data collection of soil moisture, salinity, and temperature, as well as monitoring of external climate factors, providing data for subsequent processing and analysis. The integration of multiple sensor groups ensures comprehensive monitoring of soil characteristics and environmental factors, supporting system decision-making.

[0081] The data processing and analysis layer benefits from a data preprocessing module that, through denoising and standardization, ensures accurate sensor data, avoiding deviations due to sensor errors and environmental interference. The digital twin model simulates soil dynamics based on the relationship between soil physical and chemical properties and the amount of amendment applied, helping to predict soil conditions and providing a scientific basis for optimization decisions. The optimization control module generates application strategies based on data analysis and model outputs, ensuring that the amount of amendment applied meets actual soil needs, effectively improving resource utilization and improvement effectiveness.

[0082] The benefit of the control execution layer is that it automatically executes application strategies and adjusts the amount of amendment applied to ensure that the soil needs of each area are met, avoiding errors caused by manual operation. By precisely adjusting the application amount, over- and under-application of amendments are avoided, the soil improvement effect is maximized and resources are used efficiently.

[0083] The user interface layer benefits from displaying real-time information about soil moisture, salinity, temperature, and application progress, enabling users to quickly understand soil improvement progress. The decision support module automatically recommends application strategies based on information provided by the data processing and analysis layer, while allowing users to adjust them based on actual needs. This increases system flexibility and operability, ensuring that improvement results meet user expectations.

[0084] The data preprocessing module uses the Kalman filter to remove noise from the collected soil and environmental data and standardize the data to ensure the accuracy of subsequent data analysis. The formula of the Kalman filter is:

[0085] x predicted (t)=F·x(t-1)+B·u(t),

[0086] P predicted (t) = F·P(t-1)·F T +Q,

[0087] K(t)=P predicted (t)·H T ·(H·P predicted (t)·H T +R) - ,

[0088] x(t)=x predicted (t)+K(t)·(z(t)-H·x predicted (t)),

[0089] P(t)=(IK(t)·H)·P predicted (t),

[0090] Among them, x(t) is the soil state variable at time t, xpredicted (t) is the soil state estimated at the previous moment and predicted by the control input, P(t) is the error covariance matrix at the current moment, and H T is the transpose of the observation matrix, F T is the transpose of the state transition matrix,

[0091] P predicted (t) is the error covariance matrix of the previous moment and the error covariance matrix of the current moment predicted by the state transfer matrix F,

[0092] u(t) is the applied modification dose, F is the state transfer matrix, B is the control input matrix, Q is the process noise covariance matrix, K(t) is the Kalman gain, H is the observation matrix, z(t) is the observation value, R is the observation noise covariance matrix, I is the identity matrix, P(t-1) is the error covariance matrix at the previous moment, and x(t-1) is the soil state variable at moment t-1.

[0093] The application of a Kalman filter in the data preprocessing module effectively improves the quality of soil and environmental data. Through noise removal, state estimation optimization, and dynamic adaptability, the system accurately monitors soil conditions. The Kalman filter ensures efficient and accurate performance in complex and dynamic environments, ensuring data accuracy and providing a basis for subsequent data analysis, application strategy generation, and soil improvement.

[0094] The digital twin model simulates the dynamic relationship between soil and amendment application rate using the finite difference method. The finite difference formula is:

[0095] x i (t+Δt)=x i (t)+(f i (x(t),u(t)))Δt,

[0096] Among them, x i (t) represents the i-th characteristic of the soil state at time t, Δt represents the time step, and f i (x(t),u(t)) represents the function of soil property changes,

[0097] x i (t+Δt) represents the i-th characteristic of the soil state at time t+Δt,

[0098] x(t) is the soil state variable at time t, and u(t) is the applied amendment dosage.

[0099] Using the finite difference method, the digital twin model can accurately simulate the dynamic relationship between soil and amendment application rate in real time. It demonstrates strong adaptability and efficiency, particularly when dealing with the complex interactions between soil state and application rate. Advantages include efficient computing power, adaptability to complex soil environments, and the ability to provide real-time feedback when soil state changes, ensuring the system's accuracy and flexibility in dynamic environments. Ultimately, the digital twin model supports the optimization of soil amendment application strategies, ensuring efficient use of resources and maximizing soil improvement results.

[0100] The optimization control module calculates the application strategy through optimal control theory, and the objective function is:

[0101]

[0102] Among them, J is the objective function, λ1 is the weight coefficient, λ2 is the weight coefficient,

[0103] x(t) is the soil state variable at time t, x target is the target soil state,

[0104] u(t) is the modified dose administered,

[0105] T represents the time range of the system optimization process,

[0106] ||x(t)-x target || 2 Represents soil state x(t) and target soil state x target The squared difference between ||u(t)|| 2 represents the square of the applied soil improvement dose u(t),

[0107] dt represents the time differential element in the integral.

[0108] The optimization control module leverages optimal control theory to provide a scientific, dynamic, and precise method for generating application strategies. Its advantage lies in precisely adjusting application rates through objective function optimization, maximizing soil improvement effectiveness and minimizing resource waste. Furthermore, optimization control can adapt to changes in soil conditions in real time, providing flexible and efficient regulation. The application of the optimization control module ensures precise and efficient application of soil conditioners, ensuring effective soil improvement in saline-alkali soils, improving resource utilization efficiency, and providing flexible adaptation solutions for various soil environmental conditions.

[0109] The optimization control module predicts the future application strategy based on the model predictive control method. The model predictive control optimization problem is expressed as:

[0110]

[0111] Among them, u *(t) represents the amount of soil conditioner to be applied at time t, t is the time variable, λ1 is the weight coefficient, λ2 is the weight coefficient, x(t) is the soil state variable at time t, x target is the target soil state, u(t) is the applied improvement dosage, T is the optimization period,

[0112] ||x(t)-x target || 2 Represents soil state x(t) and target soil state x target The squared difference between ||u(t)|| 2 represents the square of the applied soil improvement dose u(t),

[0113] dt represents the time differential element in the integral.

[0114] The optimization control module, based on model predictive control (MPC), precisely controls the application of soil conditioners by predicting future soil conditions and adjusting application strategies in real time. It dynamically adjusts application rates based on soil changes and proactively addresses future soil changes, optimizing resource utilization and minimizing over- and under-application. MPC provides the system with an efficient, flexible, and energy-efficient control strategy, ensuring optimal soil improvement results while reducing resource waste and unnecessary costs.

[0115] The digital twin model of the data processing and analysis layer dynamically updates the soil status based on the collected soil data and external meteorological data. The update formula is:

[0116] x(t)=f(x(t-1),u(t))+η(t),

[0117] Where x(t) is the soil state variable at time t, x(t-1) is the soil state at time t-1, η(t) is the external disturbance, and t is the time variable.

[0118] f(x(t-1),u(t)) is a function that describes the change in soil state, and u(t) is the applied amendment dosage.

[0119] The application of digital twin models in data processing and analysis significantly enhances the dynamic nature of soil conditions and the adaptability of the system. By acquiring real-time soil and external meteorological data, the digital twin model continuously updates soil conditions, predicts future changes, and adjusts application strategies accordingly. These dynamic updates and predictive capabilities ensure the system can make accurate decisions in complex and changing soil environments, improving soil improvement outcomes and resource utilization efficiency. By comprehensively considering soil and external environmental factors, the digital twin model provides the system with a high degree of accuracy, flexibility, and operability.

[0120] The user interface layer displays real-time data on soil conditions, including moisture, salinity, and temperature, through a display interface module, and provides real-time feedback to help users make decisions. The real-time feedback is calculated using the following formula:

[0121] feedback(t)=f feedback (x(t),u(t)),

[0122] Among them, feedback(t) is the real-time feedback value, f feedback (x(t),u(t)) is the feedback function, x(t) is the soil state variable at time t, u(t) is the applied amendment dosage, and t is the time variable.

[0123] Real-time feedback calculations within the user interface layer provide immediate, accurate feedback, helping users make informed decisions based on current soil conditions and application rates. This enhanced system interactivity and flexibility allows users to dynamically adjust application strategies, avoiding resource waste and improving soil improvement outcomes. This feedback system enables users to precisely control application rates, increasing soil improvement efficiency and ensuring the system's ability to effectively respond to changing environmental conditions.

[0124] The decision support module automatically recommends application plans based on the soil status information and application strategies provided by the data processing and analysis layer. The recommended strategy is generated by the following optimization formula:

[0125]

[0126] Among them, u recommended (t) is the recommended application strategy, t is the time variable, λ1 is the weight coefficient, λ2 is the weight coefficient, x(t) is the soil state variable at time t, x target is the target soil state, u(t) is the applied improvement dosage,

[0127] ||x(t)-x target || 2 Represents soil state x(t) and target soil state x target The squared difference between ||u(t)|| 2 represents the square of the applied soil improvement dose u(t),

[0128] dt represents the time differential element in the integral.

[0129] The decision support module automatically generates recommended application plans based on soil condition information and application strategies, enabling precise soil amendment application decisions. Using an optimization formula, the recommended strategy automatically provides users with an appropriate application plan, taking into account the difference between soil condition and target condition, application rate cost, and other factors. This system improves the accuracy and efficiency of application strategies, reduces resource waste, and provides users with flexible and customized decision support, ensuring a scientific and efficient soil amendment process.

[0130] The control execution layer adjusts the application amount through the automated application equipment according to the application strategy provided by the data processing and analysis layer. The automated application equipment adjusts the flow, position and pressure according to the control signal. The adjustment process is calculated according to the following formula:

[0131] u(t)=K·x(t)+P,

[0132] Where u(t) is the applied amendment dosage, K is the adjustment factor of the application equipment, x(t) is the soil state variable at time t, and P is a constant;

[0133] The monitoring system connects the data acquisition layer, data processing and analysis layer, and control execution layer through wireless communication. Wireless communication uses LoRa protocol, Wi-Fi protocol, and Bluetooth protocol for data transmission.

[0134] The integration of the control execution layer and automated application equipment, based on real-time application strategies at the data processing and analysis layer, ensures accurate and efficient application of soil conditioners. By automatically adjusting the application rate, the system dynamically adapts to soil changes, refines application, avoids resource waste, and ensures that each area receives the appropriate amount of amendment. Wireless communication technologies (LoRa, Wi-Fi, and Bluetooth protocols) enable efficient data transmission between layers, ensuring real-time and flexible application processes and providing technical support for the smooth operation of the monitoring system.

[0135] Please see the attached Figure 2 The embodiment of the present invention provides a method for monitoring the feeding of a soil conditioner in saline-alkali land, comprising the following steps:

[0136] Step 1: Real-time soil and environmental data is acquired through the data acquisition layer. This includes soil moisture sensors to collect soil moisture content, salinity sensors to detect soil salinity, temperature sensors to monitor soil temperature changes, and meteorological sensors to obtain external climate data. The collected soil and environmental data will be transmitted to the data processing and analysis layer via a wireless communication system for subsequent processing.

[0137] Step 2: Perform real-time preprocessing on the transmitted soil and environmental data. The preprocessing includes denoising and standardization. A Kalman filter is used to remove noise from the collected data.

[0138] Step 3: The digital twin model simulates the dynamic changes of soil based on the relationship between the physical and chemical properties of the soil and the amount of amendment applied. The digital twin model simulates changes in soil properties using the finite difference method and is dynamically updated based on real-time soil data and external climate data to predict future changes in soil conditions.

[0139] Step 4: Based on the data analysis results and the output of the digital twin model, the optimization control module generates an application strategy. The application strategy is calculated using optimal control theory. The optimization goal is to minimize the balance between the soil salinity error and the amount of amendment applied. When calculating the objective function, the difference between the current soil state and the target state, as well as the resource consumption of the applied amendment dosage, are considered.

[0140] Step 5: According to the application strategy provided by the optimization control module, the control execution layer adjusts the application amount of the soil conditioner through the automated application equipment;

[0141] Step 6: During the application process, the user interface layer provides real-time monitoring functions, displaying soil status and application progress. The real-time feedback system compares the current application status with the target soil status, calculates and displays feedback information, and the user can view the feedback data through the display interface module and adjust the application strategy as needed;

[0142] Step 7: The decision support module of the user interface layer automatically recommends application plans based on the soil state information and application strategies provided by the data processing and analysis layer. The recommended plans are based on real-time data analysis and take into account the difference between the current soil state and the target state. The system makes real-time adjustments to the application strategy generated by the optimal control algorithm and displays the adjusted strategy recommendations to the user, allowing the user to intervene and optimize.

[0143] Step 8. During system operation, the digital twin model is dynamically updated based on the collected soil data and external environmental data. At this time, the system adjusts the application strategy based on the feedback information to optimize the usage and distribution of soil conditioners.

[0144] The monitoring method of the present invention provides an accurate, intelligent, and dynamic soil conditioner application control solution by integrating multiple sets of efficient technical steps. The data acquisition layer and Kalman filter ensure the accuracy of the data, the digital twin model combines real-time data for dynamic prediction, the optimization control module generates a scientific application strategy through optimal control theory, and the control execution layer and automated equipment ensure accurate adjustment of the application amount. The user interface layer provides real-time monitoring and decision support, allowing the system to flexibly respond to changes in soil conditions, automatically optimize application strategies, maximize soil improvement effects, and improve resource utilization efficiency, effectively solving the problems of inaccurate application, waste of resources, and inability to dynamically adjust application strategies in the traditional saline-alkali soil improvement process, and providing a new technical solution for the efficient improvement of saline-alkali soil.

[0145] While embodiments of the present invention have been shown and described, it will be appreciated 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 invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A monitoring system for discharging soil conditioners in saline-alkali land, characterized in that: The monitoring system includes a data acquisition layer, a data processing and analysis layer, a control execution layer, and a user interface layer: The data acquisition layer is used to obtain various soil and environmental data in real time. The data acquisition layer includes a soil moisture sensor, a salinity sensor, a temperature sensor, and a meteorological sensor. The soil moisture sensor is used to measure the moisture content of the soil, the salinity sensor is used to detect the salinity of the soil, the temperature sensor is used to monitor soil temperature changes, and the meteorological sensor is used to obtain external climate data. The collected soil and environmental data are then transmitted to the data processing and analysis layer. The data processing and analysis layer is used to preprocess and analyze the transmitted soil and environmental data in real time to form an application strategy. The data processing and analysis layer includes a data preprocessing module, a digital twin model, and an optimization control module. The data preprocessing module denoises and standardizes the collected raw data. The digital twin model simulates the dynamic changes of the soil based on the relationship between the physical and chemical properties of the soil and the application amount of the amendment. The optimization control module generates an application strategy based on the data analysis results and model output. The control execution layer adjusts the application amount of the soil conditioner according to the application strategy provided by the data processing and analysis layer to achieve the soil improvement goal; The user interface layer provides users with real-time soil status monitoring and application strategy adjustment functions. The user interface layer includes a display interface module and a decision support module. The display interface module is used to display real-time data on soil moisture, salinity, and temperature and the progress of soil improvement. The decision support module automatically recommends application strategies based on information provided by the data processing and analysis layer, allowing users to adjust them according to actual needs.

2. A monitoring system for discharging a saline-alkali soil conditioner according to claim 1, characterized in that: The data preprocessing module uses a Kalman filter to remove noise from the collected soil and environmental data and standardize the data to ensure the accuracy of subsequent data analysis. The formula of the Kalman filter is: x predicted (t)=F·x(t-1)+B·u(t), P predicted (t)=F·P(t-1)·F T +Q, K(t)=P predicted (t)·H T ·(H·P predicted (t)·H T +R) - , x(t)=x predicted (t)+K(t)·(z(t)-H·x predicted (t)), P(t)=(I-K(t)·H)·P predicted (t), Among them, x(t) is the soil state variable at time t, x predicted (t) is the soil state estimated at the previous moment and predicted by the control input, P(t) is the error covariance matrix at the current moment, and H T is the transpose of the observation matrix, F T is the transpose of the state transition matrix, P predicted (t) is the error covariance matrix of the previous moment and the error covariance matrix of the current moment predicted by the state transfer matrix F, u(t) is the applied modification dose, F is the state transfer matrix, B is the control input matrix, Q is the process noise covariance matrix, K(t) is the Kalman gain, H is the observation matrix, z(t) is the observation value, R is the observation noise covariance matrix, I is the identity matrix, P(t-1) is the error covariance matrix at the previous moment, and x(t-1) is the soil state variable at moment t-1.

3. A monitoring system for discharging a saline-alkali soil conditioner according to claim 1, characterized in that: The digital twin model simulates the dynamic relationship between soil and amendment application amount using the finite difference method. The finite difference formula is: x i (t+Δt)=x i (t)+(f i (x(t),u(t)))Δt, Among them, x i (t) represents the i-th characteristic of the soil state at time t, Δt represents the time step, and f i (x(t),u(t)) represents the function of soil property changes, x i (t+Δt) represents the i-th characteristic of the soil state at time t+Δt, x(t) is the soil state variable at time t, and u(t) is the applied amendment dosage.

4. A monitoring system for discharging a saline-alkali soil conditioner according to claim 3, characterized in that: The optimization control module calculates the application strategy through optimal control theory, and the objective function is: Among them, J is the objective function, λ1 is the weight coefficient, λ2 is the weight coefficient, x(t) is the soil state variable at time t, x target is the target soil state, u(t) is the modified dose administered, T represents the time range of the system optimization process, ||x(t)-x target || 2 Represents soil state x(t) and target soil state x target The squared difference between ||u(t)|| 2 represents the square of the applied soil improvement dose u(t), dt represents the time differential element in the integral.

5. A monitoring system for discharging a saline-alkali soil conditioner according to claim 4, characterized in that: The optimization control module predicts the future application strategy based on the model predictive control method. The model predictive control optimization problem is expressed as: Among them, u * (t) represents the amount of soil conditioner to be applied at time t, t is the time variable, λ1 is the weight coefficient, λ2 is the weight coefficient, x(t) is the soil state variable at time t, x target is the target soil state, u(t) is the applied improvement dosage, T is the optimization period, ||x(t)-x target || 2 Represents soil state x(t) and target soil state x target The squared difference between ||u(t)|| 2 represents the square of the applied soil improvement dose u(t), dt represents the time differential element in the integral.

6. A monitoring system for discharging a saline-alkali soil conditioner according to claim 1, characterized in that: The digital twin model of the data processing and analysis layer dynamically updates the soil state based on the collected soil data and external meteorological data. The update formula is: x(t)=f(x(t-1),u(t))+η(t), Where x(t) is the soil state variable at time t, x(t-1) is the soil state at time t-1, η(t) is the external disturbance, and t is the time variable. f(x(t-1),u(t)) is a function that describes the change in soil state, and u(t) is the applied amendment dosage.

7. A monitoring system for discharging saline-alkali soil conditioner according to claim 1, characterized in that: The user interface layer displays real-time data on soil conditions, including moisture, salinity, and temperature, through a display interface module, and provides real-time feedback to help users make decisions. The real-time feedback is calculated using the following formula: feedback(t)=f feedback (x(t),u(t)), Among them, feedback(t) is the real-time feedback value, f feedback (x(t),u(t)) is the feedback function, x(t) is the soil state variable at time t, u(t) is the applied amendment dosage, and t is the time variable.

8. A monitoring system for discharging a saline-alkali soil conditioner according to claim 1, characterized in that: The decision support module automatically recommends application plans based on the soil status information and application strategies provided by the data processing and analysis layer. The recommended strategies are generated by the following optimization formula: Among them, u recommended (t) is the recommended application strategy, t is the time variable, λ1 is the weight coefficient, λ2 is the weight coefficient, x(t) is the soil state variable at time t, x target is the target soil state, u(t) is the applied improvement dosage, ||x(t)-x target || 2 Represents soil state x(t) and target soil state x target The squared difference between ||u(t)|| 2 represents the square of the applied soil improvement dose u(t), dt represents the time differential element in the integral.

9. A monitoring system for discharging a saline-alkali soil conditioner according to claim 1, characterized in that: The control execution layer adjusts the application amount through the automated application equipment according to the application strategy provided by the data processing and analysis layer. The automated application equipment adjusts the flow rate, position and pressure according to the control signal. The adjustment process is calculated according to the following formula: u(t)=K·x(t)+P, Where u(t) is the applied amendment dosage, K is the adjustment factor of the application equipment, x(t) is the soil state variable at time t, and P is a constant; The monitoring system connects the data acquisition layer, the data processing and analysis layer and the control execution layer through wireless communication, and the wireless communication uses the LoRa protocol, the Wi-Fi protocol and the Bluetooth protocol for data transmission.

10. A method for monitoring the discharging of a soil conditioner in saline-alkali land, according to a monitoring system for discharging a soil conditioner in saline-alkali land according to any one of claims 1 to 9, characterized in that: The steps include: Step 1: Real-time soil and environmental data is acquired through the data acquisition layer. This includes soil moisture sensors to collect soil moisture content, salinity sensors to detect soil salinity, temperature sensors to monitor soil temperature changes, and meteorological sensors to obtain external climate data. The collected soil and environmental data will be transmitted to the data processing and analysis layer via a wireless communication system for subsequent processing. Step 2: Preprocess the transmitted soil and environmental data in real time. The preprocessing includes denoising and standardization. A Kalman filter is used to remove noise from the collected data. Step 3: The digital twin model simulates the dynamic changes of the soil based on the relationship between the physical and chemical properties of the soil and the amount of amendment applied. The digital twin model simulates the changes in soil properties using the finite difference method and is dynamically updated based on real-time soil data and external climate data to predict future changes in soil conditions. Step 4: Based on the data analysis results and the output of the digital twin model, the optimization control module generates an application strategy. The application strategy is calculated using optimal control theory. The optimization goal is to minimize the balance between the soil salinity error and the amount of amendment applied. When calculating the objective function, the difference between the current soil state and the target state, as well as the resource consumption of the applied amendment dosage, are considered; Step 5: According to the application strategy provided by the optimization control module, the control execution layer adjusts the application amount of the soil conditioner through the automated application equipment; Step 6: During the application process, the user interface layer provides real-time monitoring functions, displaying soil status and application progress. The real-time feedback system compares the current application status with the target soil status, calculates and displays feedback information, and the user can view the feedback data through the display interface module and adjust the application strategy as needed; Step 7: The decision support module of the user interface layer automatically recommends an application plan based on the soil state information and application strategy provided by the data processing and analysis layer. The recommended plan is based on real-time data analysis and takes into account the difference between the current soil state and the target state. The system makes real-time adjustments to the application strategy generated by the optimal control algorithm and displays the adjusted strategy recommendations to the user, allowing the user to intervene and optimize. Step 8. During system operation, the digital twin model is dynamically updated based on the collected soil data and external environmental data. At this time, the system adjusts the application strategy based on the feedback information to optimize the usage and distribution of soil conditioners.

Images