Farmland water-saving self-adaptive irrigation system based on Internet of Things

Abstract

The invention relates to the technical field of farmland water saving, in particular to a farmland water-saving self-adaptive irrigation system based on the Internet of Things, which comprises a data acquisition module, a crop irrigation sensitivity self-adaptive adjustment module, an intelligent decision module and an intelligent control module, the data acquisition module acquires environmental data of farmland soil in real time; the crop irrigation sensitivity self-adaptive adjustment module evaluates the irrigation sensitivity of crops in the current growth stage in real time, and outputs a sensitivity level and suggested irrigation intensity; the intelligent decision-making module generates an irrigation strategy through a multi-objective optimization algorithm; the intelligent control module executes the irrigation strategy and controls the water pump, the valve and the pipe network flow of the irrigation system. According to the method, the scientificity of irrigation decision and the accuracy of data analysis are improved, and resource waste and decision errors caused by data incompleteness or deviation are effectively avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of farmland water conservation, and particularly to an Internet of Things-based adaptive irrigation system for farmland water conservation. Background Art

[0002] With the increasing severity of the global water shortage problem, as a major water user in agriculture, water-saving irrigation technology has received more and more attention. Most traditional farmland irrigation methods rely on empirical judgment and lack scientific basis, resulting in widespread phenomena of water resource waste and crop yield fluctuations. In recent years, the rapid development of Internet of Things technology has provided new ideas for the intelligent management of agriculture. By collecting environmental and crop status data in real time through sensors and combining intelligent decision-making algorithms, precise control of irrigation can be achieved, thereby improving water resource utilization efficiency and crop yields.

[0003] Currently, Internet of Things-based farmland irrigation systems have achieved data collection and control functions to a certain extent, but there are still deficiencies in many aspects. First, environmental data and crop physiological state data are not fully combined, resulting in the lack of accurate assessment of the real-time water demand status of crops in irrigation decision-making. Second, existing decision-making algorithms mainly focus on optimizing single variables and cannot comprehensively consider regional zoning requirements and water resource supply constraints. Third, the response speed of the execution link of irrigation strategies is slow and lacks dynamic feedback, making it difficult to adapt to the rapid changes in crop demands, which affects the overall efficiency and practicality of the system.

[0004] In view of the above problems, the present invention provides an Internet of Things-based adaptive irrigation system for farmland water conservation, which effectively improves water resource utilization efficiency, meets the differentiated needs of crops, and at the same time ensures the healthy growth and high yield of crops. Summary of the Invention

[0005] The present invention provides an Internet of Things-based adaptive irrigation system for farmland water conservation.

[0006] An Internet of Things-based adaptive irrigation system for farmland water conservation includes a data collection module, a crop irrigation sensitivity adaptive adjustment module, an intelligent decision-making module, and an intelligent control module, wherein;

[0007] The data collection module collects environmental data of farmland soil in real time, including soil humidity, air temperature, air humidity, and light intensity;

[0008] The crop irrigation sensitivity adaptive adjustment module collects physiological state data of crops, including crop canopy temperature, leaf area index, and leaf water content, combines the collected environmental data, evaluates the irrigation sensitivity of crops in the current growth stage in real time, and outputs the sensitivity level and recommended irrigation intensity;

[0009] The intelligent decision-making module generates an irrigation strategy through a multi-objective optimization algorithm based on the output sensitivity level and recommended irrigation intensity, combined with the zoning requirements of the farmland area and the water resource supply situation, including the regional irrigation priority, irrigation water volume allocation, and irrigation time period.

[0010] The intelligent control module executes the irrigation strategy to control the pumps, valves, and pipe network flow rates of the irrigation system.

[0011] Optionally, the data acquisition module includes:

[0012] Soil moisture data acquisition: Equipped with soil moisture sensors buried at different depths and regions in the farmland to monitor the soil moisture content in real time.

[0013] Air temperature and humidity data acquisition: Deploy environmental temperature and humidity sensors in the farmland to monitor the air temperature and humidity in real time.

[0014] Light intensity data acquisition: Install light intensity sensors in the farmland to capture the changes in farmland light intensity in real time.

[0015] Optionally, the crop irrigation sensitivity adaptive adjustment module includes:

[0016] Crop physiological state data acquisition: Collect crop physiological state data, including crop canopy temperature, leaf area index, and leaf water content.

[0017] Data preprocessing: Preprocess the collected environmental data and crop physiological state data, including noise filtering, missing value filling, and normalization processing.

[0018] Sensitivity assessment: Based on the preprocessed environmental data and crop physiological state data, use a sensitivity assessment model to evaluate the irrigation sensitivity of the crop at the current growth stage and output the sensitivity level of the crop, including low sensitivity, medium sensitivity, and high sensitivity.

[0019] Irrigation intensity recommendation: Give corresponding irrigation intensity recommendations according to different sensitivity levels.

[0020] Optionally, the crop physiological state data acquisition includes:

[0021] Crop canopy temperature acquisition: Through a non-contact infrared temperature sensor installed in the farmland, monitor the temperature change of the crop canopy in real time.

[0022] Leaf area index acquisition: By deploying a laser scanning system, obtain the image data of crop leaves and calculate the leaf area index LAI.

[0023] Leaf water content acquisition: Use a non-contact spectral sensor to calculate the water content index of crop leaves in real time by measuring the water absorption spectral characteristics of the leaves.

[0024] Optionally, the data preprocessing includes:

[0025] Noise filtering: Use the moving average method to filter the noise of the collected environmental data and crop physiological state data;

[0026] Missing value filling: Use the linear interpolation method to fill the missing values in the collected environmental data and crop physiological state data;

[0027] Normalization processing: Normalize the environmental data and crop physiological state data of different dimensions.

[0028] Optionally, the sensitivity evaluation model uses a Bayesian network model, and the Bayesian network model includes:

[0029] Construct a Bayesian network structure: Establish a network structure based on crop physiological state data and environmental data, define the conditional dependence relationship between variables, and the Bayesian network is represented as a directed acyclic graph (DAG), which consists of nodes and edges;

[0030] Quantify the conditional probability distribution: Assign a conditional probability table (CPT) to each node, and statistically calculate the conditional probability distribution of each variable according to historical crop physiological state data and environmental data;

[0031] Input data instantiation: Use the real-time collected crop physiological state data and environmental data as input to instantiate the network nodes. Each input variable E i is represented as: E i = acquisition value;

[0032] Sensitivity probability inference: According to the conditional probability table in the Bayesian network, combined with the instantiated input data, infer the posterior probability of crop irrigation sensitivity;

[0033] Output sensitivity level: According to the calculated posterior probability, select the level with the highest sensitivity probability as the final evaluation result S of the sensitivity level * When S * < 0.3, it is low sensitivity. When 0.3 ≤ S * < 0.6, it is medium sensitivity. When S * ≥ 0.6, it is high sensitivity.

[0034] Optionally, the irrigation intensity recommendation includes:

[0035] Irrigation intensity recommendation for low sensitivity level: When the sensitivity level of the crop is low sensitivity, it is recommended to keep the irrigation operation suspended;

[0036] Irrigation intensity recommendations for medium sensitivity level: When the sensitivity level of the crop is medium sensitivity, it is recommended to maintain the current irrigation time and irrigation water volume;

[0037] Irrigation intensity recommendations for high sensitivity level: When the sensitivity level of the crop is high sensitivity, water resources should be preferentially allocated. It is recommended to shorten the irrigation interval and increase the single irrigation water volume.

[0038] Optionally, the intelligent decision-making module includes:

[0039] Calculation of regional irrigation priority: According to the sensitivity level S * and weight factor of each region, calculate the priority P i ;

[0040] Optimization of water resource allocation: Based on the limited water resource W total , combined with the priority P i and water demand W i of each region, optimize the allocation of water resources with the goal of maximizing irrigation benefits;

[0041] Irrigation time period planning: Combine environmental data to select the irrigation time period.

[0042] Optionally, the intelligent control module includes:

[0043] Analysis of irrigation strategy and generation of instructions: Receive the irrigation strategy output by the intelligent decision-making module, including regional irrigation priority, irrigation water volume and irrigation time period. Generate device control instructions through a PID controller to generate corresponding water pump start, valve opening and pipe network flow regulation instructions;

[0044] Water pump control: Control the start and stop and flow regulation of the corresponding water pump according to the irrigation area and water volume demand in the irrigation strategy;

[0045] Valve control: Regulate the electric valves in the irrigation area, and dynamically adjust the opening time and opening degree of the valves according to the regional priority and irrigation time period;

[0046] Monitoring and regulation of pipe network flow: Real-time monitor the water flow and pressure of the pipe network, and maintain the water supply flow by adjusting the flow control valve or pipe diverter.

[0047] Advantages of the present invention:

[0048] In the present invention, through the collaborative work of the data acquisition module and the crop irrigation sensitivity adaptive adjustment module, the real-time acquisition and dynamic processing of environmental data and crop physiological state data are realized. Combining with the Bayesian network model, the irrigation sensitivity of crops at different growth stages is accurately evaluated, and the sensitivity level and irrigation intensity suggestions are output, significantly improving the scientific nature of irrigation decision-making and the accuracy of data analysis, and effectively avoiding resource waste and decision-making mistakes caused by incomplete or deviated data.

[0049] In the present invention, through the intelligent decision-making module using the multi-objective optimization algorithm, according to the sensitivity level, the recommended irrigation intensity, the farmland zoning requirements and the water resource supply situation, the regional irrigation priority, water volume allocation and irrigation time period are dynamically generated, comprehensively optimizing the spatial and temporal distribution of irrigation resources. By scientifically integrating multi-dimensional data, the system can provide differentiated irrigation strategies for different regions and crop types, effectively improving the water resource utilization efficiency, while ensuring the healthy growth and high yield of crops.

[0050] In the present invention, through the PID controller, the accurate execution of the irrigation strategy is realized, dynamically controlling the start and stop of the water pump, the valve opening and the pipe network flow rate, ensuring that the irrigation requirements of each region are quickly responded to, continuously monitoring the equipment operation and irrigation effect, and dynamically adjusting the strategy parameters, further improving the stability and intelligent level of the irrigation system, and achieving the dual goals of water saving and crop yield increase. Brief Description of the Drawings

[0051] 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 embodiments or the description of 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.

[0052] Figure 1 It is a schematic diagram of the system function module of the embodiment of the present invention;

[0053] Figure 2 It is a schematic diagram of the crop irrigation sensitivity adaptive adjustment module of the embodiment of the present invention. Detailed Embodiments

[0054] The following will describe the present invention in detail in combination with the 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; and the drawings part is only for more specific description of the embodiments, and is not intended to specifically limit the present invention.

[0055] It should be noted that in the specification, references to "an embodiment", "embodiments", "exemplary embodiments", "some embodiments", etc. indicate that the described embodiments may include specific features, structures, or characteristics, but not every embodiment necessarily includes that specific feature, structure, or characteristic. Additionally, when describing a specific feature, structure, or characteristic in connection with an embodiment, implementing such feature, structure, or characteristic in connection with other embodiments (whether explicitly described or not) should be within the knowledge of those skilled in the relevant art.

[0056] Generally, terms can be understood at least in part from their use in context. For example, at least in part depending on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in a singular sense, or can be used to describe a combination of features, structures, or characteristics in a plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey a set of exclusive factors, but rather, at least in part depending on the context, can allow for the existence of other factors that may not be explicitly described.

[0057] As Figure 1 - Figure 2 shown, an Internet of Things-based farmland water-saving adaptive irrigation system includes a data acquisition module, a crop irrigation sensitivity adaptive adjustment module, an intelligent decision-making module, and an intelligent control module, wherein;

[0058] The data acquisition module collects environmental data of farmland soil in real time, including soil humidity, air temperature, air humidity, and light intensity;

[0059] The crop irrigation sensitivity adaptive adjustment module collects physiological state data of crops, including crop canopy temperature, leaf area index, and leaf water content, combines the collected environmental data, evaluates the irrigation sensitivity of crops at the current growth stage in real time, and outputs the sensitivity level and recommended irrigation intensity;

[0060] The intelligent decision-making module generates an irrigation strategy based on the output sensitivity level and recommended irrigation intensity, combines the farmland area zoning requirements and water resource supply situation, and generates an irrigation strategy through a multi-objective optimization algorithm, including regional irrigation priority, irrigation water volume allocation, and irrigation time period;

[0061] The intelligent control module executes the irrigation strategy and controls the pumps, valves, and pipe network flow rates of the irrigation system;

[0062] Through the above content, the real-time collection of environmental data and crop physiological state data, dynamic irrigation sensitivity evaluation, multi-objective optimization decision-making, and precise control are organically combined, which can dynamically adjust the irrigation strategy according to actual needs, effectively improve the water resource utilization efficiency, ensure the healthy growth of crops, and meet the irrigation needs of different regions and crop types.

[0063] The data acquisition module includes:

[0064] Soil moisture data collection: Equipped with soil moisture sensors, buried at different depths and regions in the farmland to monitor the water content of the soil in real time;

[0065] Air temperature and humidity data collection: Deploy environmental temperature and humidity sensors in the farmland to monitor air temperature and humidity in real time;

[0066] Light intensity data collection: Install light intensity sensors in the farmland to capture the changes in farmland light intensity in real time;

[0067] Through the above content, key environmental data such as soil moisture, air temperature and humidity, and light intensity are accurately collected, which can comprehensively reflect the dynamic changes of the farmland environment, support precise and intelligent irrigation decisions, effectively improve the water resource utilization efficiency, meet the growth needs of crops, and achieve the dual goals of water conservation and high yield.

[0068] The crop irrigation sensitivity adaptive adjustment module includes:

[0069] Crop physiological state data collection: Collect crop physiological state data, including crop canopy temperature, leaf area index, and leaf water content;

[0070] Data preprocessing: Preprocess the collected environmental data and crop physiological state data, including noise filtering, missing value filling, and normalization processing;

[0071] Sensitivity assessment: Based on the preprocessed environmental data and crop physiological state data, use a sensitivity assessment model to evaluate the irrigation sensitivity of the crop at the current growth stage, and output the sensitivity level of the crop, including low sensitivity, medium sensitivity, and high sensitivity;

[0072] Irrigation intensity recommendation: Give corresponding irrigation intensity recommendations according to different sensitivity levels;

[0073] Through the above content, the dynamic analysis and classification of the irrigation requirements of crops at different growth stages are realized. Precise irrigation intensity recommendations can be provided according to the sensitivity level, combining the real-time state of the crops with environmental changes, greatly improving the scientificity and precision of irrigation decisions, significantly reducing water resource waste, and at the same time ensuring the healthy growth of crops and yield optimization.

[0074] Crop physiological state data collection includes:

[0075] Crop canopy temperature collection: Through a non-contact infrared temperature sensor installed in the farmland, monitor the temperature changes of the crop canopy in real time;

[0076] Leaf area index collection: By deploying a laser scanning system, obtain the image data of crop leaves and calculate the leaf area index LAI, expressed as:

[0077]

[0078] Among them, LAI is the leaf area index, I is the light intensity penetrating (the light intensity after passing through the crop canopy), I 0 is the incident light intensity (the light intensity before passing through the crop canopy), and k is the light interception factor;

[0079] Collection of leaf water content: Using a non-contact spectral sensor, by measuring the water absorption spectral characteristics of the leaves, the water content index of the crop leaves is calculated in real time, expressed as:

[0080]

[0081] Among them, WX is the leaf water content, A(λ 1 ) is the absorbance of the leaf in the water absorption band (such as 970 nm), and A(λ 2 ) is the absorbance of the leaf in the non-absorption band (such as 900 nm);

[0082] Through the above content, key physiological data such as crop canopy temperature, leaf area index, and leaf water content can be accurately obtained, which can reflect the health status and dynamic water demand of crops in real time. Combining environmental data provides scientific support for irrigation sensitivity assessment, thereby realizing more accurate irrigation decisions and improving water resource utilization efficiency and crop growth effects.

[0083] Data preprocessing includes:

[0084] Noise filtering: The sliding average method is used to filter the noise of the collected environmental data and crop physiological state data, expressed as:

[0085]

[0086] Among them, x'(t) is the smoothed value at time point t, x(t-i) is the original value at time point t-i, and l is the size of the sliding window;

[0087] Missing value filling: The linear interpolation method is used to fill the missing values in the collected environmental data and crop physiological state data, expressed as:

[0088]

[0089] Among them, t 1 ,t 2 are the time points of adjacent valid data, x(t 1 ),x(t 2 ) are the corresponding valid data values, and x(t) is the interpolation result of the missing point t;

[0090] Normalization: Normalize the environmental data and crop physiological state data in different dimensions, map the data to the interval [0, 1], and ensure the scale consistency of various data, which is expressed as:

[0091]

[0092] Among them, x norm is the normalized data value, x is the original data value, x min , x max are the minimum and maximum values of the data respectively;

[0093] Through the above content, the accuracy, integrity, and consistency of the environmental data and crop physiological state data are effectively improved, the abnormal fluctuations and missing problems in the data can be eliminated, the subsequent analysis distortion caused by data deviation or inconsistency can be avoided, and the scientific analysis of different-dimensional data on the same scale can be ensured, providing high-quality input for the irrigation sensitivity assessment, thereby improving the intelligent level of the system and the accuracy of irrigation decision-making.

[0094] The sensitivity assessment model uses a Bayesian network model, and the Bayesian network model includes:

[0095] Construct a Bayesian network structure: Establish a network structure based on the crop physiological state data and environmental data, define the conditional dependence relationship between variables, and the Bayesian network is represented as a directed acyclic graph (DAG), which is composed of nodes and edges, and is expressed as:

[0096]

[0097] Among them, X is the set of all variables, P(X i |Pa(X i )) is the conditional probability of variable X i under the condition that its parent node Pa(X i ) is given, and n is the total number of variables;

[0098] Quantify the conditional probability distribution: Assign a conditional probability table (CPT) to each node, and statistically analyze the conditional probability distribution of each variable according to the historical crop physiological state data and environmental data, which is expressed as:

[0099] P(S|E 1 , E 2 ,..., E m ) = P(E 1 , E 2 ,..., E m )·P(S);

[0100] Among them, S is the target variable (crop irrigation sensitivity), E 1 , E 2,...,E m Is a set of crop physiological state data and environmental data, P(E 1 ,E 2 ,...,E m |S) is the conditional probability distribution of the input data under the sensitivity S, and P(S) is the prior probability of the sensitivity;

[0101] Input data instantiation: Using the real-time collected crop physiological state data and environmental data as input to instantiate the network nodes. Each input variable E i Is represented as: E i = Acquisition value;

[0102] Sensitivity probability inference: According to the conditional probability table in the Bayesian network and combined with the instantiated input data, infer the posterior probability of the crop irrigation sensitivity, which is represented as:

[0103]

[0104] P(E) = ∑ S P(E∣S)·P(S);

[0105] Among them, P(S|E) is the posterior probability of the sensitivity S under the given input data E, P(E|S) is the joint probability of the input data under the sensitivity S, P(S) is the prior probability of the sensitivity, P(E) is the total probability of the input data (normalization factor), P(E i |S) is the conditional probability of a single input data variable E i under the sensitivity S, and m is the total number of input data variables;

[0106] Output sensitivity level: According to the calculated posterior probability, select the level with the highest sensitivity probability as the final evaluation result S of the sensitivity level * , when S * < 0.3, it is low sensitivity. When 0.3 ≤ S * < 0.6, it is medium sensitivity. When S * ≥ 0.6, it is high sensitivity, which is represented as:

[0107] S * = argmax S P(S|E);

[0108] Among them, S * is the final evaluation result of the sensitivity level, and P(S|E) is the posterior probability of each sensitivity level;

[0109] Through the above, it is possible to efficiently evaluate the irrigation sensitivity of crops at different growth stages, use posterior probability calculation combined with threshold division to classify the sensitivity levels, possess strong uncertainty processing capabilities and flexible dynamic decision-making capabilities. Through intuitive probability inference, the Bayesian network can integrate multi-dimensional data and accurately evaluate the water requirements of crops, support the formulation of precise irrigation strategies, thereby achieving efficient utilization of water resources, while ensuring the healthy growth and high yield of crops.

[0110] Irrigation intensity recommendations include:

[0111] Irrigation intensity recommendation for low sensitivity level: When the sensitivity level of the crop is low sensitivity, it is recommended to keep the irrigation operation suspended to reduce water resource waste;

[0112] Irrigation intensity recommendation for medium sensitivity level: When the sensitivity level of the crop is medium sensitivity, it is recommended to maintain the current irrigation time and irrigation water volume to ensure meeting the growth needs of the crop while avoiding over-irrigation;

[0113] Irrigation intensity recommendation for high sensitivity level: When the sensitivity level of the crop is high sensitivity, give priority to water resource allocation. It is recommended to shorten the irrigation interval and increase the single irrigation water volume to ensure that the water requirements of the crop can be met in a timely manner;

[0114] Through the above, it is possible to effectively match the actual water demand of the crop, suspend irrigation at low sensitivity to reduce water resource waste, maintain appropriate irrigation at medium sensitivity to ensure the normal growth of the crop, and give priority to water resource allocation at high sensitivity to meet emergency needs, achieving precise and differentiated irrigation decisions, significantly improving the water resource utilization efficiency, while ensuring the healthy growth and yield optimization of the crop.

[0115] The intelligent decision-making module includes:

[0116] Calculation of regional irrigation priority: According to the sensitivity level S * and weight factor of each region, calculate the priority P i of each partition, expressed as:

[0117]

[0118] where Pi 为 is the irrigation priority of the i-th region, is the sensitivity level of the i-th region, and w i is the weight factor of the i-th region;

[0119] Optimization of water resource allocation: Based on the limited water resource W total , combined with the priority P i of each region and the water demand W i, optimize the allocation of water resources with the goal of maximizing irrigation benefits, expressed as:

[0120] Objective function:

[0121] Constraints:

[0122]

[0123] W i ≥W min,i ,W i ≤W max,i ;

[0124] where p is the total number of farmland partitions, W total is the total water resource supply, W min,i, and W max,i are the minimum and maximum irrigation amounts in the i-th area respectively;

[0125] Irrigation period planning: Combine environmental data to select the irrigation time period to avoid water waste caused by high-temperature evaporation, expressed as:

[0126] T i = argmin t (E t ·W i );

[0127] where E t is the environmental data at time period t, W i is the water demand in the i-th area, and T i is the optimal irrigation period in the i-th area;

[0128] E t = w L ·L t + w T ·T t + w H ·H t + w s ·S t ;

[0129] where w L , w T , w H , w s are the weight factors of light intensity, air temperature, air humidity, and soil humidity respectively, and L t , T t , H t , S t are the normalized data of light intensity, air temperature, air humidity, and soil humidity within time period t respectively;

[0130] Through the above, by integrating the sensitivity level, recommended irrigation intensity, farmland area zoning requirements, and water resource supply status, and combining with the multi-objective optimization algorithm to dynamically generate irrigation strategies, including regional priorities, water volume allocation, and irrigation time periods, the scientific integration and optimization of multi-dimensional data are achieved, ensuring the accurate and reasonable allocation of water resources. At the same time, by selecting the best irrigation time period, the water resource utilization efficiency is maximized, the differentiated needs of crops are met, and the intelligent level and practicality of the water-saving irrigation system are effectively improved.

[0131] The intelligent control module includes:

[0132] Irrigation strategy analysis and instruction generation: Receive the irrigation strategy output by the intelligent decision-making module, including regional irrigation priorities, irrigation water volume, and irrigation time periods, generate device control instructions through a PID controller, and generate corresponding water pump start-up, valve opening, and pipe network flow regulation instructions;

[0133] Water pump control: According to the irrigation area and water volume requirements in the irrigation strategy, control the start-stop and flow regulation of the corresponding water pumps to ensure that the irrigation area obtains sufficient water sources while avoiding water resource waste;

[0134] Valve control: Regulate the electric valves in the irrigation area, dynamically adjust the opening time and opening degree of the valves according to regional priorities and irrigation time periods, accurately allocate irrigation water flow, and meet the requirements of multi-region collaborative irrigation;

[0135] Pipe network flow monitoring and regulation: Real-time monitor the water flow and pressure of the pipe network, and maintain the water supply flow by adjusting the flow control valve or pipe splitter to avoid a decrease in irrigation efficiency caused by flow fluctuations or uneven pressure;

[0136] Through the above, the accurate conversion from strategy to device operation is achieved. By using a PID controller to dynamically generate device instructions, the accurate adjustment of water pump start-stop, valve opening degree, and pipe network flow is ensured, effectively matching the regional irrigation requirements, improving the response speed and execution accuracy of irrigation operations, avoiding resource waste and equipment overload, and significantly enhancing the stability, intelligent level, and water resource utilization efficiency of the irrigation system.

[0137] This invention covers any substitutions, modifications, equivalent methods, and solutions made within the essence and scope of this invention. For the public to have a thorough understanding of this invention, specific details are described in detail in the following preferred embodiments of this invention. However, those skilled in the art can fully understand this invention without the description of these details. Additionally, to avoid unnecessary confusion to the essence of this invention, well-known methods, processes, procedures, components, and circuits are not described in detail.

[0138] 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. A farmland water-saving adaptive irrigation system based on the Internet of Things, characterized in that: It includes data acquisition module, crop irrigation sensitivity adaptive adjustment module, intelligent decision-making module and intelligent control module, among which; The data acquisition module collects farmland soil environmental data in real time, including soil moisture, air temperature, air humidity and light intensity; The crop irrigation sensitivity adaptive adjustment module collects crop physiological status data, including crop canopy temperature, leaf area index, and leaf water content, and combines the collected environmental data to evaluate the irrigation sensitivity of the crop at the current growth stage in real time, and outputs the sensitivity level and recommended irrigation intensity; The intelligent decision-making module generates an irrigation strategy, including regional irrigation priority, irrigation water allocation and irrigation period, through a multi-objective optimization algorithm based on the output sensitivity level and recommended irrigation intensity, combined with the farmland regional zoning requirements and water resource supply conditions; The intelligent control module executes the irrigation strategy and controls the water pumps, valves and pipe network flow of the irrigation system.

2. The farmland water-saving adaptive irrigation system based on the Internet of Things according to claim 1 is characterized in that: The data acquisition module comprises: Soil moisture data collection: Equipped with soil moisture sensors, buried at different depths and areas of farmland to monitor soil moisture content in real time; Air temperature and humidity data collection: Deploy environmental temperature and humidity sensors in farmland to monitor air temperature and humidity in real time; Light intensity data collection: Install light intensity sensors in farmland to capture changes in farmland light in real time.

3. The farmland water-saving adaptive irrigation system based on the Internet of Things according to claim 1 is characterized in that: The crop irrigation sensitivity adaptive adjustment module comprises: Crop physiological status data collection: Collect crop physiological status data, including crop canopy temperature, leaf area index and leaf water content; Data preprocessing: preprocess the collected environmental data and crop physiological status data, including noise filtering, missing value filling and normalization; Sensitivity assessment: Based on the pre-processed environmental data and crop physiological status data, the sensitivity assessment model is used to assess the irrigation sensitivity of crops at the current growth stage, and the crop sensitivity level is output, including low sensitivity, medium sensitivity and high sensitivity; Irrigation intensity recommendations: Corresponding irrigation intensity recommendations are given based on different sensitivity levels.

4. The farmland water-saving adaptive irrigation system based on the Internet of Things according to claim 3 is characterized in that: The crop physiological status data collection includes: Crop canopy temperature collection: non-contact infrared temperature sensors installed in farmland monitor crop canopy temperature changes in real time; Leaf area index collection: by deploying a laser scanning system, we can obtain image data of crop leaves and calculate the leaf area index LAI; Leaf moisture content collection: Use a non-contact spectral sensor to measure the water absorption spectral characteristics of the leaves and calculate the moisture content index of crop leaves in real time.

5. The farmland water-saving adaptive irrigation system based on the Internet of Things according to claim 4 is characterized in that: The data preprocessing includes: Noise filtering: Use the sliding average method to filter the noise of the collected environmental data and crop physiological status data; Missing value filling: Linear interpolation is used to fill missing values ​​in the collected environmental data and crop physiological status data; Normalization processing: Normalize environmental data and crop physiological status data of different dimensions.

6. The farmland water-saving adaptive irrigation system based on the Internet of Things according to claim 5 is characterized in that: The sensitivity assessment model adopts a Bayesian network model, and the Bayesian network model includes: Constructing Bayesian network structure: Building a network structure based on crop physiological status data and environmental data, defining the conditional dependency relationship between variables, and the Bayesian network is represented as a directed acyclic graph consisting of nodes and edges; Quantified conditional probability distribution: Assign a conditional probability table to each node, and calculate the conditional probability distribution of each variable based on historical crop physiological status data and environmental data; Input data instantiation: Take the crop physiological status data and environmental data collected in real time as input, instantiate the network nodes, and each input variable E i Expressed as: E i =collected value; Sensitivity probability inference: Based on the conditional probability table in the Bayesian network and the instantiated input data, the posterior probability of crop irrigation sensitivity is inferred; Output sensitivity level: According to the calculated posterior probability, select the level with the highest sensitivity probability as the final evaluation result S of the sensitivity level * , when S * <0.3, it is low sensitivity. * <0.6, it is medium sensitivity. * When ≥0.6, it is highly sensitive.

7. The farmland water-saving adaptive irrigation system based on the Internet of Things according to claim 6 is characterized in that: The irrigation intensity recommendations include: Irrigation intensity recommendations for low sensitivity levels: When the sensitivity level of the crop is low sensitivity, it is recommended to keep the irrigation operation suspended; Irrigation intensity recommendations for medium sensitivity levels: When the sensitivity level of the plant is medium, it is recommended to maintain the current irrigation time and irrigation water volume; Irrigation intensity recommendations for high sensitivity levels: When the sensitivity level of a crop is high, water resources should be allocated first. It is recommended to shorten the irrigation interval and increase the amount of water for a single irrigation.

8. The farmland water-saving adaptive irrigation system based on the Internet of Things according to claim 7 is characterized in that: The intelligent decision-making module includes: Regional irrigation priority calculation: According to the sensitivity level S of each area * And weight factor, calculate the priority P of each partition i ; Water resource allocation optimization: Based on limited water resources W total , combined with the priority P of each area i and water demand W i , optimize the allocation of water resources with the goal of maximizing irrigation benefits; Irrigation period planning: Select the irrigation time period based on environmental data.

9. The farmland water-saving adaptive irrigation system based on the Internet of Things according to claim 1, characterized in that: The intelligent control module comprises: Irrigation strategy analysis and instruction generation: Receive the irrigation strategy output by the intelligent decision-making module, including regional irrigation priority, irrigation water volume and irrigation period, generate equipment control instructions through the PID controller, and generate corresponding water pump start, valve opening and pipe network flow adjustment instructions; Water pump control: Control the start and stop of the corresponding water pump and adjust the flow rate according to the irrigation area and water demand in the irrigation strategy; Valve control: regulate the electric valves in the irrigation area and dynamically adjust the valve opening time and opening degree according to the area priority and irrigation period; Pipeline network flow monitoring and regulation: Real-time monitoring of water flow and pressure in the pipeline network, and maintaining water supply flow by adjusting flow control valves or pipeline diverters.

Images