Corn and soybean strip-shaped composite planting intelligent irrigation system based on Internet of Things

Abstract

The invention provides a corn and soybean strip-shaped composite planting intelligent irrigation system based on the Internet of Things. The system comprises a root system soil sensing module; the atmosphere monitoring module is used for collecting weather data; a time module; the decision generation module generates an irrigation strategy by using an algorithm; and the execution module provides key data for irrigation decisions. The root health monitoring unit collects root density, oxygen data and soil conductivity, calculates a root health index by using an algorithm, and evaluates the root health of crops. The root system growth direction recognition unit obtains a root system three-dimensional panoramic image, generates a thermodynamic diagram and provides visual information for an irrigation strategy. The decision-making module makes an irrigation strategy by using multi-dimensional data and an algorithm, and the execution module ensures that the strategy is implemented through control equipment. By combining humidity monitoring, root health detection and growth direction recognition technologies, precise and intelligent irrigation of the corn and soybean planting area is realized, the irrigation precision and efficiency are improved, meanwhile, health of crop roots is guaranteed, and growth is promoted.

Description

Technical Field

[0001] The present invention relates to the technical field of crop irrigation, and in particular to an intelligent irrigation system for corn and soybean strip composite planting based on the Internet of Things. Background Art

[0002] In agricultural production, irrigation is crucial for ensuring crop growth and food security. Effective irrigation not only significantly improves crop yield and quality but also optimizes water resource utilization. Irrigation is the lifeline of agricultural production, particularly in arid and semi-arid regions. Corn and soybeans, as important food and cash crops, are extremely sensitive to water demands for growth and development. Therefore, precision irrigation is crucial for improving the profitability of corn and soybean strip plantings.

[0003] However, traditional irrigation methods have numerous limitations and are unable to meet the precision irrigation demands of modern agriculture. Traditional irrigation relies primarily on farmers' experience and judgment, manually observing soil moisture, weather conditions, and other factors to determine irrigation parameters such as water volume and frequency. This method is subject to significant subjectivity, lacks real-time performance, and suffers from low accuracy. This can easily lead to over- or under-irrigation, wasting precious water resources and negatively impacting crop growth. For example, over-irrigation can lead to soil salinization and root hypoxia, while under-irrigation can cause drought stress in crops, impacting yield and quality. Furthermore, traditional irrigation methods are complex and labor-intensive to manage. For large-scale farmland, manual management struggles to achieve comprehensive and precise management, resulting in low irrigation efficiency and significant water waste. Furthermore, with the increasing problem of water scarcity, traditional irrigation methods are no longer able to meet the demands of sustainable modern agriculture. Summary of the Invention

[0004] The present invention aims to at least solve the technical problem of low irrigation precision in the prior art, and particularly innovatively proposes an intelligent irrigation system for corn and soybean strip composite planting based on the Internet of Things.

[0005] In order to achieve the above-mentioned object of the present invention, the present invention provides an intelligent irrigation system for corn and soybean strip composite planting based on the Internet of Things, the system comprising:

[0006] The root soil sensing module is installed at the root system of crops to collect moisture data, root health index and root growth direction data, including a three-dimensional thermal map of the root system;

[0007] Atmospheric monitoring module, used to collect weather data;

[0008] Time module, used to provide current time information;

[0009] a decision generation module, in communication with the root soil sensing module, the time module, and the atmosphere monitoring module, for generating an irrigation strategy using a multi-objective optimization algorithm based on the weather data, humidity data, root health index, and root growth direction data;

[0010] The execution module is connected to the decision-making module and the time module, and is used to perform timed, quantitative and directional irrigation on crops according to the irrigation strategy.

[0011] As an optional embodiment of the present invention, optionally, the root soil sensing module includes:

[0012] Humidity collection unit, used for collecting humidity data;

[0013] a root health monitoring unit for collecting root density data, oxygen data around the roots, and soil conductivity data, and calculating a root health index based on the density data, oxygen data around the roots, and soil conductivity data using a root health assessment algorithm;

[0014] The root growth direction identification unit uses a rotating probe and multi-band radar wave detection method to obtain panoramic images of the root system in different frequency bands in three-dimensional space and generate a three-dimensional thermal map of the root system.

[0015] As an optional embodiment of the present invention, optionally, generating a three-dimensional root system heat map using a root system growth direction identification unit includes:

[0016] Set the radar frequency range, set different frequencies based on the frequency range, perform circular scanning, arc scanning, and parallel linear scanning on the root system to obtain root reflection signals at different depths;

[0017] The root system is scanned panoramically using a rotating probe to obtain a panoramic image of the root system in three-dimensional space;

[0018] Mapping the root system reflection signals onto the panoramic image in a one-to-one correspondence to obtain a root system distribution map of the root system in three-dimensional space;

[0019] The panoramic image and the root reflection signal in the root distribution map are fused, and the soil particle interference in the panoramic image is removed by using a median filter algorithm, and the root reflection signal is denoised by using a wavelet transform to retain the root reflection characteristic peak;

[0020] The root distribution map is processed using the structure-from-motion algorithm to generate a point cloud of the root surface and construct a three-dimensional root model.

[0021] Calculating the root system spatial coordinates based on the root system three-dimensional model radar reflection time difference;

[0022] Setting output pixels based on the root surface point cloud and the root space coordinates, and performing kernel density analysis with adaptive bandwidth to generate two-dimensional heat maps of different frequency bands;

[0023] The two-dimensional heat maps of different frequency bands were imported into three-dimensional visualization software to set the basic height threshold of the surface point cloud, and color gradient mapping was used to display the root distribution to generate a three-dimensional heat map of the root system.

[0024] As an optional embodiment of the present invention, optionally, the decision generation module includes:

[0025] Irrigation rule library, which includes pre-set irrigation rules;

[0026] A preprocessing unit, configured to perform spatiotemporal alignment and standardization operations on the weather data, humidity data, root health index, and root three-dimensional thermal map;

[0027] a rule matching unit connected to the preprocessing unit and the irrigation rule base, for matching the preprocessed weather data, humidity data, root health index, and root three-dimensional thermal map with the rules in the irrigation rule base, calculating the rule confidence using a forward reasoning mechanism, and selecting irrigation rules based on a conflict resolution strategy;

[0028] a multi-objective optimization unit connected to the rule matching unit, and optimizing the matched irrigation rules using a multi-objective optimization algorithm to generate an irrigation strategy, wherein the multi-objective optimization algorithm aims to minimize water resource consumption, health risks, and maximize irrigation efficiency, and considers constraints such as post-irrigation humidity, single irrigation amount, and irrigation period;

[0029] The feedback optimization unit is connected to the multi-objective optimization unit and the execution module, and is used to receive the irrigation effect data fed back by the execution module, optimize and adjust the rule weights in the irrigation rule library according to the irrigation effect data, and update the parameters of the multi-objective optimization algorithm.

[0030] As an optional embodiment of the present invention, optionally, the rule matching unit selects the irrigation rule including:

[0031] Extracting key features of the root system based on the three-dimensional heat map;

[0032] Based on the current weather data, humidity data, root health index and root key characteristics, the irrigation rules in the irrigation rule library are matched to obtain a rule set;

[0033] respectively calculating the priorities of the weather data, humidity data, root health index and key root characteristics;

[0034] Calculating the rule confidence of each rule in the rule set using a conflict algorithm;

[0035] Sort the rule set based on rule confidence and priority, and select the irrigation rule with the highest rule confidence and priority as the irrigation rule;

[0036] If two or more rules have the same confidence and priority, they are screened based on the historical execution effects of the rules and the growth of crops after irrigation.

[0037] As an optional embodiment of the present invention, optionally, the execution module includes:

[0038] an irrigation strategy parsing unit, configured to parse the irrigation strategy and obtain irrigation parameters, wherein the irrigation parameters include irrigation amount, irrigation frequency, irrigation direction, and irrigation period;

[0039] an irrigation equipment control unit, connected to the irrigation strategy analysis unit, and configured to control the operation of the irrigation equipment according to the irrigation parameters;

[0040] The irrigation effect monitoring unit is connected to the irrigation equipment control unit and is used to monitor the root soil moisture, root health index and root growth of crops after irrigation, and feed the monitoring data back to the feedback optimization unit in the decision generation module.

[0041] As an optional embodiment of the present invention, optionally, the system also includes a user interaction interface, which is connected to the decision generation module and the execution module, and is used to display irrigation strategies, irrigation parameters and irrigation effect data, and receive irrigation instructions and parameter adjustment instructions input by the user.

[0042] The present invention has the following beneficial effects: Through the humidity acquisition unit, the system can obtain real-time soil moisture information, providing critical data support for irrigation decision-making. The root health monitoring unit collects root density, oxygen levels around the roots, and soil electrical conductivity data, and uses a root health assessment algorithm to calculate a root health index, thereby accurately assessing the health of crop roots. Furthermore, the root growth direction identification unit captures a panoramic image of the root system in three-dimensional space and generates a three-dimensional root heat map, providing more intuitive root distribution information for irrigation strategy formulation. Based on this multi-dimensional data, the decision generation module uses a series of complex algorithms and optimization processes to ultimately generate a scientific and reasonable irrigation strategy. The execution module is responsible for analyzing the irrigation strategy and controlling the operation of irrigation equipment to ensure its effective implementation. Therefore, by integrating advanced technologies such as humidity acquisition, root health monitoring, and root growth direction identification, the present invention achieves precise and intelligent irrigation management for corn and soybean strip planting areas, improving irrigation accuracy. This system not only improves irrigation efficiency but also ensures the health of crop roots, promoting crop growth and development.

[0043] Additional aspects and advantages of the present invention will be set forth in part in the description which follows and, in part, will be obvious from the description which follows, or may be learned by practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the following description of the embodiments with reference to the accompanying drawings, in which:

[0045] Figure 1 The present invention is a structural schematic diagram of an intelligent irrigation system for corn and soybean strip composite planting based on the Internet of Things. DETAILED DESCRIPTION

[0046] The following describes embodiments of the present invention in detail. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended only to explain the present invention and are not to be construed as limiting the present invention.

[0047] like Figure 1 As shown, an intelligent irrigation system for corn and soybean strip composite planting based on the Internet of Things, the system includes:

[0048] The root soil sensing module is installed at the root system of crops to collect moisture data, root health index and root growth direction data, including a three-dimensional thermal map of the root system;

[0049] It should be noted that the root soil sensing module includes a humidity collection unit, a root health monitoring unit, and a root growth direction identification unit. The humidity collection unit is used to obtain soil moisture information in real time. Specifically, the humidity collection unit realizes real-time monitoring of soil moisture by setting humidity sensors around the roots of crops. The root health monitoring unit collects data such as root density, oxygen concentration around the roots, and soil conductivity, and uses a preset root health assessment algorithm to calculate the root health index, thereby accurately assessing the health status of the crop roots. The root growth direction identification unit obtains a panoramic image of the root system in three-dimensional space, and uses image processing technology and three-dimensional modeling technology to generate a three-dimensional heat map of the root system, which intuitively displays the distribution of the root system in the soil and provides an important reference for the subsequent formulation of irrigation strategies.

[0050] Atmospheric monitoring module, used to collect weather data;

[0051] It should be noted that in this embodiment, the atmospheric monitoring module obtains real-time weather data for the current and future period of time, including but not limited to temperature, humidity, precipitation, wind speed, etc., by interacting with the weather forecast system or weather station.

[0052] Time module, used to provide current time information;

[0053] It should be noted that the time module is a clock module, which is used to record and provide current time information to ensure that the formulation and implementation of irrigation strategies can be based on accurate time points.

[0054] a decision generation module, in communication with the root soil sensing module, the time module, and the atmosphere monitoring module, for generating an irrigation strategy using a multi-objective optimization algorithm based on the weather data, humidity data, root health index, and root growth direction data;

[0055] It should be noted that the decision-making module includes irrigation rules, a rule matching unit, a feedback optimization unit, and a strategy optimization unit. The irrigation rules store a series of preset irrigation rules based on factors such as crop growth needs, weather conditions, soil moisture, and root health. The rule matching unit is responsible for intelligently matching the relevant rules in the irrigation rule library based on real-time weather data, humidity data, root health index, and root three-dimensional heat map information to form a preliminary rule set. The strategy optimization unit further combines the multi-objective optimization algorithm to comprehensively consider multiple objectives such as water resource consumption, crop health risks, and irrigation efficiency, optimizes the initially formed irrigation strategy, and generates the final irrigation strategy plan. The feedback optimization unit continuously optimizes and adjusts the rule weights in the irrigation rule library based on historical irrigation results and crop growth feedback to ensure the scientific nature and effectiveness of the irrigation strategy.

[0056] The execution module is connected to the decision-making module and the time module, and is used to perform timed, quantitative and directional irrigation on crops according to the irrigation strategy.

[0057] It should be noted that the execution module includes an irrigation strategy parsing unit, an irrigation equipment control unit, and an irrigation effect monitoring unit. The irrigation strategy parsing unit is responsible for parsing the irrigation strategy from the decision generation module and extracting specific irrigation parameters, such as irrigation volume, irrigation frequency, irrigation direction, and irrigation period. The irrigation equipment control unit precisely controls the operation of the irrigation equipment based on the parameters provided by the irrigation strategy parsing unit, ensuring that irrigation operations are carried out according to the preset strategy. The irrigation effect monitoring unit is responsible for real-time monitoring of the root soil moisture, root health index, and root growth of crops after irrigation is completed, and promptly feeds the monitoring data back to the feedback optimization unit in the decision generation module to further optimize and adjust the irrigation strategy.

[0058] When the corn and soybean strip composite planting intelligent irrigation system based on the Internet of Things of the present embodiment is used, the root soil moisture, root health index and root growth direction data of the crops are first collected in real time through the root soil sensing module. These data are obtained through high-precision sensors and advanced image processing technology. Subsequently, the atmospheric monitoring module obtains the current weather data in real time, including key information such as temperature, humidity, and precipitation. The time module provides accurate time information to ensure that the irrigation operation can be carried out at the most appropriate time point. After the decision generation module receives this data (root soil moisture, weather data, root health index and root growth direction data), it will immediately start the multi-objective optimization algorithm, comprehensively considering multiple factors such as weather conditions, soil moisture, root health status and irrigation efficiency, and intelligently generate the optimal irrigation strategy. This strategy not only takes into account the actual needs of the crops, but also fully takes into account the rational use of water resources and the requirements of environmental protection.

[0059] After receiving an irrigation instruction, the execution module first analyzes the irrigation strategy through the irrigation strategy analysis unit, extracting key irrigation parameters such as irrigation volume, frequency, direction, and time period. Subsequently, the irrigation equipment control unit precisely controls the opening and closing of the irrigation equipment and the irrigation volume based on the analyzed irrigation parameters, ensuring that irrigation operations are carried out according to the preset strategy. During the irrigation process, the irrigation equipment irrigates the crops at the specified frequency and direction, ensuring that every patch of soil receives sufficient water. Simultaneously, the irrigation effect monitoring unit monitors soil moisture, root health index, and root growth in real time after irrigation, and promptly feeds this data back to the feedback optimization unit in the decision generation module. The feedback optimization unit further optimizes and adjusts the irrigation strategy based on this real-time monitoring data, ensuring that the irrigation strategy remains synchronized with the actual needs of the crops. Through this complete intelligent irrigation system, the present invention achieves precise irrigation management for corn and soybean strip planting areas, improving irrigation efficiency and accuracy while ensuring healthy root growth, laying a solid foundation for a good harvest.

[0060] As an optional embodiment of the present invention, optionally, the root soil sensing module includes:

[0061] Humidity collection unit, used for collecting humidity data;

[0062] It should be noted that, in this embodiment, the humidity collection unit is a humidity sensor installed around the root system, which can sense the moisture content in the soil in real time and convert the collected humidity data into an electrical signal for transmission.

[0063] a root health monitoring unit for collecting root density data, oxygen data around the roots, and soil conductivity data, and calculating a root health index based on the density data, oxygen data around the roots, and soil conductivity data using a root health assessment algorithm;

[0064] It should be noted that the root health monitoring unit specifically collects data such as root density, oxygen concentration around the roots, and soil conductivity through multiple sensors. These data are key factors in evaluating the health of the root system. In this embodiment, 10 to 20 sensors are installed per acre when the sensors are installed. The root density data reflects the degree of development of the crop root system, while the oxygen concentration around the roots directly affects the respiration and growth of the roots. The soil conductivity data can indirectly reflect the salt content and fertility status of the soil, which is of great significance for evaluating the impact of the soil environment on root health. The collected data are sent to a preset root health assessment algorithm for processing. The algorithm comprehensively considers multiple factors such as root density, oxygen concentration, and conductivity, and finally obtains the root health index through calculation and analysis.

[0065] The root growth direction identification unit uses a rotating probe and multi-band radar wave detection method to obtain panoramic images of the root system in different frequency bands in three-dimensional space and generate a three-dimensional thermal map of the root system.

[0066] It should be noted that the root growth direction identification unit specifically rotates in the soil through a rotating probe, while emitting multi-band radar waves, which can penetrate the soil and be reflected back by the roots. By receiving and analyzing the reflected radar wave signals, the root growth direction identification unit can obtain a panoramic image of the root system in three-dimensional space. Subsequently, using advanced image processing technology and three-dimensional modeling algorithms, these image data are converted into an intuitive three-dimensional heat map of the root system. In the heat map, different colors represent different densities and distributions of the roots, allowing users to clearly see the growth direction and distribution of the roots in the soil, so that irrigation can be more accurately targeted to the needs of the crop roots.

[0067] As an optional embodiment of the present invention, optionally, the root health assessment algorithm is expressed as:

[0068]

[0069] Wherein, HI represents the root health index;

[0070] w1 represents the weight of root density;

[0071] represents the standardized root density data;

[0072] w2 represents the weight of oxygen data around the root system;

[0073] represents the normalized oxygen data around the roots;

[0074] w3 represents the weight of soil conductivity data;

[0075] Represents the normalized soil electrical conductivity data.

[0076] In the root health assessment algorithm, the weight w1 of the root density, the weight w2 of the oxygen data around the root system, and the weight w3 of the soil conductivity data are determined based on the experience of agricultural experts. In this embodiment, w1, w2, and w3 are as follows:

[0077] parameter <![CDATA[Weight (w i )]]> Weight basis <![CDATA[Root density R d > 0.4 Directly reflects root distribution and growth potential <![CDATA[Oxygen content O2]]> 0.35 Affects root respiration and nutrient absorption efficiency Soil electrical conductivity EC 0.25 Indirectly reflects soil fertility and salt stress

[0078] As an optional embodiment of the present invention, optionally, generating a three-dimensional root system heat map using a root system growth direction identification unit includes:

[0079] Set the radar frequency range, set different frequencies based on the frequency range, perform circular scanning, arc scanning, and parallel linear scanning on the root system to obtain root reflection signals at different depths;

[0080] It should be noted that in this embodiment, the root system is scanned using radar waves of different frequencies to obtain reflected signals of the root system at different depths. Circular scanning can obtain the horizontal distribution of the root system, arc scanning helps understand the growth trend of the root system on an inclined surface, and parallel linear scanning can reveal the extension of the root system in the vertical direction. Combining these scanning methods can construct a comprehensive and detailed three-dimensional image of the root system. By processing and analyzing the reflected signals, the root growth direction identification unit can accurately identify the specific location, morphology, and distribution density of the root system in the soil, and then generate a three-dimensional heat map of the root system. In the heat map, different shades of color represent different density areas of the root system, which can intuitively display the growth direction and distribution of the root system in the soil. This information can guide irrigation equipment to irrigate crops in the most appropriate way for formulating precise irrigation strategies, ensuring that water can directly act on the areas where the root system needs it most, thereby improving irrigation efficiency and crop growth quality.

[0081] The root system is scanned panoramically using a rotating probe to obtain a panoramic image of the root system in three-dimensional space;

[0082] It should be noted that the rotating head used in this embodiment is driven by a stepper motor, and a plurality of sensors and radar wave transmitters are provided on the rotating head. The stepper motor can accurately control the rotation angle and speed of the rotating head to ensure the stability and accuracy of the scanning process. During the scanning process, the rotating head rotates in the soil according to a preset trajectory, while emitting multi-band radar waves. These radar waves can penetrate the soil and be reflected back by the roots, and the sensors on the rotating head are responsible for receiving these reflected signals. By processing and analyzing the received signals, the root growth direction identification unit can accurately obtain a panoramic image of the root system in three-dimensional space. These image data are then sent to the image processing system and the three-dimensional modeling algorithm for further processing, and finally generate an intuitive three-dimensional thermal map of the root system.

[0083] Mapping the root system reflection signals onto the panoramic image in a one-to-one correspondence to obtain a root system distribution map of the root system in three-dimensional space;

[0084] It's important to note that precisely matching the root reflectance signals with the panoramic image ensures that each reflectance accurately reflects the root's location within the soil. Using advanced image processing techniques and algorithms, the root growth direction recognition unit maps these reflectance signals onto the panoramic image, creating a complete and accurate three-dimensional map of the root distribution.

[0085] The panoramic image and the root reflection signal in the root distribution map are fused, and the soil particle interference in the panoramic image is removed by using a median filter algorithm, and the root reflection signal is denoised by using a wavelet transform to retain the root reflection characteristic peak;

[0086] It should be noted that, during the fusion process, the panoramic image provides the macroscopic distribution of the roots in the soil, while the root reflection signal reveals the specific position and morphology of the roots at the microscopic level. By organically combining the two, a comprehensive and detailed three-dimensional image of the root system can be generated. However, due to the interference of soil particles and the presence of noise, the directly acquired image may not be clear enough. Therefore, this embodiment uses a median filtering algorithm to remove the interference of soil particles in the panoramic image. This algorithm can effectively smooth the image, reduce the impact of noise, and make the image clearer. At the same time, the root reflection signal is denoised using wavelet transform. Wavelet transform is a powerful signal processing tool that can decompose the signal into different frequency components and retain the root reflection characteristic peaks, thereby further improving the accuracy and reliability of the image.

[0087] The root distribution map is processed using the structure-from-motion algorithm to generate a point cloud of the root surface and construct a three-dimensional root model.

[0088] It should be noted that the structure-from-motion algorithm is a 3D reconstruction technology based on image sequences. It extracts 3D information from 2D images, generating point cloud data of the root surface. By processing and analyzing this point cloud data, a 3D root model can be constructed. This model not only illustrates the morphology and distribution of the root system but also the interaction between the root system and the soil, providing a more intuitive and accurate basis for formulating irrigation strategies.

[0089] Calculating the root system spatial coordinates based on the root system three-dimensional model radar reflection time difference;

[0090] It should be noted that the calculated spatial coordinates of the roots can be used to further understand the three-dimensional distribution of the roots in the soil. Specifically, after knowing the specific location of the roots, irrigation equipment can be guided to irrigate crops in a more precise manner, ensuring that water can directly act on the places where the roots need it most, thereby improving irrigation efficiency and crop growth quality.

[0091] Setting output pixels based on the root surface point cloud and the root space coordinates, and performing kernel density analysis with adaptive bandwidth to generate two-dimensional heat maps of different frequency bands;

[0092] It's important to note that kernel density analysis is a nonparametric statistical method that reveals the distribution density and clustering of roots in the soil by estimating the density of root surface point clouds and root spatial coordinates. By setting different output pixels and adaptive bandwidths, two-dimensional heat maps can be generated in different frequency bands. These heat maps show the density distribution of roots at different depths and locations.

[0093] The two-dimensional heat maps of different frequency bands were imported into three-dimensional visualization software to set the basic height threshold of the surface point cloud, and color gradient mapping was used to display the root distribution to generate a three-dimensional heat map of the root system.

[0094] It's important to note that after importing 2D heat maps from different frequency bands into 3D visualization software, technicians first need to set a basic height threshold for the surface point cloud. This determines which point cloud data will be considered valid root distribution information in the 3D heat map, which in turn affects the accuracy and readability of the final image. The height threshold is based on the average root depth and distribution characteristics of the crop, determined by agricultural experts and field observations.

[0095] The 3D visualization software then uses color gradient mapping to display the root distribution. Different colors represent varying root density and distribution, allowing technicians to intuitively visualize the three-dimensional distribution and growth trends of the roots within the soil. The color gradient is typically chosen for ease of distinction and identification, ensuring image clarity and readability.

[0096] Ultimately, through this series of processing and analysis steps, the present invention generates a three-dimensional root system thermal map. This image not only displays the morphology and distribution of the root system but also reveals the interaction between the root system and the soil. Based on the information in this three-dimensional root system thermal map, technicians can precisely guide irrigation equipment to irrigate crops in the most appropriate manner, ensuring that water reaches the roots where it is most needed, thereby improving irrigation efficiency and crop growth quality.

[0097] As an optional embodiment of the present invention, optionally, the decision generation module includes:

[0098] Irrigation rule library, which includes pre-set irrigation rules;

[0099] It's important to note that the irrigation rules library contains a series of preset irrigation rules based on factors such as crop growth needs, weather conditions, soil moisture, and root health. These rules comprehensively consider the water needs of crops at different growth stages, the impact of current weather conditions on soil evaporation, real-time soil moisture monitoring data, and root health assessment results. By matching current conditions with the preset rules, the irrigation rule library intelligently generates the most appropriate irrigation strategy.

[0100] A preprocessing unit, configured to perform spatiotemporal alignment and standardization operations on the weather data, humidity data, root health index, and root three-dimensional thermal map;

[0101] Spatiotemporal alignment and standardization ensure that this data is consistent across time and space, enabling it to be effectively processed and utilized by irrigation decision-making algorithms. Spatiotemporal alignment primarily addresses the temporal and spatial mismatches between data from different sources, ensuring that all data is mapped to the same spatiotemporal coordinate system. Standardization de-dimensionalizes and normalizes the data, enabling comparison and weighted calculations of data of different dimensions and ranges. This ensures that all input data are of the same scale and comparable.

[0102] a rule matching unit connected to the preprocessing unit and the irrigation rule base, for matching the preprocessed weather data, humidity data, root health index, and root three-dimensional thermal map with the rules in the irrigation rule base, calculating the rule confidence using a forward reasoning mechanism, and selecting irrigation rules based on a conflict resolution strategy;

[0103] It should be noted that the rule matching unit first uses a similarity matching algorithm on the preprocessed data to identify data features that match the preset rules in the irrigation rule library. This process involves complex logical reasoning and pattern matching algorithms, accurately extracting information that is critical to irrigation decision-making from large amounts of data. During the rule matching process, a forward reasoning mechanism is employed, which gradually infers the most appropriate irrigation strategy based on the logical sequence of the preset rules. Furthermore, considering the possibility that multiple rules may meet the requirements simultaneously, a conflict resolution strategy is introduced to ensure that the ultimately selected irrigation rule is optimal and non-conflicting.

[0104] a multi-objective optimization unit connected to the rule matching unit, and optimizing the matched irrigation rules using a multi-objective optimization algorithm to generate an irrigation strategy, wherein the multi-objective optimization algorithm aims to minimize water resource consumption, health risks, and maximize irrigation efficiency, and considers constraints such as post-irrigation humidity, single irrigation amount, and irrigation period;

[0105] It should be noted that the multi-objective optimization algorithm can not only comprehensively consider multiple objectives such as water resource consumption, health risks and irrigation efficiency, but can also adjust and optimize according to constraints such as actual post-irrigation humidity, single irrigation volume and irrigation period. This comprehensive consideration approach ensures that the generated irrigation strategy not only meets the actual needs of crops, but also maximizes water resource utilization efficiency while reducing potential health risks. In specific implementation, the multi-objective optimization unit will first receive the matching results from the rule matching unit, which include an irrigation rule. Subsequently, the multi-objective optimization algorithm will be activated to further optimize this irrigation rule. During optimization, the multi-objective optimization unit will consider the impact of each rule on water resource consumption, health risks and irrigation efficiency, and through a complex calculation process, find an irrigation strategy that can simultaneously achieve the optimization of multiple objectives while meeting all constraints.

[0106] The feedback optimization unit is connected to the multi-objective optimization unit and the execution module, and is used to receive the irrigation effect data fed back by the execution module, optimize and adjust the rule weights in the irrigation rule library according to the irrigation effect data, and update the parameters of the multi-objective optimization algorithm.

[0107] It should be noted that the specific workflow of the feedback optimization unit is as follows: First, it will receive irrigation effect data from the execution module. These data include key indicators such as soil moisture after actual irrigation, crop growth status, and water resource consumption. By analyzing these data, the feedback optimization unit can evaluate the actual effect of the current irrigation strategy and compare it with the expected target. If there is a deviation between the actual effect and the expected target, the rule weights in the irrigation rule library are optimized and adjusted according to the analysis results. At the same time, the feedback optimization unit will also update the parameters of the multi-objective optimization algorithm based on the irrigation effect data to improve the accuracy and adaptability of the algorithm. Through continuous learning and optimization, the present invention can gradually improve its own irrigation decision-making ability and provide more accurate and efficient irrigation services for corn and soybean strip composite planting.

[0108] As an optional embodiment of the present invention, optionally, the rule matching unit selects the irrigation rule including:

[0109] Extracting key features of the root system based on the three-dimensional heat map;

[0110] It should be noted that this example uses advanced image recognition technology to perform a detailed analysis of the three-dimensional root system heat map, extracting key root characteristics. These characteristics include root distribution range, peak density areas, growth direction, and morphological indicators closely related to health status. By accurately grasping these characteristics, a deeper understanding of the root growth status of crops can be achieved.

[0111] Based on the current weather data, humidity data, root health index and root key characteristics, the irrigation rules in the irrigation rule library are matched to obtain a rule set;

[0112] It should be noted that this embodiment uses a similarity matching algorithm to match currently acquired weather data, humidity data, root health index, and key root characteristics extracted from the three-dimensional root heat map with the preset rules in the irrigation rule library. This process not only considers the actual growth conditions of the crop roots but also integrates external environmental factors such as weather and soil moisture, thereby ensuring the comprehensiveness and accuracy of irrigation rule selection. During the matching process, the system selects the irrigation rules that best match the current situation based on a preset similarity threshold, forming a rule set.

[0113] respectively calculating the priorities of the weather data, humidity data, root health index and key root characteristics;

[0114] It should be noted that this embodiment uses a weighting method based on data importance to determine the priority of these data items. Specifically, the system comprehensively considers the impact of weather data, humidity data, root health index, and key root characteristics on irrigation decisions, as well as their stability and reliability in historical data. By comprehensively evaluating these factors, the system assigns a corresponding weight to each data item, with higher weights indicating greater importance in irrigation decisions.

[0115] Calculating the rule confidence of each rule in the rule set using a conflict algorithm;

[0116] It should be noted that rule confidence indicates the degree of match and reliability of each rule in the rule set with the current reality. In this embodiment, the conflict algorithm comprehensively considers weather data, humidity data, and root health index. The higher the rule confidence, the more consistent it is with the current reality and the more likely it is to be selected as the final irrigation strategy.

[0117] Sort the rule set based on rule confidence and priority, and select the irrigation rule with the highest rule confidence and priority as the irrigation rule;

[0118] It should be noted that, in this embodiment, sorting the rule set based on rule confidence and priority is a comprehensive consideration process. First, the system will sort the irrigation rules in the rule set from high to low according to the rule confidence, and the rule confidence reflects the degree of fit between the rule and the current actual situation. Subsequently, the system will further consider the priority of weather data, humidity data, root health index and key root characteristics, and the rules corresponding to data with high priority will obtain higher sorting weights. Through this comprehensive sorting process, the system can select the rules that are in line with the current actual situation and have the most important influence in irrigation decision-making as the final irrigation strategy. This strategy will directly guide the operation of irrigation equipment, ensuring that water can act on the root system of crops in the most accurate and efficient way, thereby promoting the healthy growth of crops and improving overall irrigation efficiency.

[0119] If two or more rules have the same confidence and priority, they are screened based on the historical execution effects of the rules and the growth of crops after irrigation.

[0120] It's important to note that when faced with multiple rules with the same confidence and priority, this invention further incorporates a screening mechanism based on historical rule execution results and post-irrigation crop growth. Specifically, the system reviews the actual performance of these rules in past applications, including key indicators such as soil moisture changes after irrigation, crop growth responses, and water resource efficiency. By analyzing this historical data, the system can evaluate the actual effectiveness of each rule and identify those that have performed well in the past and produced the best irrigation results.

[0121] As an optional embodiment of the present invention, optionally, the expression for calculating the rule confidence is:

[0122]

[0123] Where C represents the confidence of the rule, and All represent weight coefficients, ΔH represents humidity deviation, RHI represents root health index, T represents time urgency, S represents spatial matching, H target Indicates the target humidity of the crop at the current growth stage, H current represents the humidity value collected in real time by the root soil sensing module, α, β and γ represent weight coefficients, ρ represents the standardized root density, and ρ max represents the historical maximum value of root density, O2 represents the oxygen concentration around the root system, O 2,opt represents the optimal oxygen concentration around the roots, EC represents the electrical conductivity of the soil, and EC crit represents the critical threshold of soil conductivity, A overlap A represents the overlapping area between the irrigation area and the root active area. root Represents the total area of ​​active regions extracted from the three-dimensional heat map of the root system.

[0124] As an optional embodiment of the present invention, optionally, the expression of the multi-objective optimization algorithm is:

[0125]

[0126] f1(x)=α1x1+α2x2x3

[0127]

[0128] x1∈Q max ,x2∈[τ min ,τ max ],x3∈[f min ,f max ]

[0129] in, represents the minimization objective function vector, f(x) represents the objective function vector, f1(x) represents the total cost of water resource consumption, f2(x) represents the quantitative health risk function, f3(x) represents the maximization irrigation efficiency function, α1 represents the weight coefficient of water volume, x1 represents the irrigation water volume, α2 represents the weight coefficient of time, x2 represents the irrigation duration, x3 represents the irrigation frequency, β1 and β2 both represent weights, H 临界 represents the health threshold, H(x) represents the root health index after irrigation, N represents the total number of root nodes, dist() represents the Euclidean distance between the irrigation direction and the root distribution, x4 represents the irrigation direction, Root i represents the i-th root node, γ1 and γ2 represent efficiency weights, ΔS represents the soil moisture improvement value, Coverage(x) represents the root volume covered by irrigation, Q max represents the maximum single irrigation amount, τ min Indicates the minimum duration, τ max Indicates the maximum duration, f min Indicates the minimum frequency, f max Indicates the maximum frequency.

[0130] As an optional embodiment of the present invention, optionally, the execution module includes:

[0131] an irrigation strategy parsing unit, configured to parse the irrigation strategy and obtain irrigation parameters, wherein the irrigation parameters include irrigation amount, irrigation frequency, irrigation direction, and irrigation period;

[0132] It should be noted that in this embodiment, the irrigation strategy analysis unit specifically analyzes the irrigation strategy in depth and converts it into specific irrigation parameters. These irrigation parameters include but are not limited to irrigation amount, irrigation frequency, irrigation direction, and irrigation time period, which together constitute detailed instructions for the actual operation of the irrigation equipment.

[0133] an irrigation equipment control unit, connected to the irrigation strategy analysis unit, and configured to control the operation of the irrigation equipment according to the irrigation parameters;

[0134] It should be noted that the irrigation equipment control unit, through close collaboration with the irrigation strategy analysis unit, is able to receive and analyze irrigation parameters in real time, and then accurately control the various operations of the irrigation equipment. These operations cover the precise adjustment of irrigation volume, the reasonable arrangement of irrigation frequency, the precise positioning of irrigation direction, and the scientific setting of irrigation time periods, ensuring that irrigation operations are both efficient and energy-saving. In this embodiment, the irrigation equipment is a sprinkler irrigation device or a drip irrigation device. Intelligent sprinkler irrigation equipment uses high pressure to evenly spray water mist on crop leaves and soil surfaces, which helps to increase air humidity and promote crop photosynthesis. Drip irrigation equipment, on the other hand, transports water directly to the vicinity of crop roots through pipes, reducing water evaporation and improving water resource utilization efficiency.

[0135] The irrigation effect monitoring unit is connected to the irrigation equipment control unit and is used to monitor the root soil moisture, root health index and root growth of crops after irrigation, and feed the monitoring data back to the feedback optimization unit in the decision generation module.

[0136] It should be noted that the irrigation effect monitoring unit of this embodiment specifically includes components such as a high-precision soil moisture sensor, a root health monitor, and a root growth monitoring camera. The high-precision soil moisture sensor can measure the moisture data of the root soil in real time to ensure the accuracy and reliability of the data. The root health monitor uses advanced biosensing technology to monitor the health status of the root system in real time, including the vitality, nutritional status, and potential risks of diseases and pests. The root growth monitoring camera uses high-definition imaging technology to capture the dynamic process of root growth, providing an intuitive visual basis for adjusting the irrigation strategy. These monitoring data will be transmitted in real time to the feedback optimization unit in the decision generation module, so that the system can be adjusted and optimized in time according to the irrigation effect, further improving the accuracy and efficiency of irrigation.

[0137] As an optional embodiment of the present invention, optionally, the system also includes a user interaction interface, which is connected to the decision generation module and the execution module, and is used to display irrigation strategies, irrigation parameters and irrigation effect data, and receive irrigation instructions and parameter adjustment instructions input by the user.

[0138] It should be noted that the user interaction interface of this embodiment is designed to be intuitive and easy to operate, and is intended to provide users with a comprehensive irrigation management experience. Through this interface, users can clearly view the currently implemented irrigation strategy, specific irrigation parameters (such as irrigation amount, irrigation frequency, irrigation direction, etc.), and the effect data after irrigation, including changes in the moisture content of the root soil, improvements in the root health index, and the growth status of the root system. These data are presented in the form of charts and reports, which are convenient for users to quickly understand and analyze. The user interaction interface also allows users to input irrigation instructions and parameter adjustment instructions according to actual needs. For example, users can manually adjust irrigation strategies or irrigation parameters according to information such as the growth stage of crops or weather forecasts to adapt to different environments. In addition, the user interaction interface also has an intelligent prompt function, which can provide users with reasonable irrigation suggestions and optimization plans based on historical data and crop growth models.

[0139] 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 alterations may be made to the embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the claims and their equivalents.

Claims

1. An intelligent irrigation system for corn and soybean strip composite planting based on the Internet of Things, characterized by: The system comprises: The root soil sensing module is installed at the root system of crops to collect moisture data, root health index and root growth direction data, including a three-dimensional thermal map of the root system; Atmospheric monitoring module, used to collect weather data; Time module, used to provide current time information; a decision generation module, in communication with the root soil sensing module, the time module, and the atmosphere monitoring module, for generating an irrigation strategy using a multi-objective optimization algorithm based on the weather data, humidity data, root health index, and root growth direction data; The execution module is connected to the decision-making module and the time module, and is used to perform timed, quantitative and directional irrigation on crops according to the irrigation strategy.

2. The intelligent irrigation system for corn and soybean strip composite planting based on the Internet of Things according to claim 1, characterized in that: The root soil perception module includes: Humidity collection unit, used for collecting humidity data; a root health monitoring unit for collecting root density data, oxygen data around the roots, and soil conductivity data, and calculating a root health index based on the density data, oxygen data around the roots, and soil conductivity data using a root health assessment algorithm; The root growth direction identification unit uses a rotating probe and multi-band radar wave detection method to obtain panoramic images of the root system in different frequency bands in three-dimensional space and generate a three-dimensional thermal map of the root system.

3. The intelligent irrigation system for corn and soybean strip composite planting based on the Internet of Things according to claim 2, characterized in that: The root health assessment algorithm is expressed as: Among them, HI represents the root health index, w1 represents the weight of root density, represents the standardized root density data, w2 represents the weight of the oxygen data around the roots, represents the standardized oxygen data around the roots, w3 represents the weight of the soil conductivity data, Represents the normalized soil electrical conductivity data.

4. The intelligent irrigation system for corn and soybean strip composite planting based on the Internet of Things according to claim 2, characterized in that: Generating a three-dimensional root heat map using the root growth direction recognition unit includes: Set the radar frequency range, set different frequencies based on the frequency range, perform circular scanning, arc scanning, and parallel linear scanning on the root system to obtain root reflection signals at different depths; The root system is scanned panoramically using a rotating probe to obtain a panoramic image of the root system in three-dimensional space; Mapping the root system reflection signals onto the panoramic image in a one-to-one correspondence to obtain a root system distribution map of the root system in three-dimensional space; The panoramic image and the root system reflection signal in the root distribution map are fused, and the soil particle interference in the panoramic image is removed by using a median filter algorithm, and the root system reflection signal is denoised by using a wavelet transform to retain the root system reflection characteristic peak; The root distribution map is processed using the structure-from-motion algorithm to generate a point cloud of the root surface and construct a three-dimensional root model. Calculating the root system spatial coordinates based on the root system three-dimensional model radar reflection time difference; Setting output pixels based on the root surface point cloud and the root space coordinates, and performing kernel density analysis with adaptive bandwidth to generate two-dimensional heat maps of different frequency bands; The two-dimensional heat maps of different frequency bands were imported into three-dimensional visualization software to set the basic height threshold of the surface point cloud, and color gradient mapping was used to display the root distribution to generate a three-dimensional heat map of the root system.

5. The intelligent irrigation system for corn and soybean strip composite planting based on the Internet of Things according to claim 1, characterized in that: The decision making module includes: Irrigation rule library, which includes pre-set irrigation rules; A preprocessing unit, configured to perform spatiotemporal alignment and standardization operations on the weather data, humidity data, root health index, and root three-dimensional thermal map; a rule matching unit connected to the preprocessing unit and the irrigation rule base, for matching the preprocessed weather data, humidity data, root health index, and root three-dimensional thermal map with the rules in the irrigation rule base, calculating the rule confidence using a forward reasoning mechanism, and selecting irrigation rules based on a conflict resolution strategy; a multi-objective optimization unit connected to the rule matching unit, and optimizing the matched irrigation rules using a multi-objective optimization algorithm to generate an irrigation strategy, wherein the multi-objective optimization algorithm aims to minimize water resource consumption, health risks, and maximize irrigation efficiency, and considers constraints such as post-irrigation humidity, single irrigation amount, and irrigation period; The feedback optimization unit is connected to the multi-objective optimization unit and the execution module, and is used to receive the irrigation effect data fed back by the execution module, optimize and adjust the rule weights in the irrigation rule library according to the irrigation effect data, and update the parameters of the multi-objective optimization algorithm.

6. The intelligent irrigation system for corn and soybean strip composite planting based on the Internet of Things according to claim 5, characterized in that: The rule matching unit selects the irrigation rule including: Extracting key features of the root system based on the three-dimensional heat map; Based on the current weather data, humidity data, root health index and root key characteristics, the irrigation rules in the irrigation rule library are matched to obtain a rule set; respectively calculating the priorities of the weather data, humidity data, root health index and key root characteristics; Calculating the rule confidence of each rule in the rule set using a conflict algorithm; Sort the rule set based on rule confidence and priority, and select the irrigation rule with the highest rule confidence and priority as the irrigation rule; If two or more rules have the same confidence and priority, they are screened based on the historical execution effects of the rules and the growth of crops after irrigation.

7. The intelligent irrigation system for corn and soybean strip composite planting based on the Internet of Things according to claim 6, characterized in that: The expression for calculating the confidence of the rule is: Where C represents the confidence of the rule, and All represent weight coefficients, ΔH represents humidity deviation, RHI represents root health index, T represents time urgency, S represents spatial matching, H target Indicates the target humidity of the crop at the current growth stage, H current represents the humidity value collected in real time by the root soil sensing module, α, β and γ represent weight coefficients, ρ represents the standardized root density, and ρ max represents the historical maximum value of root density, O2 represents the oxygen concentration around the root system, O 2,opt represents the optimal oxygen concentration around the roots, EC represents the electrical conductivity of the soil, and EC crit represents the critical threshold of soil conductivity, A overlap A represents the overlapping area between the irrigation area and the root active area. root Represents the total area of ​​active regions extracted from the three-dimensional heat map of the root system.

8. The intelligent irrigation system for corn and soybean strip-shaped composite planting based on the Internet of Things according to claim 5, characterized in that: The expression of the multi-objective optimization algorithm is: f1(x)=α1x1+α2x2x3 x1∈Q max ,x2∈[τ min ,t max ],x3∈[f min ,f max ] in, represents the minimization objective function vector, f(x) represents the objective function vector, f1(x) represents the total cost of water resource consumption, f2(x) represents the quantitative health risk function, f3(x) represents the maximization irrigation efficiency function, α1 represents the weight coefficient of water volume, x1 represents the irrigation water volume, α2 represents the weight coefficient of time, x2 represents the irrigation duration, x3 represents the irrigation frequency, β1 and β2 both represent weights, H 临界 represents the health threshold, H(x) represents the root health index after irrigation, N represents the total number of root nodes, dist() represents the Euclidean distance between the irrigation direction and the root distribution, x4 represents the irrigation direction, Root i represents the i-th root node, γ1 and γ2 represent efficiency weights, ΔS represents the soil moisture improvement value, Coverage(x) represents the root volume covered by irrigation, Q max represents the maximum single irrigation amount, τ min Indicates the minimum duration, τ max Indicates the maximum duration, f min Indicates the minimum frequency, f max Indicates the maximum frequency.

9. The intelligent irrigation system for corn and soybean strip composite planting based on the Internet of Things according to claim 1, characterized in that: The execution module includes: an irrigation strategy parsing unit, configured to parse the irrigation strategy and obtain irrigation parameters, wherein the irrigation parameters include irrigation amount, irrigation frequency, irrigation direction, and irrigation period; an irrigation equipment control unit, connected to the irrigation strategy analysis unit, and configured to control the operation of the irrigation equipment according to the irrigation parameters; The irrigation effect monitoring unit is connected to the irrigation equipment control unit and is used to monitor the root soil moisture, root health index and root growth of crops after irrigation, and feed the monitoring data back to the feedback optimization unit in the decision generation module.

10. The intelligent irrigation system for corn and soybean strip-shaped composite planting based on the Internet of Things according to claim 1, characterized in that: The system also includes a user interaction interface, which is connected to the decision generation module and the execution module, and is used to display irrigation strategies, irrigation parameters and irrigation effect data, and receive irrigation instructions and parameter adjustment instructions input by the user.

Images