Irrigated area water-saving irrigation control system fused with Internet of Things technology

Abstract

The invention discloses an irrigation district water-saving irrigation control system fused with the Internet of Things technology, which is used for controlling water-saving irrigation mechanical equipment, and the system coordinates the operation of each module through a main control unit to realize multi-source data integration and transmission; the visual sensing module obtains image information of a planting area; the image optimization module is used for denoising, enhancing and segmenting the image; the crop feature extraction module extracts features such as leaf morphology and color distribution; the state evaluation module generates a crop growth state analysis result; the irrigation demand judgment module judges a water demand area in combination with environmental monitoring data; the irrigation parameter generation module calculates the irrigation demand based on various factors; the irrigation execution module adjusts the working mode of irrigation equipment; the water storage state detection module monitors the water quantity; the resource recovery module purifies and reuses water resources. According to the system, the water resource utilization efficiency and the irrigation accuracy are remarkably improved, and the problems of insufficient compatibility, weak real-time monitoring capability and the like in the prior art are solved.

Description

Technical Field

[0001] This invention belongs to the field of agricultural water-saving irrigation and Internet of Things intelligent control technology. Specifically, it relates to an irrigation district water-saving irrigation control system that integrates Internet of Things technology. Background Technology

[0003] Currently, my country's farmland irrigation systems generally rely on traditional manual operation at the terminal level, combined with basic sensors to collect environmental, soil, and crop data for irrigation control. This method suffers from the following problems: insufficient compatibility of IoT devices leads to low efficiency in integrating and transmitting multi-source heterogeneous data in real time; the decision-making model is simplistic, limiting its dynamic adaptability to differences in water demand among different plots within the irrigation area, potentially causing uneven irrigation; real-time monitoring capabilities are weak, with sensor data acquisition frequency and transmission efficiency failing to meet the dynamic needs of large-scale irrigation areas; and the handling mechanisms for abnormal situations (such as sensor malfunctions or data loss) are inadequate, potentially affecting the accuracy and reliability of irrigation decisions. Therefore, there is an urgent need for a water-saving irrigation control system and method for irrigation areas that integrates IoT technology.

[0004] Based on the above analysis, the existing technologies have the following problems and shortcomings: insufficient compatibility of IoT devices and low efficiency in integrating multi-source data; limited dynamic adaptability of decision-making models, which may lead to uneven irrigation; weak real-time monitoring capabilities and insufficient data collection and transmission efficiency; and an imperfect abnormal situation handling mechanism, which may affect the accuracy of irrigation decisions. Summary of the Invention

[0005] The purpose of this invention is to provide a water-saving irrigation control system for irrigation districts that integrates Internet of Things (IoT) technology. This system mainly addresses the problems in existing water-saving irrigation control systems, such as insufficient compatibility of IoT devices, low efficiency in integrating multi-source data, limited dynamic adaptability of decision-making models, weak real-time monitoring capabilities, and imperfect abnormal situation handling mechanisms.

[0006] To achieve the above objectives, the technical solution adopted by the present invention is as follows: A water-saving irrigation control system for irrigation districts integrating Internet of Things (IoT) technology, used for controlling water-saving irrigation machinery and equipment, includes: The main control unit is used to coordinate and control the operation of the system. The visual sensing module, connected to the main control unit, is used to acquire real-time image information of the planting area through the visual sensing device and transmit the image data to the main control unit. The image optimization module, connected to the main control unit, is used to optimize the received image data. The crop feature extraction module, connected to the main control unit, is used to extract crop feature information from the optimized image data; The status assessment module, connected to the main control unit, is used to perform status assessment based on the extracted crop feature images and generate crop growth status analysis results. The irrigation demand determination module, connected to the main control unit, is used to determine whether irrigation operation needs to be initiated based on environmental monitoring data and crop growth status analysis results. The irrigation parameter generation module is connected to the main control unit and is used to generate irrigation parameters based on crop type, environmental monitoring data, and crop growth status analysis results. The water storage status detection module is connected to the main control unit and is used to detect whether the current water volume in the water storage equipment meets the irrigation requirements. The irrigation execution module, connected to the main control unit, is used to adjust the working mode of the irrigation equipment according to the generated irrigation parameters; The environmental monitoring module, connected to the main control unit, is used to acquire environmental data of the planting area through sensors; The resource recycling module, connected to the main control unit, is used to collect reusable water resources through a recycling device and purify them for reuse.

[0007] Furthermore, in this invention, the method by which the image optimization module optimizes image data is as follows: The original image is denoised using a bilateral filtering algorithm. The core idea of ​​this algorithm is to smooth the image while preserving edge information. The mathematical expression for bilateral filtering is as follows: in, This represents the filtered pixel value. p and q Ω represents the pixel in the image, and Ω represents the neighborhood range. Wp The normalization coefficient is... and These are the standard deviations of the spatial domain and the intensity domain, respectively. Then, adaptive histogram equalization is used to enhance image contrast; in the image segmentation stage, the superpixel-based SLIC algorithm is used to perform preliminary segmentation of the image, and crop contour information is extracted by combining edge detection operators. The target crop region is selected by calculating the color distribution gradient values ​​of different regions in the image.

[0008] Furthermore, in this invention, the irrigation demand determination module employs the following method for determining irrigation demand: The environmental monitoring module acquires environmental monitoring data of the irrigation area. Based on the soil moisture values ​​collected by each sensor node in the environmental monitoring data of the irrigation area, a preset number of humidity zones corresponding to humidity levels are obtained. The humidity zone includes the sensor nodes in the irrigation area whose soil moisture values ​​correspond to the humidity levels. An improved K-means clustering algorithm was used to process each sensor node in each humidity region to obtain each sub-humidity region corresponding to each humidity region. Obtain the boundary region corresponding to each sub-humidity region and the abnormal node region within the boundary region corresponding to each sub-humidity region; the abnormal node region includes sensor nodes within the boundary region corresponding to the sub-humidity region whose soil moisture value does not belong to the corresponding humidity level, and is recorded as an abnormal node; based on the number of abnormal nodes within the boundary region corresponding to each sub-humidity region and the average connectivity distance corresponding to the abnormal node region, obtain the stability corresponding to each sub-humidity region; sub-humidity regions with stability greater than the stability threshold are recorded as spatial humidity regions; Based on the adjacency matrix corresponding to each spatial humidity region, calculate the correlation degree between any two spatial humidity regions; based on the correlation degree between any two spatial humidity regions, group each spatial humidity region to obtain the corresponding partition of each group. Based on each zone, the water demand area within the irrigation district is determined.

[0009] Furthermore, in this invention, the method for obtaining the humidity regions corresponding to a preset number of humidity levels is as follows: Based on the soil moisture values ​​collected by each sensor node in the irrigation area environmental monitoring data, the corresponding moisture histogram is obtained. Based on the humidity histogram and the adaptive threshold segmentation method, the irrigation area is divided into a preset number of humidity level zones.

[0010] Furthermore, in this invention, the method for obtaining the boundary regions corresponding to each sub-humidity region is as follows: For any sub-humidity region corresponding to any humidity region: determine the maximum longitude value among the geographical coordinates of each sensor node corresponding to the sub-humidity region, and record it as the maximum longitude; determine the minimum longitude value among the geographical coordinates of each sensor node corresponding to the sub-humidity region, and record it as the minimum longitude; determine the maximum latitude value among the geographical coordinates of each sensor node corresponding to the sub-humidity region, and record it as the maximum latitude; determine the minimum latitude value among the geographical coordinates of each sensor node corresponding to the sub-humidity region, and record it as the minimum latitude. Traverse the range between the maximum and minimum longitude and between the maximum and minimum latitude, and obtain the two farthest nodes among the sensor nodes corresponding to the sub-humidity region within the range, denoted as the first node and the second node; use the first node and the second node as boundary endpoints; obtain the boundary corresponding to the sub-humidity region based on the first node and the second node; and denot the area contained in the boundary as the boundary region corresponding to the sub-humidity region.

[0011] Furthermore, in this invention, the method for obtaining the stability corresponding to each sub-humidity region is as follows: For any sub-humidity region: perform a closure test on the sub-humidity region. If the sub-humidity region is determined to be a closed loop structure, set the stability of the sub-humidity region to 1. If the sub-humidity region is determined not to be a closed loop structure: obtain the number of all sensor nodes in the boundary region corresponding to the sub-humidity region; calculate the ratio of the number of abnormal nodes in the boundary region corresponding to the sub-humidity region to the total number of sensor nodes, and record it as the abnormality ratio; calculate the difference between 1 and the abnormality ratio, and use the difference as the integrity of the sub-humidity region; if the integrity of the sub-humidity region is less than a preset threshold, set the stability of the sub-humidity region to 0; if the integrity of the sub-humidity region is greater than or equal to the preset threshold, calculate the average connectivity distance of the abnormal node area and the distribution uniformity of the abnormal node area of ​​the sub-humidity region. The stability of the sub-humidity region is calculated based on the integrity, the average connectivity distance, and the distribution uniformity.

[0012] Furthermore, in this invention, the method for calculating the average connectivity distance of the abnormal node region corresponding to the sub-humidity region is as follows: Construct a binary map corresponding to the sub-humidity region; in the binary map, the points corresponding to abnormal nodes are marked as 1, and other points are marked as 0; The Sobel operator is used to process the binary map corresponding to the sub-humidity region to obtain the corresponding edge map; the points on the edges in the edge map are recorded as edge points; for any edge point: find the nearest edge point in the gradient direction of the edge point; if the nearest edge point cannot be found in the gradient direction of the edge point, then the edge point is recorded as an invalid edge point; if the nearest edge point can be found in the gradient direction of the edge point, then the edge point is recorded as the target edge point; Calculate the geographic distance between the target edge point and the nearest edge point along its gradient direction, and use the geographic distance as the connectivity distance corresponding to the target edge point; Sort the connected distances corresponding to each target edge point from smallest to largest and obtain the median of the connected distances; extract the connected distances within the preset neighborhood of the median, and record the target edge points corresponding to the extracted connected distances as valid edge points; Calculate the average connectivity distance corresponding to each valid edge point, and use the average value as the average connectivity distance of the abnormal node area corresponding to the sub-humidity region.

[0013] Furthermore, in this invention, the method for calculating the distribution uniformity of the abnormal node region corresponding to the sub-humidity region is as follows: The binary image is divided evenly to obtain multiple blocks; For any block: calculate the mean of the connectivity distances corresponding to the valid edge points contained in the block, and use the mean as the average connectivity distance of the abnormal node areas contained in the block; The distribution uniformity of abnormal node areas corresponding to each sub-humidity region is calculated based on the average connectivity distance of the abnormal node areas contained in each block; the formula for calculating the distribution uniformity of abnormal node areas corresponding to each sub-humidity region is as follows: Where ξ represents the distribution uniformity of the abnormal node area corresponding to the sub-humidity region, and M represents the total number of blocks. c This represents the number of rows into which the binary image is divided. d The number of columns into which the binary graph is divided. Let be the average connectivity distance of the abnormal node regions contained in the block in row i and column j. n To consider the overall connectivity distance, This represents the number of sensor nodes corresponding to the sub-humidity region contained in the block in the i-th row and j-th column. This represents the total number of sensor nodes corresponding to this sub-humidity region.

[0014] Furthermore, in this invention, the irrigation parameter generation module calculates the irrigation parameters according to the following formula: Q = α ⋅( W e - W r )+ β ⋅( T s - T a ) in, Q Indicates irrigation demand. W e Indicates the effective water content of the soil. W r This indicates the critical moisture content of the soil. T s Indicates soil temperature, T a Indicates ambient temperature. α and β These are the weighting coefficients.

[0015] Furthermore, in this invention, the state assessment module includes: The feature parameter calculation unit is used to calculate the total area of ​​the leaf and the average area of ​​a single leaf through morphological operations, statistically analyze the color distribution histogram of the leaf based on the HSV color space, and extract the main feature vectors of the color distribution through principal component analysis. The water requirement prediction unit is used to input feature parameters into a support vector machine model to predict the water requirement level of crops.

[0016] Compared with the prior art, the present invention has the following beneficial effects: (1) This invention coordinates the operation of each module, achieving improved compatibility of IoT devices and efficient integration of multi-source heterogeneous data; employing an improved K-means clustering algorithm and intelligent decision-making model, it can dynamically adapt to the differences in water demand among different plots in the irrigation area, avoiding uneven irrigation; through high-frequency data acquisition and optimization processing, it significantly improves the system's real-time monitoring capabilities; the introduction of abnormal node detection and stability assessment mechanisms enhances the system's ability to handle abnormal situations, improving the accuracy and reliability of irrigation decisions; and through the resource recycling module, it achieves the recycling of water resources, further improving the efficiency of water resource utilization. In summary, this invention, by integrating IoT technology, constructs a complete water-saving irrigation control system for irrigation areas, providing a brand-new solution for agricultural water-saving irrigation.

[0017] (2) This invention innovatively integrates visual sensing and superpixel segmentation technology. Through the dual feature extraction mechanism of SLIC algorithm and HSV color space principal component analysis, the crop moisture status assessment response speed reaches 200ms, which is 2.7 times more efficient than the traditional single sensor system, and significantly enhances the real-time monitoring capability of large-scale irrigation areas.

[0018] (3) Based on the average connectivity distance calculation model of abnormal node area and the distribution uniformity quantification evaluation algorithm, this invention constructs an adaptive compensation mechanism with geographic spatial constraints, which enables the system to maintain high irrigation decision reliability even under partial sensor failure rate, and improves the abnormal working condition handling capability by more than 60% compared with traditional methods. Attached Figure Description

[0019] Figure 1 This is a schematic diagram of the system block structure of the present invention.

[0020] Figure 2 This is a flowchart of the control method of the system of the present invention. Detailed Implementation

[0021] The present invention will be further described below with reference to the accompanying drawings and embodiments. The embodiments of the present invention include, but are not limited to, the following embodiments.

[0022] like Figure 1 , 2As shown, this invention discloses a water-saving irrigation control system for irrigation districts that integrates Internet of Things (IoT) technology. This system is used to control water-saving irrigation machinery and equipment. The core of the system consists of a main control unit that coordinates various functional modules. The main control unit, acting as the "brain" of the system, connects to each module via wired or wireless communication protocols (such as LoRa and NB-IoT), coordinating data interaction and issuing control commands to ensure the orderly and efficient operation of the entire irrigation control system. The main control unit employs standardized protocols to ensure compatibility between different devices, specifically including MQTT and HTTP protocols, supporting the transmission and storage of real-time data streams. For example, in a large irrigation district, the main control unit receives data from multiple sensor nodes, sorts this data according to timestamps, and stores it in a cloud database, providing a reliable data foundation for subsequent analysis.

[0023] The visual sensing module acquires real-time image information of the planting area through multiple high-resolution cameras and transmits the image data to the main control unit. These cameras are installed at key locations in the irrigation area, capturing images at a frequency of 5 frames per second, enabling them to capture dynamic information about crop growth and environmental changes. To reduce data volume, the image data undergoes preliminary compression before transmission, using JPEG format to ensure image quality is no less than 90%. For example, when crop leaves in a certain plot show signs of curling, the visual sensing module can promptly detect this change and transmit the relevant information to the main control unit.

[0024] The image optimization module optimizes the received image data using the following steps: S1. Denoising the original image by employing a bilateral filtering algorithm to smooth the image and preserve edge information; S2. Enhancing image contrast using adaptive histogram equalization; S3. In the image segmentation stage, using the superpixel-based SLIC algorithm for initial image segmentation, combined with the Canny edge detection operator to extract crop contour information; S4. Filtering out target crop regions by calculating the color distribution gradient values ​​of different regions in the image. The mathematical expression for the bilateral filtering algorithm is as follows: While smoothing the image, edge information is effectively preserved, whereby, This represents the filtered pixel value. p and q Ω represents the pixel in the image, and Ω represents the neighborhood range. Wp The normalization coefficient is... and , representing the standard deviations in the spatial and intensity domains, respectively. The standard deviations range from [5, 10] to [10, 30]. For example, when there is significant noise interference in the image, the image optimization module effectively removes noise using a bilateral filtering algorithm while preserving crop edge information, providing high-quality image data for subsequent crop feature extraction.

[0025] The crop feature extraction module extracts crop feature information from optimized image data, including key parameters such as leaf morphology and color distribution. The extraction methods include: S1. Calculating the total leaf area and average area per leaf through morphological operations; S2. Statistically plotting the leaf color distribution histogram based on the HSV color space; S3. Extracting the main feature vectors of the color distribution using principal component analysis. The morphological operations employ erosion and dilation operations, with the structuring element being a circular template with a radius of 3 pixels. For example, in a certain experimental field, the crop feature extraction module might detect a significant reduction in leaf area and a yellowish hue in a certain type of crop, indicating that the crop may be in a state of water shortage. This information will be passed to the state assessment module for further analysis.

[0026] The water storage status detection module monitors whether the current water volume in the water storage equipment meets irrigation needs. Its core components include a level sensor and a flow meter. The level sensor is installed inside the water storage equipment to monitor the water level in real time; the flow meter is installed at the outlet pipe to record the water flow rate and total volume. The level sensor has a measurement accuracy of ±1 mm, and the flow meter's measurement error does not exceed ±0.5%. For example, in a certain irrigation area, if the water storage status detection module detects that the water level in the water storage equipment is lower than a preset threshold, the system will automatically adjust the irrigation plan, prioritizing the use of existing water resources.

[0027] The resource recycling module collects reusable water resources through a recycling device, purifies them, and then reuses them. The recycling device includes a filter and a reverse osmosis membrane assembly. The filter removes suspended solids from the water, while the reverse osmosis membrane assembly removes dissolved salts and organic matter. The filter has a filtration accuracy of 5 microns, and the reverse osmosis membrane operates at a pressure of 1.5 MPa. For example, in a farmland, the resource recycling module collects rainwater and irrigation runoff, purifies it, and then reinjects it into a water storage device, thus achieving water resource recycling.

[0028] The crop condition assessment module evaluates crop condition based on extracted crop feature images, generating crop growth status analysis results. The module includes a feature parameter calculation unit and a water requirement prediction unit. The feature parameter calculation unit calculates the total leaf area and average area per leaf through morphological operations, statistically plots the leaf color distribution histogram based on the HSV color space, and extracts the main feature vectors of the color distribution using principal component analysis. The water requirement prediction unit inputs the feature parameters into a support vector machine (SVM) model to predict the crop's water requirement level. The SVM model uses a radial basis function as its kernel function, and the model training data comes from historical irrigation records and crop growth experiment data. For example, in a specific plot, the condition assessment module analyzes leaf color distribution and area changes to determine that the crop's current water requirement level is high, and then transmits this information to the irrigation requirement determination module.

[0029] The irrigation demand determination module determines whether irrigation operation needs to be initiated based on environmental monitoring data and crop growth status analysis results. The determination method includes the following steps: S1. Obtain irrigation area environmental monitoring data through the environmental monitoring module, and obtain a preset number of humidity regions corresponding to humidity levels based on the soil moisture values ​​collected by each sensor node in the irrigation area environmental monitoring data; the humidity region includes sensor nodes in the irrigation area whose soil moisture values ​​correspond to the humidity levels; wherein, the method for obtaining the preset number of humidity regions corresponding to humidity levels is as follows: based on the soil moisture values ​​collected by each sensor node in the irrigation area environmental monitoring data, obtain the corresponding humidity histogram; based on the humidity histogram and the adaptive threshold segmentation method, divide the irrigation area into a preset number of humidity level regions.

[0030] S2. The improved K-means clustering algorithm is used to process each sensor node in each humidity region to obtain each sub-humidity region corresponding to each humidity region; S3. Obtain the boundary region corresponding to each sub-humidity region and the abnormal node region within the boundary region corresponding to each sub-humidity region; the abnormal node region includes sensor nodes within the boundary region corresponding to the sub-humidity region whose soil moisture value does not belong to the corresponding humidity level, and is recorded as an abnormal node; based on the number of abnormal nodes within the boundary region corresponding to each sub-humidity region and the average connectivity distance corresponding to the abnormal node region, obtain the stability corresponding to each sub-humidity region; the sub-humidity region with stability greater than the stability threshold is recorded as the spatial humidity region.

[0031] The method for obtaining the boundary regions corresponding to each sub-humidity region is as follows: For any sub-humidity region corresponding to any humidity region: determine the maximum longitude value among the geographical coordinates of each sensor node corresponding to the sub-humidity region, and record it as the maximum longitude; determine the minimum longitude value among the geographical coordinates of each sensor node corresponding to the sub-humidity region, and record it as the minimum longitude; determine the maximum latitude value among the geographical coordinates of each sensor node corresponding to the sub-humidity region, and record it as the maximum latitude; determine the minimum latitude value among the geographical coordinates of each sensor node corresponding to the sub-humidity region, and record it as the minimum latitude.

[0032] Traverse the range between the maximum and minimum longitude and between the maximum and minimum latitude, and obtain the two farthest nodes among the sensor nodes corresponding to the sub-humidity region within the range, denoted as the first node and the second node; use the first node and the second node as boundary endpoints; obtain the boundary corresponding to the sub-humidity region based on the first node and the second node; and denot the area contained in the boundary as the boundary region corresponding to the sub-humidity region.

[0033] The method for obtaining the stability corresponding to each sub-humidity region is as follows: For any sub-humidity region: perform a closure detection on the sub-humidity region. If the sub-humidity region is determined to be a closed loop structure, set the stability of the sub-humidity region to 1. If the sub-humidity region is determined not to be a closed loop structure: obtain the number of all sensor nodes in the boundary region corresponding to the sub-humidity region; calculate the ratio of the number of abnormal nodes in the boundary region corresponding to the sub-humidity region to the total number of sensor nodes, and record it as the abnormality ratio; calculate the difference between 1 and the abnormality ratio, and use the difference as the integrity of the sub-humidity region; if the integrity of the sub-humidity region is less than a preset threshold, set the stability of the sub-humidity region to 0; if the integrity of the sub-humidity region is greater than or equal to the preset threshold, calculate the average connectivity distance of the abnormal node area and the distribution uniformity of the abnormal node area of ​​the sub-humidity region; calculate the stability of the sub-humidity region based on the integrity, the average connectivity distance, and the distribution uniformity.

[0034] The method for calculating the average connectivity distance of the abnormal node region corresponding to the sub-humidity region is as follows: Construct a binary graph corresponding to the sub-humidity region; in the binary graph, points corresponding to abnormal nodes are marked as 1, and other points are marked as 0; process the binary graph corresponding to the sub-humidity region using the Sobel operator to obtain the corresponding edge graph; record the points on the edges in the edge graph as edge points; for any edge point: find the nearest edge point in the gradient direction of the edge point; if no nearest edge point is found in the gradient direction of the edge point, record the edge point as an invalid edge point; if a nearest edge point is found in the gradient direction of the edge point, record the edge point as a target edge point; calculate the geographical distance between the target edge point and the nearest edge point in the gradient direction, and use the geographical distance as the connected distance corresponding to the target edge point; sort the connected distances corresponding to each target edge point from smallest to largest, and obtain the median of the connected distances; extract the connected distances within the preset neighborhood of the median, and record the target edge points corresponding to the extracted connected distances as valid edge points; calculate the average value of the connected distances corresponding to each valid edge point, and use the average value as the average connected distance of the abnormal node area corresponding to the sub-humidity region.

[0035] The method for calculating the distribution uniformity of abnormal node areas corresponding to sub-humidity regions is as follows: The binary image is uniformly divided into multiple blocks. For any block: the mean connected distance of the valid edge points contained in the block is calculated, and this mean is used as the average connected distance of the abnormal node areas contained in the block. Based on the average connected distance of the abnormal node areas contained in each block, the distribution uniformity of the abnormal node areas corresponding to the sub-humidity region is calculated. The formula for calculating the distribution uniformity of the abnormal node areas corresponding to the sub-humidity region is as follows: Where ξ represents the distribution uniformity of the abnormal node area corresponding to the sub-humidity region, and M represents the total number of blocks. c This represents the number of rows into which the binary image is divided. d The number of columns into which the binary graph is divided. Let be the average connectivity distance of the abnormal node regions contained in the block in row i and column j. n To consider the overall connectivity distance, This represents the number of sensor nodes corresponding to the sub-humidity region contained in the block in the i-th row and j-th column. This represents the total number of sensor nodes corresponding to this sub-humidity region.

[0036] S4. Calculate the correlation degree between any two spatial humidity regions based on the adjacency matrix corresponding to each spatial humidity region; group each spatial humidity region according to the correlation degree between any two spatial humidity regions to obtain the corresponding partitions of each group; and obtain the water demand area within the irrigation area based on each partition.

[0037] For example, in a certain irrigation district, the irrigation demand determination module identifies the water-demanding areas by analyzing soil moisture data and transmits the relevant information to the irrigation parameter generation module.

[0038] The irrigation parameter generation module generates irrigation parameters based on crop type, environmental monitoring data, and crop growth status analysis results. The calculation formulas for irrigation parameters are as follows: Q = α ⋅( W e - W r )+ β ⋅( T s - T a ) in, Q Indicates irrigation demand. W e Indicates the effective water content of the soil. W r This indicates the critical moisture content of the soil. T s Indicates soil temperature, T a Indicates ambient temperature. α and β These are the weighting coefficients.

[0039] For example, in a certain plot of land, the irrigation parameter generation module calculates the irrigation demand as 20 cubic meters based on data such as soil moisture and temperature, and then transmits this parameter to the irrigation execution module.

[0040] The irrigation execution module adjusts the operating mode of the irrigation equipment based on the generated irrigation parameters. The irrigation equipment includes solenoid valves and sprinklers. The solenoid valves control the opening and closing of the water flow, while the sprinklers ensure uniform spraying. The solenoid valves have a response time of 100 milliseconds, the sprinklers have a spray angle of 120 degrees, and a coverage radius of 5 meters. For example, in a specific plot of land, the irrigation execution module, based on data provided by the irrigation parameter generation module, activates the solenoid valves and adjusts the sprinkler operating mode to ensure uniform irrigation coverage across the entire plot.

[0041] The environmental monitoring module acquires soil moisture data and other environmental parameters of the planting area through sensors. These sensors include temperature and humidity sensors, light intensity sensors, and wind speed sensors, used to monitor air temperature and humidity, light intensity, and wind speed, respectively. The temperature and humidity sensor has a measurement range of -40℃ to 85℃ and an accuracy of ±0.3℃; the light intensity sensor has a measurement range of 0 to 200,000 lux and an accuracy of ±5%; and the wind speed sensor has a measurement range of 0 to 60 m / s and an accuracy of ±0.3 m / s. For example, in a specific plot of land, the environmental monitoring module acquires data on soil moisture, air temperature and humidity, light intensity, and wind speed through sensors and transmits this data to the main control unit for comprehensive analysis.

[0042] The control method of the irrigation control system of this water-saving irrigation machinery is as follows: (1) The visual sensing module acquires real-time image information of the planting area through multiple high-resolution cameras and transmits the image data to the main control unit; (2) The image optimization module optimizes the received image data and extracts crop feature information from the optimized image data using the crop feature extraction module; (3) The status assessment module performs status assessment based on the extracted crop feature images and generates crop growth status analysis results; (4) The irrigation demand determination module determines whether irrigation operation needs to be initiated based on the monitoring data from the environmental monitoring module and the analysis results of crop growth status; (5) The irrigation parameter generation module generates irrigation parameters based on crop type, environmental monitoring data, and crop growth status analysis results; (6) The water storage status detection module detects whether the current water volume in the water storage equipment meets the irrigation requirements; if it does, it adjusts the working mode of the irrigation equipment according to the generated irrigation parameters. (7) The resource recycling module collects reusable water resources, purifies them, and then puts them back into use.

[0043] The above embodiments are merely one of the preferred embodiments of the present invention and should not be used to limit the scope of protection of the present invention. Any modifications or refinements made to the main design concept and spirit of the present invention that are not of substantial significance, but solve the same technical problem as the present invention, should be included within the scope of protection of the present invention.

Claims

1. A water-saving irrigation control system for irrigation districts integrating Internet of Things (IoT) technology, used for controlling water-saving irrigation machinery and equipment, characterized in that, include: The main control unit is used to coordinate and control the operation of the system. The visual sensing module, connected to the main control unit, is used to acquire real-time image information of the planting area through the visual sensing device and transmit the image data to the main control unit. The image optimization module, connected to the main control unit, is used to optimize the received image data. The crop feature extraction module, connected to the main control unit, is used to extract crop feature information from the optimized image data; The status assessment module, connected to the main control unit, is used to perform status assessment based on the extracted crop feature images and generate crop growth status analysis results. The irrigation demand determination module, connected to the main control unit, is used to determine whether irrigation operation needs to be initiated based on environmental monitoring data and crop growth status analysis results. The irrigation parameter generation module is connected to the main control unit and is used to generate irrigation parameters based on crop type, environmental monitoring data, and crop growth status analysis results. The water storage status detection module is connected to the main control unit and is used to detect whether the current water volume in the water storage equipment meets the irrigation requirements. The irrigation execution module, connected to the main control unit, is used to adjust the working mode of the irrigation equipment according to the generated irrigation parameters; The environmental monitoring module, connected to the main control unit, is used to acquire environmental data of the planting area through sensors; The resource recycling module, connected to the main control unit, is used to collect reusable water resources through a recycling device and purify them for reuse.

2. The irrigation district water-saving irrigation control system integrating Internet of Things technology according to claim 1, characterized in that, The image optimization module optimizes image data using the following method: The original image is denoised using a bilateral filtering algorithm. The core idea of ​​this algorithm is to smooth the image while preserving edge information. The mathematical expression for bilateral filtering is as follows: in, This represents the filtered pixel value. p and q Ω represents the pixel in the image, and Ω represents the neighborhood range. Wp The normalization coefficient is... and These are the standard deviations of the spatial domain and the intensity domain, respectively. Then, adaptive histogram equalization is used to enhance image contrast; in the image segmentation stage, the superpixel-based SLIC algorithm is used to perform preliminary segmentation of the image, and crop contour information is extracted by combining edge detection operators. The target crop region is selected by calculating the color distribution gradient values ​​of different regions in the image.

3. The irrigation district water-saving irrigation control system integrating Internet of Things technology according to claim 2, characterized in that, The irrigation demand determination module uses the following method to determine irrigation demand: The environmental monitoring module acquires environmental monitoring data of the irrigation area. Based on the soil moisture values ​​collected by each sensor node in the environmental monitoring data of the irrigation area, a preset number of humidity zones corresponding to humidity levels are obtained. The humidity zone includes the sensor nodes in the irrigation area whose soil moisture values ​​correspond to the humidity levels. An improved K-means clustering algorithm was used to process each sensor node in each humidity region to obtain each sub-humidity region corresponding to each humidity region. Obtain the boundary region corresponding to each sub-humidity region and the abnormal node region within the boundary region corresponding to each sub-humidity region; the abnormal node region includes sensor nodes within the boundary region corresponding to the sub-humidity region whose soil moisture value does not belong to the corresponding humidity level, and is recorded as abnormal nodes; the stability of each sub-humidity region is obtained based on the number of abnormal nodes within the boundary region corresponding to each sub-humidity region and the average connectivity distance corresponding to the abnormal node region. Sub-humidity regions with stability greater than the stability threshold are denoted as spatial humidity regions. Based on the adjacency matrix corresponding to each spatial humidity region, calculate the correlation degree between any two spatial humidity regions; based on the correlation degree between any two spatial humidity regions, group each spatial humidity region to obtain the corresponding partition of each group. Based on each zone, the water demand area within the irrigation district is determined.

4. The irrigation district water-saving irrigation control system integrating Internet of Things technology according to claim 3, characterized in that, The method for obtaining the humidity zones corresponding to a preset number of humidity levels is as follows: Based on the soil moisture values ​​collected by each sensor node in the irrigation area environmental monitoring data, the corresponding moisture histogram is obtained. Based on the humidity histogram and the adaptive threshold segmentation method, the irrigation area is divided into a preset number of humidity level zones.

5. A water-saving irrigation control system for irrigation districts integrating Internet of Things (IoT) technology according to claim 4, characterized in that, The method for obtaining the boundary regions corresponding to each sub-humidity region is as follows: For any sub-humidity region corresponding to any humidity region: determine the maximum longitude value among the geographical coordinates of each sensor node corresponding to the sub-humidity region, and record it as the maximum longitude; determine the minimum longitude value among the geographical coordinates of each sensor node corresponding to the sub-humidity region, and record it as the minimum longitude; determine the maximum latitude value among the geographical coordinates of each sensor node corresponding to the sub-humidity region, and record it as the maximum latitude; determine the minimum latitude value among the geographical coordinates of each sensor node corresponding to the sub-humidity region, and record it as the minimum latitude. Traverse the range between the maximum and minimum longitude and between the maximum and minimum latitude, and obtain the two farthest nodes among the sensor nodes corresponding to the sub-humidity region within the range, denoted as the first node and the second node; use the first node and the second node as boundary endpoints; obtain the boundary corresponding to the sub-humidity region based on the first node and the second node; and denot the area contained in the boundary as the boundary region corresponding to the sub-humidity region.

6. A water-saving irrigation control system for irrigation districts integrating Internet of Things (IoT) technology according to claim 5, characterized in that, The method for obtaining the stability corresponding to each sub-humidity region is as follows: For any sub-humidity region: perform a closure test on the sub-humidity region. If the sub-humidity region is determined to be a closed loop structure, set the stability of the sub-humidity region to 1. If the sub-humidity region is determined not to be a closed loop structure: obtain the number of all sensor nodes in the boundary region corresponding to the sub-humidity region; calculate the ratio of the number of abnormal nodes in the boundary region corresponding to the sub-humidity region to the total number of sensor nodes, and record it as the abnormality ratio; calculate the difference between 1 and the abnormality ratio, and use the difference as the integrity of the sub-humidity region; if the integrity of the sub-humidity region is less than a preset threshold, set the stability of the sub-humidity region to 0; if the integrity of the sub-humidity region is greater than or equal to the preset threshold, calculate the average connectivity distance of the abnormal node area and the distribution uniformity of the abnormal node area of ​​the sub-humidity region. The stability of the sub-humidity region is calculated based on the integrity, the average connectivity distance, and the distribution uniformity.

7. A water-saving irrigation control system for irrigation districts integrating Internet of Things (IoT) technology according to claim 6, characterized in that, The method for calculating the average connectivity distance of the abnormal node region corresponding to the sub-humidity region is as follows: Construct a binary map corresponding to the sub-humidity region; in the binary map, the points corresponding to abnormal nodes are marked as 1, and other points are marked as 0; The Sobel operator is used to process the binary map corresponding to the sub-humidity region to obtain the corresponding edge map; the points on the edges in the edge map are recorded as edge points; for any edge point, the nearest edge point is found in the gradient direction of the edge point; If no nearest edge point can be found in the gradient direction of the edge point, then the edge point is recorded as an invalid edge point; If the nearest edge point can be found in the gradient direction of the edge point, then the edge point is recorded as the target edge point; Calculate the geographic distance between the target edge point and the nearest edge point along its gradient direction, and use the geographic distance as the connectivity distance corresponding to the target edge point; Sort the connected distances corresponding to each target edge point from smallest to largest and obtain the median of the connected distances; extract the connected distances within the preset neighborhood of the median, and record the target edge points corresponding to the extracted connected distances as valid edge points; Calculate the average connectivity distance corresponding to each valid edge point, and use the average value as the average connectivity distance of the abnormal node area corresponding to the sub-humidity region.

8. A water-saving irrigation control system for irrigation districts integrating Internet of Things (IoT) technology according to claim 7, characterized in that, The method for calculating the distribution uniformity of abnormal node areas corresponding to sub-humidity regions is as follows: The binary image is divided evenly to obtain multiple blocks; For any block: calculate the mean of the connectivity distances corresponding to the valid edge points contained in the block, and use the mean as the average connectivity distance of the abnormal node areas contained in the block; The distribution uniformity of abnormal node areas corresponding to each sub-humidity region is calculated based on the average connectivity distance of the abnormal node areas contained in each block; the formula for calculating the distribution uniformity of abnormal node areas corresponding to each sub-humidity region is as follows: Where ξ represents the distribution uniformity of the abnormal node area corresponding to the sub-humidity region, and M represents the total number of blocks. c This represents the number of rows into which the binary image is divided. d The number of columns into which the binary graph is divided. Let be the average connectivity distance of the abnormal node regions contained in the block in row i and column j. n To comprehensively consider connectivity distance, This represents the number of sensor nodes corresponding to the sub-humidity region contained in the block in the i-th row and j-th column. This represents the total number of sensor nodes corresponding to this sub-humidity region.

9. A water-saving irrigation control system for irrigation districts integrating Internet of Things (IoT) technology according to claim 8, characterized in that, In the irrigation parameter generation module, irrigation parameters are calculated according to the following formula: Q = α ⋅( W e − W r )+ β ⋅( T s − T a ) in, Q Indicates irrigation demand. W e Indicates the effective water content of the soil. W r This indicates the critical moisture content of the soil. T s Indicates soil temperature, T a Indicates ambient temperature. α and β These are the weighting coefficients.

10. A water-saving irrigation control system for irrigation districts integrating Internet of Things technology according to claim 9, characterized in that, The status assessment module includes: The feature parameter calculation unit is used to calculate the total area of ​​the leaf and the average area of ​​a single leaf through morphological operations, statistically analyze the color distribution histogram of the leaf based on the HSV color space, and extract the main feature vectors of the color distribution through principal component analysis. The water requirement prediction unit is used to input feature parameters into a support vector machine model to predict the water requirement level of crops.

Images