Intelligent irrigation station control system based on Internet of Things

Abstract

The invention relates to the field of irrigation station control, in particular to an intelligent irrigation station control system based on the Internet of Things, which comprises a data acquisition layer, a data analysis layer and equipment execution, and is characterized in that the data acquisition layer comprises water consumption acquisition and water supply acquisition; the data acquisition layer is used for acquiring multi-dimensional data such as soil moisture content, crop growth, weather, water consumption and water supply quantity through various sensors and metering equipment; the data analysis layer comprises supply and demand relationship analysis and intelligent deployment analysis; the data analysis layer performs supply and demand relationship analysis and intelligent deployment decision making by using a model algorithm based on the acquired data; the equipment execution layer comprises irrigation station control execution and water valve control execution; according to the scheme, dynamic scheduling and abnormal response of water resources are realized by virtue of cooperation of the multi-stage water transfer decision model and the equipment execution layer. The water supply guarantee rate is improved to 98% and the fault processing time is shortened to be within 30 minutes through the first-level, second-level and cross-level water transfer strategies and water pressure balance control in cooperation with pipeline monitoring and emergency scheduling plans.

Description

Technical Field

[0001] The present invention relates to the technical field of pumping station control, and in particular to an intelligent pumping station control system based on the Internet of Things. Background Art

[0002] Irrigation stations are core facilities in agricultural water conservancy projects, used to lift water to a designated height for irrigation and water supply. They typically consist of pump units, water pipelines, and control equipment. Irrigation station control systems manage the operation of equipment and water allocation at the station. Traditional control systems rely on manual operation or simple automated control. IoT-based irrigation station control systems utilize sensors, communication networks, and intelligent algorithms to enable digital monitoring and intelligent management of the entire irrigation station process.

[0003] Traditional control systems have significant shortcomings: weak data collection capabilities and a lack of real-time monitoring of multi-dimensional data such as soil moisture, crop growth, and meteorological changes. This leads to significant inaccuracies in water demand forecasts. For example, it's impossible to accurately determine the moisture content of different soil layers and the water demand patterns of crops during their growth periods. Water resource allocation often relies on empirical judgment, resulting in a utilization rate as low as 65%. The scheduling mechanism is rigid, enabling only simple local water supply. It lacks multi-level water diversion strategies and dynamic water pressure balance control. This makes it impossible to respond quickly to water supply and demand imbalances or pipeline failures. The water supply guarantee rate is less than 90%, and troubleshooting takes over two hours.

[0004] To this end, the present invention proposes an intelligent irrigation station control system based on the Internet of Things. By constructing a three-layer architecture of "data collection-analysis and decision-making-equipment execution", the present invention uses multiple types of sensors to realize real-time collection of water, soil and air data, combines the LSTM model with the linear programming algorithm to perform supply and demand forecasting and water diversion optimization, and combines it with a three-level water diversion strategy and dynamic water pressure control. It has achieved a technological breakthrough in increasing water resource utilization to 88%, reducing energy consumption by 12%, and achieving a water supply guarantee rate of 98%, significantly improving the intelligence and intensiveness of farmland irrigation. Summary of the Invention

[0005] Technical problems to be solved: Data collection capabilities are weak, and it is impossible to accurately obtain the moisture content of different soil layers and the water demand patterns of crops during the growth period. Water resource allocation is often based on experience, and there is a lack of multi-level water transfer strategies and dynamic water pressure balance control.

[0006] In view of the shortcomings of the existing technology, the present invention provides an intelligent irrigation station control system based on the Internet of Things, thereby solving the technical problems mentioned in the background technology.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: An IoT-based smart irrigation station control system includes a data acquisition layer, a data analysis layer, and device execution: The data collection layer includes water consumption and water supply collection. The data collection layer collects multi-dimensional data such as soil moisture, crop growth, weather, water consumption and water supply through a variety of sensors and metering equipment. The data analysis layer includes supply and demand relationship analysis and intelligent allocation analysis. Based on the collected data, the data analysis layer uses model algorithms to conduct supply and demand relationship analysis and intelligent allocation decision-making. The equipment execution layer includes the control execution of the irrigation station and the control execution of the water valve. Based on the analysis results, the equipment execution layer realizes the intelligent control, unmanned operation and energy-saving optimization of the water pump unit of the irrigation station, and at the same time performs remote opening adjustment, linkage scheduling and fault safety control of the water valve.

[0008] In a possible implementation, the water consumption collection is specifically as follows: Soil moisture monitoring: TRIME-PICO-IPH sensors are deployed, with one monitoring point for every 100 mu of farmland, buried at depths of 10 cm, 20 cm, and 40 cm. The sensors collect soil moisture and temperature every 15 minutes and transmit the data via LoRa. Crop growth monitoring: Using a RedEdge-P multispectral camera combined with a YOLOv8 algorithm visual terminal, it collects spectral indicators such as NDVI and PRI, as well as crop types and growth stages, every hour and transmits them via 5G. Meteorological data collection: Deploy VantagePro2 micro-weather station to monitor 12 parameters and upload data to the server via GPRS every 5 minutes; Water consumption terminal metering: Install E+H Promag W400 electromagnetic flowmeter with ±0.5% accuracy, and transmit flow data via NB-IoT once every minute; In a possible implementation, the water supply amount is collected as follows: Water source and quantity monitoring: SR50A ultrasonic water level meters and YSI6600V2 water quality sensors are deployed at water sources, transmitting turbidity, pH value and other data via 4G every 30 minutes; Water outlet metering at the pumping station: Install a Nivelco DUF600 Doppler flow meter with ±1% accuracy, transmitting data via LoRa every 5 minutes, and supporting solar power supply; Water pipeline monitoring: Rosemount 3051 pressure sensors and FLEXIM FLUX USG601 flow sensors are installed every 5 kilometers, and data is transmitted via industrial Ethernet + optical fiber; Reservoir capacity calculation: The Kongsberg EM2040 multi-beam bathymetric system is used to establish a reservoir capacity-water level model, and the reservoir capacity is automatically recalculated when the water level changes by more than 0.5 meters.

[0009] In a possible implementation, the supply and demand relationship analysis is specifically as follows: Water demand forecasting: Based on an LSTM neural network, historical water consumption, soil moisture, crop stage, and weather forecast are input, and the Adam optimizer is trained with an error of ±8%. Water demand curves are generated by crop type.

[0010] Water supply capacity assessment: River-type water supply points use the MIKE11 model to predict water inflow, according to the formula Calculate the adjustable water volume, where is the current storage capacity, To predict water inflow, is the ecological water demand, To reserve water, index, Assess reliability, where The successful duration of historical water supply, is the total water supply time, is the average water supply, is the average demand, The higher the value, the greater the water supply reliability.

[0011] Supply and demand balance algorithm: Divide the grid into 10km×10km, use linear programming model to solve the optimal water diversion plan, the objective function , constraining water supply, water demand and pipeline capacity, among which From the water supply point To the water point The unit water transfer cost is To adjust the water volume.

[0012] In one possible implementation, intelligent allocation analysis is used to establish a distance matrix between water supply points and water consumption points. The first-level water transfer range is a straight-line distance of ≤5 kilometers, the second-level water transfer range is 5-100 kilometers, and the cross-level water transfer range is >100 kilometers. Design distance priority coefficient , the calculation formula is: ,in For distance, is the attenuation coefficient, The larger the value, the higher the scheduling priority, ensuring that nearby water supply points participate in scheduling first; Level 1 water diversion: give priority to the nearest water supply point , calculate the available water Whether the water point is met Demand .like , then directly dispatch and adjust the water volume ;like , then enter the secondary water diversion; Secondary water diversion: Enable secondary water supply points by distance priority, and calculate the remaining water volume of each secondary water supply point after meeting its own primary water demand , secondary water supply point Remaining water ,in for First-level water point demand; check in order of priority Is it satisfied Remaining demand , until a suitable water supply point is found or inter-level water transfer is initiated; Inter-level water transfer: When the first and second level water transfer cannot meet the demand, the inter-regional water transfer mechanism is activated. First, all water supply points within a radius of 300 kilometers are searched, their remaining water volume and water transfer costs are calculated, and the water supply point with the lowest cost and sufficient water volume is selected for inter-level scheduling.

[0013] In a possible implementation, the pumping station controls execution, the pumping station Equipped with variable frequency speed regulating water pump unit, integrated with remote monitoring and control functions; The water valve control is executed by installing electric regulating valves and electromagnetic butterfly valves at key nodes of the water pipeline. The valve controller supports remote adjustment of 0-100% opening, with a response time of ≤5 seconds. The opening feedback signal is transmitted through 4-20mA analog quantity with an accuracy of ±0.5%.

[0014] Beneficial effects compared with existing technologies: 1. In this solution, by constructing a three-tier IoT architecture of "data collection - analysis and decision-making - device execution," the smart irrigation station control system achieves precise scheduling and efficient utilization of water resources. The system uses soil moisture sensors, multispectral imagers, and other equipment to collect real-time water and soil environment and crop growth data. Combining LSTM neural networks with linear programming algorithms, it dynamically models water demand and water supply capacity, keeping water volume prediction errors within ±8%. At the scheduling level, an innovative three-tier water diversion strategy with distance priority is designed. Level one water diversion ensures efficient water supply over short distances, while level two water diversion is supplemented by secondary networks within a 100-kilometer threshold. Cross-level water diversion overcomes regional restrictions and enables global resource allocation. Combined with EPANET water pressure simulation and dynamic balance control, the system ensures that the pressure in the water pipeline remains stable above 0.2 MPa. In actual application, the system has increased the water resource utilization rate in the basin from 65% to 88%, and reduced the comprehensive energy consumption of the irrigation station by 12%. At the same time, through equipment health management and abnormal emergency dispatch, the water supply guarantee rate has reached 98%, and the fault handling time has been shortened to within 30 minutes, significantly improving the intelligence and intensiveness of farmland irrigation. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention and implement it according to the contents of the specification, the following is a detailed description of the preferred embodiments of the present invention with reference to the accompanying drawings.

[0016] Figure 1 This is a schematic diagram of the regional division of the present invention; Figure 2 Schematic diagram of the system framework of the present invention. DETAILED DESCRIPTION

[0017] Preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. However, the present invention can be implemented in various forms, so the present invention is not limited to the embodiments described below. The technical solution in the embodiments of the present application is to solve the problems of the above-mentioned background technology, and the overall idea is as follows: Example: Please refer to Figure 1 As shown, this embodiment introduces a smart irrigation station control system based on the Internet of Things, which is as follows: 1. The data collection layer is used to collect water consumption data and water supply data. Water consumption data collection includes evenly distributing soil moisture sensors in each water use area, using a multispectral imager combined with AI visual recognition technology to monitor crop growth, setting up micro-meteorological stations to collect meteorological data, and installing electromagnetic flow meters on the water inlet pipes of water use points to measure water consumption. Water supply data collection includes deploying ultrasonic water level meters and water quality sensors at the water source in the water supply area, installing Doppler ultrasonic flow meters on the outlet mains of the irrigation station, installing pressure and flow sensors at key nodes of the water transmission pipeline, and using a multi-beam sounding system combined with a water level meter to estimate reservoir capacity. 1.1 Water consumption collection (1) Deployment of soil moisture sensors In each water-using area Soil moisture sensors, model TRIME-PICO-IPH, are evenly distributed throughout the farmland. These sensors can monitor soil moisture content, temperature, and other parameters in real time. One monitoring point is set up for every 100 mu of farmland, with sensors buried at depths of 10 cm, 20 cm, and 40 cm, respectively, to obtain moisture data for different soil layers. Data is collected every 15 minutes and transmitted to the regional gateway via the LoRa wireless communication module. (2) Crop growth status monitoring A multispectral imaging system combined with AI visual recognition technology is used: fixed multispectral cameras (such as RedEdge-P) are set up in the field to obtain spectral reflectance data of the crop canopy, focusing on monitoring indicators such as NDVI (Normalized Difference Vegetation Index) and PRI (Photochemical Reflectance Index). At the same time, AI visual recognition terminals (powered by the YOLOv8 algorithm) are deployed to identify crop types, growth stages, and pest and disease conditions in real time. Data from these two types of equipment are transmitted to the cloud platform via a 5G private network, with a collection frequency of once an hour. (3) Meteorological data collection A miniature weather station, model VantagePro2, is installed in each water-using area to monitor 12 parameters, including rainfall, wind speed, wind direction, air temperature, humidity, and solar radiation. The weather station is installed in an open area, 2.5 meters above the ground, and uploads data to the central server via GPRS communication. The data collection frequency is 5 minutes per time. (4) Water terminal metering At each water point An electromagnetic flowmeter (such as E+H Promag W400) is installed on the water inlet pipe. The diameter is adapted to the pipe size and the measurement accuracy is ±0.5%. The flowmeter is equipped with an NB-IoT communication module, which supports real-time flow measurement and cumulative water volume statistics. The data transmission frequency is 1 minute / time, ensuring high-precision collection of water consumption data. 1.2 Water supply collection (1) Water source and water quantity monitoring In each water supply area Ultrasonic water level meters (such as SR50A) and water quality sensors are deployed at water sources (such as reservoirs and river water intakes). The water level meter is installed in a fixed logging well, with a measurement range of 0-50 meters and an accuracy of ±1cm. It is connected to the data collector via the RS485 interface. The water quality sensor monitors indicators including turbidity, pH value, conductivity, dissolved oxygen, etc. The model is YSI6600V2, with a data collection frequency of 30 minutes / time, and is transmitted to the management platform via the 4G network. (2) Water output measurement at the pumping station At each pumping station A Doppler ultrasonic flowmeter (such as Nivelco DUF600) is installed on the outlet main, suitable for open channel or pipeline flow measurement, with a measurement accuracy of ±1%. The flowmeter is equipped with a solar power supply system and a LoRa communication module to achieve continuous monitoring under unattended conditions, with a data transmission frequency of 5 minutes. (3) Water pipeline monitoring Pressure sensors (such as the Rosemount 3051) and flow sensors are installed every 5 kilometers on the main water pipeline to monitor pipeline pressure and flow data in real time. The pressure sensor has a measurement range of 0-1.6 MPa and an accuracy of ±0.075%. The flow sensor uses a time-of-flight ultrasonic flowmeter (such as the FLEXIM FLUX USG601) with an accuracy of ±0.5%. The data is transmitted via industrial Ethernet to relay stations along the pipeline and then aggregated to the central control room via optical fiber. (4) Calculation of reservoir capacity For reservoir-type water supply points, a multi-beam bathymetry system (such as Kongsberg EM2040) is used to regularly measure reservoir capacity. This is combined with water level data to establish a reservoir capacity-water level relationship model. Daily monitoring uses water level gauge data to estimate reservoir capacity in real time. When the water level changes by more than 0.5 meters, a recalculation of reservoir capacity is automatically triggered to ensure the accuracy of water supply data. Second, the data analysis layer builds a water demand forecasting model and a water supply capacity assessment system based on the data collected by the data acquisition layer to analyze the supply and demand relationship. It also develops distance-priority scheduling strategies, multi-level water diversion decision-making models, dynamic water pressure balance control, and emergency scheduling solutions for abnormal conditions to achieve intelligent allocation analysis. 2.1 Analysis of supply and demand (1) Water demand prediction model A water consumption prediction model based on an LSTM (Long Short-Term Memory) network was constructed. The input variables included historical water consumption data (past 7 days, 30 days, and 90 days), soil moisture data, crop growth stage, and weather forecast data (rainfall, temperature, and evaporation for the next 7 days). The model was trained using the Adam optimizer with a learning rate of 0.001, a batch size of 64, and a training cycle of 200 rounds. The prediction error was kept within ±8%. Independent water demand models are established for different crop types (such as rice, corn, and wheat). Combined with the water demand patterns during the crop growth period (for example, the water demand during the tillering period of rice accounts for 30% of the entire growth period), a daily water demand curve is generated. For example, if 500 mu of rice is planted in a certain area, the daily water demand during the tillering period is calculated by the model as: (m³ / mu·day), where 80 is the unit water requirement parameter for rice in the tillering period in this area: (2) Water supply capacity assessment system A dynamic assessment model for available water at water supply points was established, taking into account factors such as current reservoir capacity / water level, upstream water inflow forecast, water quality, and ecological flow guarantee requirements. For river-type water supply points, the MIKE11 hydrological model was used to predict water inflow for the next seven days, and the available water volume was calculated in combination with reservoir scheduling rules: ,in is the current storage capacity, To predict water inflow, is the ecological water demand, To reserve water: The water supply reliability index (SPI) is introduced to comprehensively evaluate the water supply stability of each water supply point: the SPI calculation formula is: ,in The successful duration of historical water supply, is the total water supply time, is the average water supply, is the average demand: the higher the SPI value, the greater the water supply reliability: (3) Supply and demand balance analysis algorithm Develop a dual-dimensional supply and demand balance analysis algorithm in time and space. In the spatial dimension, the water supply grid is divided into 10 km × 10 km units, and the difference between the total water demand and the total water supply in each grid is calculated. In the temporal dimension, the supply and demand change trend in the next 1 day, 3 days, and 7 days is predicted: A linear programming model is used to solve the optimal regional supply and demand matching solution, and the objective function is to minimize the total water transfer cost: , the constraints include the maximum water supply at the water supply point, the minimum water demand at the water use point, the capacity limit of the water transfer pipeline, etc. From the water supply point To the water point The unit water transfer cost is To adjust the water volume: 2.2 Intelligent Allocation Analysis (1) Distance-priority scheduling strategy Establish a distance matrix between water supply points and water consumption points, and use the Dijkstra algorithm to calculate the shortest path: define the first-level water transfer range as a straight-line distance ≤ 5 kilometers, the second-level water transfer range as 5-100 kilometers, and the cross-level water transfer range as > 100 kilometers: like Figure 1 As shown, water points With water supply points The distance is 3 kilometers, which belongs to the first-level water diversion; The distance is 80 kilometers, which belongs to the second-level water diversion; similarly, the water supply point 、 、 Three points away from water points All are within 5-100 km, but water supply points 、 、 Distance to water point The distances are different, so the priority of water diversion (priority coefficient ) are also sorted by distance; Design distance priority coefficient , the calculation formula is: ,in is the distance (km), is the attenuation coefficient (take 0.05): The larger the value, the higher the scheduling priority, ensuring that nearby water supply points are given priority in scheduling: (2) Multi-level water transfer decision-making model Construct a three-level water transfer decision tree model (such as Figure 1 shown): Level 1 water diversion: give priority to the nearest water supply point , calculate the available water Whether the water point is met Demand :like , then directly dispatch and adjust the water volume ;like , then enter the secondary water diversion: Secondary water diversion: Enable secondary water supply points by distance priority, and calculate the remaining water volume of each secondary water supply point after meeting its own primary water demand : For example, secondary water supply points Remaining water ,in for First-level water point demand: check in order of priority Is it satisfied Remaining demand , until a suitable water supply point is found or inter-level water transfer is initiated: Inter-level water transfer: When the first and second level water transfer systems cannot meet demand, the inter-regional water transfer mechanism is activated. First, all water supply points within a 300-kilometer radius are searched, their remaining water volume and water transfer costs are calculated, and the water supply point with the lowest cost and sufficient water volume is selected for inter-level water transfer. (3) Dynamic water pressure balance control A water pressure simulation model for the water supply pipeline was established, and EPANET software was used to conduct a hydraulic analysis of the entire water supply network, simulating the water pressure distribution under different water diversion schemes. The minimum service water pressure at the end of the pipeline was set to 0.2 MPa. When the water pressure in a certain section of the pipeline fell below 0.15 MPa, the pump frequency of the upstream pumping station was automatically adjusted or the pressure reducing valve was opened to ensure stable water pressure. Develop a water pressure-flow linkage control algorithm that automatically calculates the required water pressure adjustment when the water flow rate changes by more than 10%: ,in is the pipe network characteristic coefficient, obtained by fitting historical data. The adjustment methods include water pump variable frequency speed regulation and valve opening adjustment, and the adjustment accuracy is controlled within ±0.02MPa: (4) Emergency dispatch for abnormal working conditions Develop emergency dispatch plans for abnormal operating conditions such as water supply pipeline leakage, water pump failure, and water source pollution: When a sudden drop in pipeline pressure (exceeding 0.3MPa / minute) or a sudden change in flow rate (exceeding 20%) is detected, the system automatically locates the leak point (with a positioning error of ≤500 meters) and initiates the following measures: Close the upstream and downstream valves of the leak point to isolate the faulty pipe section: Activate backup water supply lines and ensure water supply to affected areas through secondary or inter-level water diversion: Generate emergency water diversion plan and calculate minimum emergency water supply: , ensuring priority supply of domestic water for residents: In response to water source pollution incidents, a water quality early warning and emergency dispatch linkage mechanism is established: when water quality indicators (such as turbidity > 50 NTU) exceed the early warning threshold, the system automatically switches to the backup water source, initiates the contaminated water source treatment process, and adjusts the water diversion path to prevent contaminated water from entering the water supply network: Third, the equipment execution layer, based on the decision-making results of the data analysis layer, intelligently controls the pump units in the irrigation station, including variable frequency speed regulation, multi-pump linkage, and soft start control, enabling unmanned operation of the irrigation station. Energy management and energy-saving optimization are also performed simultaneously. Furthermore, intelligent control is performed on water valves, such as electric regulating valves and electromagnetic butterfly valves on the water pipeline, enabling coordinated scheduling, status monitoring, and maintenance of water valves. Data transmission and command exchange are carried out between each layer through the "5G+fiber+LoRa" hybrid IoT communication network. 3.1. Control and execution of irrigation stations Intelligent control of water pump units, irrigation stations Equipped with variable frequency speed control water pump units, model KQSN series centrifugal pumps, single unit flow rate 50-500m³ / h, head 30-120m, the pumping station equipment integrates remote monitoring and control functions: 3.2. Water valve control execution: Electric regulating valves (such as Fisher657 series) and electromagnetic butterfly valves (such as VTOND941X) are installed at key nodes of the water pipeline. The valve diameter is DN50-DN1200, and the control accuracy is ±1% of the opening: the valve controller supports remote adjustment of 0-100% opening, with a response time of ≤5 seconds. The opening feedback signal is transmitted via 4-20mA analog quantity with an accuracy of ±0.5%: In summary, if Figure 1 As shown, the system implementation example is as follows: 1. First-level water diversion According to the distance priority water supply rule, each water use area has a designated priority water supply point, such as the water supply point and The closest water supply point Through the irrigation station Prioritize water supply areas according to distance priority rules For water supply, similarly, water supply points Through the irrigation station Prioritize water supply areas according to distance priority rules to provide water; 2. Secondary water diversion According to the rules of the secondary water transfer area, such as water use points Except for the nearest water supply point In addition, according to the distance priority, there are 、 、 Three water supply points, when water supply points The water supply is not enough to support water points After the demand, according to the distance rule Distance ratio Nearly, the secondary water diversion is carried out in order of priority. For example, by calculating the water supply point Whether the water volume can meet the water consumption points In addition to demand, we can also supply If possible, open and The water supply network between the water supply points Water is diverted to water points ; If the water supply point The amount of water to meet the water point After the demand, it cannot be supplied , then the water supply points are given priority according to the distance , by calculating the water supply point Whether the water volume can meet the water consumption points In addition to demand, we can also supply If possible, open and The water supply network between the water supply points Water is diverted to water points ; If both the first-level water diversion and the second-level water diversion cannot meet the water demand If the demand is met, inter-regional water transfer will be implemented; 3. Inter-level water transfer The premise of cross-level water transfer is that the water supply of the first-level water transfer and the second-level water transfer water transfer points to which the water use point belongs cannot meet its water demand, such as Figure 1 Water Point As shown, the first-level water diversion and supply point is The secondary water diversion water supply point is 、 、 When using water First-level water diversion and supply point , Secondary water diversion and supply points 、 、 Unable to meet water needs hour; Prioritize water points according to the order of priority Whether the water supply point can meet the requirements; for example, the water point There are also secondary water diversion and supply points 、 、 , because of water supply points 、 Unable to meet water needs of water consumption, and water supply points also have The water consumption is abundant, but the water supply points Not a water point Therefore, we consider the water supply point The amount of water first supplied to , and then Supply to water points , forming cross-level mobilization of water resources; The premise of this cross-level transfer is still based on the priority of distance.

[0018] Finally, it should be noted that the above embodiments are merely examples for the purpose of illustrating the present invention and are not intended to limit the embodiments. Those skilled in the art will readily appreciate that other variations or modifications based on the above description are possible. It is not necessary and impossible to provide an exhaustive list of all embodiments. However, obvious variations or modifications arising therefrom remain within the scope of protection of the present invention.

Claims

1. A smart irrigation station control system based on the Internet of Things, characterized by: Including data collection layer, data analysis layer and device execution: The data collection layer includes water consumption and water supply collection. The data collection layer collects multi-dimensional data on soil moisture, crop growth, weather, water consumption, and water supply through a variety of sensors and metering equipment. The data analysis layer includes supply and demand relationship analysis and intelligent allocation analysis. Based on the collected data, the data analysis layer uses model algorithms to conduct supply and demand relationship analysis and intelligent allocation decision-making. The equipment execution layer includes the control execution of the irrigation station and the control execution of the water valve. Based on the analysis results, the equipment execution layer realizes the intelligent control, unmanned operation and energy-saving optimization of the water pump unit of the irrigation station, and at the same time performs remote opening adjustment, linkage scheduling and fault safety control of the water valve.

2. The smart irrigation station control system based on the Internet of Things according to claim 1, characterized in that: The water consumption is collected as follows: Soil moisture monitoring: TRIME-PICO-IPH sensors are deployed, with one monitoring point for every 100 mu of farmland, buried at depths of 10 cm, 20 cm, and 40 cm. The sensors collect soil moisture and temperature every 15 minutes and transmit the data via LoRa. Crop growth monitoring: Using a RedEdge-P multispectral camera combined with a YOLOv8 algorithm visual terminal, data on NDVI, PRI spectral indicators, crop type, and growth stage are collected hourly and transmitted via 5G. Meteorological data collection: Deploy VantagePro2 micro-weather station to monitor 12 parameters and upload data to the server via GPRS every 5 minutes; Water consumption terminal metering: Install E+H Promag W400 electromagnetic flowmeter with ±0.5% accuracy, and transmit flow data via NB-IoT once every minute.

3. The smart irrigation station control system based on the Internet of Things according to claim 1, characterized in that: The water supply amount is collected as follows: Water source and quantity monitoring: SR50A ultrasonic water level meters and YSI6600V2 water quality sensors are deployed at water sources, transmitting turbidity and pH value data via 4G every 30 minutes. Water outlet metering at the pumping station: Install a Nivelco DUF600 Doppler flow meter with ±1% accuracy, transmitting data via LoRa every 5 minutes, and supporting solar power supply; Water pipeline monitoring: Rosemount 3051 pressure sensors and FLEXIM FLUX USG601 flow sensors are installed every 5 kilometers, and data is transmitted via industrial Ethernet + optical fiber; Reservoir capacity calculation: The Kongsberg EM2040 multi-beam bathymetric system is used to establish a reservoir capacity-water level model, and the reservoir capacity is automatically recalculated when the water level changes by more than 0.5 meters.

4. The smart irrigation station control system based on the Internet of Things according to claim 1, characterized in that: The supply and demand relationship analysis is as follows: Water demand forecasting: Based on an LSTM neural network, historical water consumption, soil moisture, crop stage, and weather forecast are input, and the Adam optimizer is trained with an error of ±8%. Water demand curves are generated by crop type. Water supply capacity assessment: River-type water supply points use the MIKE11 model to predict water inflow, according to the formula Calculate the adjustable water volume, where is the current storage capacity, To predict water inflow, is the ecological water demand, To reserve water, index, Assess reliability, where The successful duration of historical water supply, is the total water supply time, is the average water supply, is the average demand, The higher the value, the greater the water supply reliability; Supply and demand balance algorithm: Divide the grid into 10km×10km, use linear programming model to solve the optimal water diversion plan, the objective function , constraining water supply, water demand and pipeline capacity, among which From the water supply point To the water point The unit water transfer cost is To adjust the water volume.

5. The IoT-based smart irrigation station control system according to claim 1, characterized in that: Intelligent allocation analysis to establish a distance matrix between water supply points and water use points. The first-level water transfer range is a straight-line distance of ≤5 kilometers, the second-level water transfer range is 5-100 kilometers, and the cross-level water transfer range is >100 kilometers; Design distance priority coefficient , the calculation formula is: ,in For distance, is the attenuation coefficient, The larger the value, the higher the scheduling priority, ensuring that nearby water supply points participate in scheduling first; Level 1 water diversion: give priority to the nearest water supply point , calculate the available water Whether the water point is met Demand .like , then directly dispatch and adjust the water volume ;like , then enter the secondary water diversion; Secondary water diversion: Enable secondary water supply points by distance priority, and calculate the remaining water volume of each secondary water supply point after meeting its own primary water demand , secondary water supply point Remaining water ,in for First-level water point demand; check in order of priority Is it satisfied Remaining demand , until a suitable water supply point is found or inter-level water transfer is initiated; Inter-level water transfer: When the first and second level water transfer cannot meet the demand, the inter-regional water transfer mechanism is activated. First, all water supply points within a radius of 300 kilometers are searched, their remaining water volume and water transfer costs are calculated, and the water supply point with the lowest cost and sufficient water volume is selected for inter-level scheduling.

6. The IoT-based smart irrigation station control system according to claim 1, characterized in that: The irrigation station controls the execution of the irrigation station. Equipped with variable frequency speed regulating water pump unit, integrated with remote monitoring and control functions; The water valve control is executed by installing electric regulating valves and electromagnetic butterfly valves at key nodes of the water pipeline. The valve controller supports remote adjustment of 0-100% opening, with a response time of ≤5 seconds. The opening feedback signal is transmitted through 4-20mA analog quantity with an accuracy of ±0.5%.

Images