Farmland intelligent monitoring spraying system and method based on Internet of Things

Abstract

The invention relates to the technical field of agricultural Internet of Things and intelligent irrigation, and discloses an intelligent farmland monitoring and spraying system and method based on the Internet of Things. The system comprises a sensing layer, a network layer, a control layer and an execution layer, the sensing layer collects multi-dimensional parameters of soil, crops and environment through multiple sensors according to a differentiation period, and the multi-dimensional parameters are transmitted to the control layer through encrypted dual-mode communication; the control layer processes the data and then compares the data with a crop growth period water demand model, and a decision module dynamically divides irrigation partitions, sorts priorities, optimizes an alternating period in combination with a wind speed, and generates a control instruction; the execution layer is linked with the partition spraying device and the flow control module to perform accurate spraying, and the sensing layer performs high-frequency feedback to realize closed-loop correction. According to the invention, soil-crop-environment collaborative perception and dynamic adaptive irrigation are realized, the irrigation accuracy and the water resource utilization rate are improved, the system is adaptive to large-scale farmlands of different crops and terrains, and water-saving and intelligent development of agriculture is assisted.

Description

Technical Field

[0001] This invention relates to the field of agricultural Internet of Things (IoT) and smart irrigation technology, and more specifically, to an IoT-based smart monitoring and spraying system and method for farmland. Background Technology

[0002] Existing farmland irrigation technology has undergone a development process from traditional extensive methods to preliminary intelligent methods. Traditional irrigation mainly adopts flood irrigation, furrow irrigation and other methods, relying on human experience to judge the timing and amount of irrigation. With the rise of agricultural Internet of Things technology, some farmland has begun to introduce intelligent irrigation equipment. By deploying basic monitoring components such as soil temperature and humidity sensors, combined with timed control or simple threshold triggering mechanisms, irrigation operations are realized. Some systems are trying to apply alternating irrigation technology, which performs irrigation switching according to fixed zones and fixed cycles to reduce water consumption. These technologies have reduced the intensity of manual labor to a certain extent and improved the problem of the extensive nature of traditional irrigation.

[0003] However, existing technologies still have several prominent shortcomings: First, the monitoring dimensions are limited. Most systems only collect single parameters such as soil temperature and humidity, failing to combine soil fertility, crop physiological status (e.g., canopy temperature), and environmental dynamics (e.g., light, wind speed, and precipitation) for multi-dimensional collaborative sensing. This results in irrigation decisions lacking comprehensive data support and making it difficult to match the actual water requirements of crops. Second, the alternating irrigation patterns are rigid. Existing alternating irrigation systems mostly use preset fixed zones and fixed cycles, failing to consider soil differences within farmland, uneven crop growth, and dynamic water requirement differences caused by environmental changes. This leads to inconsistencies in water requirements in some areas. The system suffers from several problems: insufficient irrigation, excessive irrigation in some areas, and low irrigation accuracy; insufficient intelligence and collaboration, with a lack of efficient linkage between data collection, processing, and irrigation execution, and the absence of a dynamically adaptable decision-making model, making it difficult to adjust irrigation strategies in real time according to changes in crop growth stages and environmental fluctuations; and a lack of system adaptability and stability, with existing equipment mostly designed for single terrains and single crops, resulting in low modularity and difficulty in adapting to different terrains such as plains and hills, as well as the planting needs of various grain and cash crops. Furthermore, the communication links lack redundancy design, making it easy for irrigation operations to be interrupted or malfunctioned when the network is interrupted.

[0004] It is evident that existing intelligent irrigation systems for farmland have shortcomings in multi-parameter collaborative monitoring, dynamic alternating irrigation decision-making, multi-scenario adaptability, and closed-loop control, failing to meet the actual needs of large-scale agriculture for precise water conservation and efficient management. Therefore, there is an urgent need for an intelligent monitoring and spraying system and method for farmland that integrates multi-dimensional precise monitoring via the Internet of Things, dynamic adaptive alternating irrigation decision-making, multi-scenario compatibility, and closed-loop feedback control. This would address issues such as low water resource utilization, poor matching between irrigation and crop needs, and insufficient intelligence in existing technologies, thereby promoting the upgrading of agricultural irrigation towards precision, water conservation, and intelligence. Summary of the Invention

[0005] In view of this, the present invention proposes an intelligent monitoring and spraying system and method for farmland based on the Internet of Things, aiming to solve the problems of low water resource utilization, poor matching between irrigation and crop needs, and insufficient intelligence in the current technology.

[0006] This invention proposes an intelligent monitoring and spraying system and method for farmland based on the Internet of Things, comprising: It includes a perception layer, a network layer, a control layer, and an execution layer that work together, with each layer forming a closed-loop control based on data interaction and command transmission; The sensing layer is equipped with several monitoring units arranged in zones as needed. Each unit integrates soil temperature and humidity sensors, crop canopy temperature sensors, and environmental sensors to collect soil conditions, crop water requirements, and environmental influencing factors, thereby achieving synchronous collection of multi-dimensional parameters. The network layer includes an IoT communication module and a data relay gateway adapted to the monitoring unit, which undertakes bidirectional data transmission, command issuance and encryption protection functions for each layer; The control layer is the core decision-making unit, including a data processing module, a decision-making module and a storage module. The decision-making module pre-stores water requirement models for different crop growth stages and a dynamic alternating irrigation rule base, and can generate targeted irrigation parameters based on monitoring data. The execution layer includes a zoned spraying device, a flow control module, and a drive module. The drive module receives instructions from the control layer and coordinates the spraying device and the flow control module to achieve precise alternating spraying.

[0007] Furthermore, the monitoring unit also integrates a soil conductivity sensor, which works in conjunction with a soil temperature and humidity sensor to collect soil state parameters, which together reflect soil fertility and salinization, providing comprehensive soil condition support for adjusting irrigation parameters. The environmental sensor is a multi-parameter combined sensor, including at least a light sensor, a wind speed sensor, and a precipitation sensor, which respectively capture light intensity, air flow status, and natural precipitation.

[0008] Furthermore, the IoT communication module is a wireless communication module adapted to the complex outdoor environment of agriculture, supporting single or multiple combined communication modes, and has the function of adaptively switching communication modes according to signal coverage and transmission requirements when used in combination. The gateway integrates a protocol conversion unit, which can achieve compatible conversion between different communication protocols, and has the functions of data caching when the network is interrupted and retransmission after the network is restored.

[0009] Furthermore, the alternating irrigation rule base includes dynamic irrigation zone division rules, irrigation priority ranking rules, and alternating cycle adjustment rules. These three work together to divide irrigation demand zones based on soil and crop parameters, rank irrigation according to the urgency of water demand, and adjust irrigation intervals in conjunction with environmental parameters.

[0010] Furthermore, the zoned spraying device is configured according to independent irrigation zones, with each zone corresponding to a set of independently controllable spraying components. The spraying components include irrigation nozzles with adjustable spray angle and coverage area, and solenoid valves for controlling the on / off state of the zone. The flow control module integrates flow detection elements and flow regulation equipment to form a closed-loop control, which is used to ensure that the actual irrigation volume is consistent with the decision parameters.

[0011] Furthermore, an IoT-based intelligent monitoring and spraying method for farmland includes the following steps: S1: Each monitoring unit in the sensing layer synchronously collects soil conditions, crop water requirements, and environmental influencing factors related to the corresponding zone according to a preset cycle, and transmits them to the control layer through network encryption. S2: The control layer data processing module performs outlier removal, data noise reduction and normalization on the collected data, and compares the standardized effective data with the crop growth period water requirement model and soil moisture threshold stored in the storage module. S3: The decision module divides irrigation zones, determines irrigation priorities and alternation rules based on the comparison results, and generates control instructions that include solenoid valve switching timing and flow regulation parameters. S4: The execution layer driver module parses instructions, links the zoned spraying device and the flow control module, and realizes alternating zoned spraying according to the decision rules; S5: During irrigation, the sensing layer provides real-time feedback on changes in soil moisture, and the decision-making module dynamically adjusts irrigation parameters until each zone meets the irrigation target.

[0012] Furthermore, the collection period for different types of parameters in step S1 can be configured independently to adapt to the crop growth stage and the rate of environmental change. During collection, a timestamp with a unified time base is recorded synchronously to ensure the consistency of data time sequence.

[0013] Furthermore, in step S3, the irrigation zones are divided into water-demand zones, temporarily suspended irrigation zones, and prohibited irrigation zones. The division is based on whether the soil condition parameters meet the water requirements of the crop during its current growth period, whether the crop's water requirements are obvious, and whether there is natural precipitation replenishment.

[0014] Furthermore, in step S3, irrigation priorities are ranked comprehensively based on soil condition differences and the urgency of crop water demand, with higher priority for zones with more urgent water needs; the adjustment of the alternation cycle is related to wind speed in environmental parameters, and water drift loss is reduced by optimizing the interval duration.

[0015] Furthermore, the feedback adjustment in step S5 forms a closed-loop control. After a certain zone reaches the irrigation target, the decision module adjusts the irrigation parameters of subsequent zones based on its actual irrigation effect and the real-time soil moisture of the remaining zones to ensure the uniformity of irrigation for the entire farmland.

[0016] Compared with the prior art, the beneficial effects of the present invention are as follows: By integrating soil temperature and humidity, crop canopy temperature, soil conductivity, and multi-dimensional environmental sensors in the sensing layer, the system achieves collaborative perception of soil conditions, crop physiological water requirements, and environmental influencing factors, overcoming the limitations of existing technologies with their single monitoring dimension. Relying on pre-stored multi-crop growth stage water requirement models and a dynamic alternating irrigation rule base in the control layer, the system dynamically divides irrigation zones, prioritizes irrigation, and adjusts alternating cycles accordingly. This breaks the rigidity of traditional fixed alternating irrigation patterns, ensuring a high degree of compatibility between irrigation strategies and real-time crop water requirements. Through the encrypted transmission, cached data transfer, and closed-loop data interaction between layers via the IoT communication module and gateway, the system achieves efficient linkage between data processing, decision generation, and irrigation execution, addressing the shortcomings of existing technologies in terms of intelligence and collaboration. Furthermore, the system adopts a modular design, supporting flexible adaptation to different terrains and crops, improving application stability and scenario compatibility. This effectively solves the core pain points of existing technologies, such as low water resource utilization, poor irrigation adaptability, and limited intelligence, helping agricultural irrigation move towards a virtuous cycle of precise regulation, water-saving operation, and intelligent management. Attached Figure Description

[0017] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 A schematic diagram of the architecture of an IoT-based intelligent farmland monitoring and spraying system is provided for an embodiment of the present invention: Figure 2 A flowchart illustrating a smart monitoring and spraying method for farmland based on the Internet of Things (IoT) provided in this embodiment of the invention. Detailed Implementation

[0018] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the disclosure to those skilled in the art. It should be noted that, unless otherwise specified, embodiments and features in the embodiments of the present invention can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0019] like Figures 1-2As shown in some embodiments of this application, this embodiment provides an IoT-based intelligent farmland monitoring and spraying system, including: The perception layer, network layer, control layer and execution layer work together, and each layer forms a closed-loop control based on data interaction and command transmission. The sensing layer is equipped with several monitoring units arranged in zones as needed. Each unit integrates soil temperature and humidity sensors, crop canopy temperature sensors, and environmental sensors to collect soil conditions, crop water requirements, and environmental influencing factors, thereby achieving synchronous collection of multi-dimensional parameters. The network layer includes an IoT communication module and a data relay gateway adapted to the monitoring unit, which undertakes bidirectional data transmission, command issuance and encryption protection functions for each layer; The control layer is the core decision-making unit, including a data processing module, a decision-making module and a storage module. The decision-making module pre-stores water requirement models for different crop growth stages and a dynamic alternating irrigation rule base, and can generate targeted irrigation parameters based on monitoring data. The execution layer includes a zoned spraying device, a flow control module, and a drive module. The drive module receives instructions from the control layer and coordinates the spraying device and the flow control module to achieve precise alternating spraying.

[0020] Specifically, such as Figure 1 As shown, the monitoring unit also integrates a soil conductivity sensor, which works in conjunction with a soil temperature and humidity sensor to collect soil state parameters. Together, these parameters are used to reflect soil fertility and salinization, providing comprehensive soil condition support for adjusting irrigation parameters. The environmental sensor is a multi-parameter combined sensor, including at least a light sensor, a wind speed sensor, and a precipitation sensor, which respectively capture light intensity, air flow status, and natural precipitation.

[0021] It is understood that the monitoring unit integrates a soil conductivity sensor and is deployed in conjunction with a soil temperature and humidity sensor. The soil temperature and humidity sensor's measurement range covers common temperature and humidity ranges in farmland soil, while the soil conductivity sensor's measurement range is adapted to the detection needs of farmland soil fertility and salinity. Both sensors synchronously collect data at a 5-10 minute acquisition cycle and perform complementary verification. Simultaneously, the sensor's burial depth can be adjusted according to crop root distribution. Together, they accurately capture changes in soil temperature and humidity, fertility levels, and salinity levels. Combined with pre-stored water requirement models for different crop growth stages in the control layer, this provides comprehensive soil physicochemical status data for the dynamic adjustment of irrigation volume and intervals. The system is supported by location data. The environmental sensors are designed with a combination of multiple parameters, including light intensity, wind speed, and precipitation. The light intensity sensor covers the changes in light intensity in farmland at different times of day. The wind speed sensor can accurately capture common wind speed ranges that affect the drift of irrigation water resources. The precipitation sensor has the resolution to identify trace amounts of precipitation. The three sensors capture relevant environmental parameters in real time at a collection cycle of 10 to 30 minutes. The collected data forms a multi-dimensional linked dataset with soil and crop parameters. Furthermore, the installation height of the environmental sensors is adapted to the growth height of different crops to ensure the accuracy of data collection. This provides an environmental correlation decision-making basis for the periodic adjustment and priority ranking in the alternating irrigation rule base of the control layer. This design overcomes the limitations of existing technologies that only monitor basic soil temperature and humidity, relying solely on a single dimension. By clearly defining the sensor's measurement range, data acquisition cycle, and installation specifications, it achieves precise and coordinated sensing of parameters across the entire soil-crop-environment chain. This allows irrigation decisions to be dynamically adjusted based on specific soil fertility and salinity levels, preventing indiscriminate irrigation from exacerbating salinization or causing fertility loss. Furthermore, it can dynamically respond to the impact of environmental fluctuations on irrigation effectiveness based on real-time environmental data (such as adjusting irrigation angles when wind speed exceeds specific values ​​or reducing irrigation volume when rainfall reaches a certain level). This significantly reduces water drift waste and irrigation delays, further improving the alignment between irrigation strategies and actual crop water requirements. Standardized sensor parameters and installation specifications enhance the reliability of data acquisition and the system's practicality, reinforcing the system's multiple advantages of precise water conservation, soil ecological protection, and efficient irrigation. Moreover, the data collected by the crop canopy temperature sensor is not used in isolation but is analyzed in conjunction with air temperature and light intensity data collected by the environmental sensors. The decision-making module pre-stores the correlation between the canopy-air temperature difference (ΔT) and the degree of water stress based on a crop physiological model. Under strong light, the normal ΔT range differs from that under weak light. By comprehensively analyzing ΔT and light intensity, the system can more accurately determine whether the crop's temperature rise is due to normal transpiration or abnormal temperature rise caused by stomatal closure due to water shortage. This allows for a more accurate assessment of the crop's water urgency and avoids misjudgments that may arise from relying solely on canopy temperature as a single indicator.

[0022] Specifically, such as Figure 1As shown, the IoT communication module is a wireless communication module adapted to the complex outdoor environment of agriculture. It supports single or multiple combined communication modes and has the function of adaptively switching communication modes according to signal coverage and transmission requirements when used in combination. The gateway integrates a protocol conversion unit, which can achieve compatible conversion between different communication protocols, and has the functions of data caching when the network is interrupted and retransmission after the network is restored.

[0023] It is understood that the IoT communication module uses wireless communication modules such as LoRa, NB-IoT, and 5G, which are adapted to the complex outdoor environment of agriculture. It supports single deployment or multiple combinations. Among them, the LoRa module has a communication distance of ≥3km and a receiving sensitivity of ≤-148dBm, which is suitable for long-distance low-power transmission requirements; the NB-IoT module supports eDRX mode and power consumption of ≤10μA, which is suitable for wide coverage and low data volume scenarios; the 5G module supports SA standalone networking and a transmission rate of ≥100Mbps, which is suitable for high-concurrency data transmission requirements. When used in combination, the communication mode can be adaptively switched according to the signal coverage strength of the farmland (e.g., switching to LoRa mode when the signal strength is <-100dBm) and the data transmission priority. The gateway integrates a conversion unit that supports protocols such as MQTT, TCP / IP, and Modbus, which can realize protocol compatibility conversion between different communication modules and the control layer. The gateway has a built-in local cache unit of ≥16GB, which can store at least 72 hours of monitoring data and control commands when the network is interrupted, and automatically retransmit them in timestamp order after the network is restored. This design solves the problems of poor adaptability and unstable signal of existing agricultural communication modules. By clarifying the core parameters of the module and the adaptive switching logic, it ensures full signal coverage of farmland with different terrains such as plains and hills. At the same time, the gateway's protocol conversion function improves system compatibility, and the buffering and retransmission mechanism avoids data loss or irrigation command errors caused by network interruption. It significantly improves the reliability of data transmission and the stability of system operation, adapts to the remote monitoring and irrigation control needs of large-scale farmland, and reduces water waste and irrigation errors caused by communication problems.

[0024] Specifically, such as Figure 1 As shown, the alternating irrigation rule base includes dynamic irrigation zone division rules, irrigation priority ranking rules, and alternating cycle adjustment rules. The three work together to divide irrigation demand zones based on soil and crop parameters, rank them according to the urgency of water demand, and adjust irrigation intervals in combination with environmental parameters.

[0025] It is understandable that the alternating irrigation rule base includes dynamic irrigation zoning rules, irrigation priority ranking rules, and alternating cycle adjustment rules that work in synergy. The dynamic zoning rules are not executed all at once, but rather at the beginning of each decision cycle, recalculating and dividing the entire field based on the latest monitoring data to achieve true "dynamic" zoning. The irrigation priority ranking rules employ a quantitative weighted scoring mechanism, for example: Priority Score = (Soil Moisture Deficit × Weight W1) + (Crop Water Stress Index × Weight W2) - (Recent Effective Rainfall Compensation × Weight W3). The irrigation order is determined based on the score. The crop water stress index is derived from the aforementioned synergistic analysis of canopy-air temperature difference (ΔT) and light data. The alternating cycle adjustment rules not only consider reducing drift but also ensure irrigation effectiveness. When wind speed exceeds a threshold, the system evaluates and extends the interval, essentially waiting for a more suitable microclimate window for irrigation. All three rely on pre-stored multi-crop growth stage water requirement models and soil moisture threshold databases in the control layer to generate irrigation logic adapted to the current farmland conditions through multi-dimensional parameter linkage. This design completely breaks the rigid mode of fixed zones and fixed cycles in traditional alternating irrigation, solving the pain point of poor adaptability of existing irrigation technologies to dynamic crop water requirements and environmental changes. Through quantitative judgment standards and dynamic adjustment logic, irrigation decisions are made more accurately to meet the actual needs of farmland, avoiding both insufficient or excessive irrigation in some areas, reducing water waste caused by environmental factors, significantly improving irrigation uniformity and water resource utilization, and enhancing the scientific nature and flexibility of system decision-making to adapt to the large-scale irrigation needs of different crops and environments.

[0026] Specifically, such as Figure 1 As shown, the zoned spraying device is configured according to independent irrigation zones, and each zone corresponds to a set of independently controllable spraying components. The spraying components include irrigation nozzles with adjustable spray angle and coverage area, and solenoid valves for controlling the on / off state of the zone. The flow control module integrates flow detection elements and flow regulation equipment to form a closed-loop control, which is used to ensure that the actual irrigation volume is consistent with the decision parameters.

[0027] Understandably, the zonal spraying device divides the area into independent irrigation zones of 3-10 mu / zone. Each zone is equipped with an independently controllable spraying assembly. The irrigation nozzles in the assembly support a continuously adjustable spraying angle of 30° to 360°, with a spraying radius covering 3-8m, adapting to different crop planting densities and zone shapes. The solenoid valve adopts a waterproof design with a response time ≤50ms and a leakage rate ≤0.1mL / min, ensuring the accuracy and sealing of zone on / off control. The flow control module integrates an electromagnetic flow sensor and a variable frequency centrifugal water pump. The flow sensor has a measurement range of 5-60m. 3With a flow rate of / h and an accuracy of ≤±0.5%FS, it can capture water flow changes in real time. The variable frequency water pump has a power of 3~15kW and a flow rate adjustment range of 10~50m³ / h. 3 With a pressure regulation accuracy of ≤±0.02MPa, the system utilizes real-time feedback data from a flow sensor and dynamic pump adjustment to form a closed-loop control, ensuring a high degree of consistency between the actual irrigation volume and the control layer's decision parameters. This design solves the problems of uneven coverage and uncontrolled flow in existing zoned irrigation systems. Independent spray components and adjustable nozzles ensure no dead zones in irrigation, while high-response solenoid valves prevent cross-contamination between zones. Closed-loop flow control significantly reduces irrigation volume errors, minimizing water waste and crop drought / flood risks caused by improper flow. It also adapts to the irrigation needs of different crops in different zones, improving overall irrigation uniformity and accuracy, and providing hardware support for efficient water-saving irrigation in large-scale farmland.

[0028] In some embodiments of this application, such as Figure 2 As shown in the figure, this embodiment provides a smart monitoring and spraying method for farmland based on the Internet of Things, including the following steps: S1: Each monitoring unit in the sensing layer synchronously collects soil conditions, crop water requirements, and environmental influencing factors related to the corresponding zone according to a preset cycle, and transmits them to the control layer through network encryption. S2: The control layer data processing module performs outlier removal, data noise reduction and normalization on the collected data, and compares the standardized effective data with the crop growth period water requirement model and soil moisture threshold stored in the storage module. S3: The decision module divides irrigation zones, determines irrigation priorities and alternation rules based on the comparison results, and generates control instructions that include solenoid valve switching timing and flow regulation parameters. S4: The execution layer driver module parses instructions, links the zoned spraying device and the flow control module, and realizes alternating zoned spraying according to the decision rules; S5: During irrigation, the sensing layer provides real-time feedback on changes in soil moisture, and the decision-making module dynamically adjusts irrigation parameters until each zone meets the irrigation target.

[0029] Understandably, in S1, each monitoring unit in the sensing layer synchronously collects parameters according to differentiated preset cycles. Soil state parameters (including temperature, humidity, and electrical conductivity) are collected every 5-10 minutes, while crop water requirement characteristics (canopy temperature) and environmental influencing factors (light, wind speed, and precipitation) are collected every 10-30 minutes. The collected data is encrypted using AES-128 and transmitted to the control layer via an IoT communication module (LoRa / NB-IoT / 5G compatible switching) and gateway, ensuring data transmission security and stability. In S2, the control layer data processing module uses the 3σ criterion to remove outliers caused by sensor malfunctions or interference, filters random noise using a moving average filtering algorithm, and then performs Min-Max normalization to unify the multi-dimensional data dimensions. Subsequently, the standardized valid data is combined with pre-stored multi-crop growth stage water requirement models (adapted to different growth stages of food and cash crops) and targeted soil moisture thresholds in the storage module. Multi-dimensional comparative analysis; In S3, the decision module, based on the comparison results and combined with the alternating irrigation rule base, accurately divides the water-demand zone, the temporarily suspended irrigation zone, and the prohibited irrigation zone. It determines the irrigation priority according to the soil moisture deficiency and the urgency of crop water demand, and generates control signals including solenoid valve switching sequence, flow regulation parameters, and nozzle angle adjustment commands by combining environmental parameters (such as adjusting the alternation interval when the wind speed is >3m / s); In S4, the execution layer drive module quickly parses the commands and links the waterproof solenoid valve (response time ≤50ms), adjustable nozzle, and electromagnetic flow sensor and variable frequency water pump of the flow control module of the zoned spraying device to achieve precise alternating spraying of zones according to the decision rules; In S5, the sensing layer transmits soil moisture change data in real time at a feedback cycle of 2-5 minutes / time. The decision module dynamically corrects the irrigation amount, irrigation duration, and alternation interval of subsequent zones until the soil moisture of each zone accurately matches the water demand threshold of the corresponding crop at the current growth stage. This closed-loop process of "collection-processing-decision-execution-feedback" overcomes the pain points of existing technologies, such as fragmented processes, delayed responses, and rigid decision-making. Differentiated collection and encrypted transmission ensure data timeliness and security, while precise data processing algorithms eliminate invalid interference and improve data reliability. The dynamic decision-making mechanism allows irrigation strategies to closely align with soil conditions, crop needs, and environmental changes. Real-time feedback corrections prevent insufficient or excessive irrigation, significantly reducing water waste and the risk of soil salinization. It also adapts to the needs of large-scale farmland with different crops and terrains, improving irrigation uniformity and crop growth consistency, enhancing the system's intelligence, precision, and practicality, and providing full-process technical support for efficient water-saving irrigation in agriculture. The control logic of this method is embodied in "feedforward-feedback composite control." S2 and S3 constitute the feedforward control core, which pre-calculates and generates a set of optimal irrigation instructions based on models and real-time sensing data. S4 and S5 constitute the feedback control loop, which monitors the irrigation effect online through high-frequency soil moisture feedback during instruction execution and dynamically corrects subsequent unexecuted instructions in real time (such as fine-tuning flow rate and duration).This composite control mode leverages both model-based prediction and planning capabilities, and the ability to correct for uncertainties such as soil spatial variability and equipment errors, thereby achieving higher precision irrigation control.

[0030] Specifically, such as Figure 2 As shown, the collection period of different types of parameters in step S1 can be configured independently to adapt to the crop growth stage and the rate of environmental change. During collection, a timestamp with a unified time base is recorded synchronously to ensure the consistency of data time sequence.

[0031] It is understandable that the acquisition cycle of different types of parameters in step S1 can be independently customized through the remote interaction module or the local configuration interface. Soil state parameters (temperature, humidity, electrical conductivity) can be configured to 5-10 minutes / time, crop water requirement characteristic parameters (canopy temperature) can be configured to 10-15 minutes / time, and environmental influencing factor parameters (light, wind speed, precipitation) can be configured to 15-30 minutes / time. It can be flexibly adapted to different crop growth stages (e.g., the soil parameter acquisition cycle can be shortened to 5 minutes during the seedling stage when water requirements are sensitive, and extended to 10 minutes during the maturity stage) and environmental change rates (e.g., the acquisition cycle of precipitation parameters can be shortened to 15 minutes during the rainy season and extended to 30 minutes during the dry season). During the acquisition process, the control layer clock synchronization module provides a unified time reference (supports regular calibration of NTP protocol, with a time error ≤10ms), and synchronously records a standard format timestamp containing year, month, day, hour, minute, and second. The timestamp is bound and stored one by one with the acquired parameters to ensure that the three types of data—soil, crop, and environment—are completely aligned in the time series dimension. This design addresses the limitations of existing technologies, such as fixed data collection cycles that cannot adapt to crop growth dynamics and environmental fluctuations. Independent configuration allows collection strategies to better align with real-world application scenarios, avoiding data lag due to excessively long cycles or resource redundancy caused by excessively short cycles. A unified time base timestamp ensures the temporal consistency of multi-dimensional data, providing precise temporal support for subsequent data fusion processing and irrigation decision analysis. It facilitates tracing the correlation between changes in different parameters (such as the temporal correlation between changes in light intensity and crop canopy temperature), further enhancing the scientific nature of decision-making logic and data reliability. Simultaneously, it strengthens the system's flexibility and adaptability, meeting the personalized monitoring needs of different crops and planting scenarios, and laying a solid data foundation for precise irrigation decisions.

[0032] Specifically, such as Figure 2 As shown, in step S3, the irrigation zones are divided into water-demand zones, temporarily suspended irrigation zones, and prohibited irrigation zones. The division is based on whether the soil condition parameters meet the water requirements of the crop during its current growth period, whether the crop's water requirements are obvious, and whether there is natural precipitation replenishment.

[0033] Understandably, in step S3, the irrigation zones are precisely divided into water-demand zones, temporarily suspended irrigation zones, and prohibited irrigation zones based on three core criteria: whether the soil state parameters (temperature, humidity, electrical conductivity) have reached the water demand threshold for the current growth stage of the crop, combined with the degree of water demand characteristics reflected by the crop canopy temperature (if the canopy temperature is consistently higher than the suitable range, the water demand characteristics are significant), and whether the natural precipitation in the environmental parameters has reached the effective replenishment threshold (if a single precipitation of ≥5mm is considered effective replenishment). The three criteria work together and are compared with the multi-crop growth stage water demand model stored in the storage module to clarify the judgment boundaries of the water-demand zone (parameters do not meet the requirements, water demand is obvious, and there is no effective precipitation), the temporarily suspended irrigation zone (parameters are close to the threshold, water demand is not obvious, and there is no effective precipitation), and the prohibited irrigation zone (parameters meet the requirements or there is effective precipitation replenishment). This design addresses the problems of existing irrigation zoning technologies being too broad and based on a single criterion. By using multi-dimensional parameters for collaborative judgment, the zoning results are made more closely aligned with the actual water needs of farmland, avoiding under- or over-irrigation caused by misjudgments based on a single indicator. This reduces water waste and accurately matches the actual water needs of crops in different areas, providing a scientific basis for subsequent irrigation priority ranking and alternation rule formulation. It further improves the rationality and accuracy of irrigation decisions and adapts to the differentiated irrigation needs of large-scale farmland.

[0034] Specifically, such as Figure 2 As shown, in step S3, irrigation priority is sorted by soil condition differences and the urgency of crop water demand, with higher priority for zones with more urgent water demand; the adjustment of the alternation cycle is related to wind speed in the environmental parameters, and water drift loss is reduced by optimizing the interval duration.

[0035] Understandably, in step S3, irrigation priority adopts a weighted comprehensive ranking mechanism. Soil condition differences (with soil moisture deficiency value and electrical conductivity deviating from the suitable range of crop growth period as core indicators) account for 0.6% of the weight, and the urgency of crop water demand (based on the magnitude and duration of canopy temperature exceeding the suitable range) accounts for 0.4% of the weight. The ranking results are generated through quantitative scoring. Among them, the zones with soil moisture deficiency value >15% or canopy temperature continuously higher than 32℃ are judged as having the most urgent water demand and the highest priority. The alternation cycle adjustment is precisely linked with real-time wind speed. Referring to the pre-stored wind speed-interval adaptation model, when the wind speed is ≤3m / s, the basic alternation interval is adopted. When the wind speed is 3-6m / s, the interval is extended by 20%-30%. When the wind speed is >6m / s, the interval is extended by 50% or the irrigation of non-core high-priority zones is suspended. The water resource drift caused by high wind is avoided by dynamically optimizing the interval duration. This design addresses the pain points of existing technologies, such as subjective and inefficient prioritization and rigid alternation cycles. Weighted quantitative prioritization ensures that irrigation resources are tilted towards the areas with the most urgent needs, avoiding the imbalance of "emphasizing secondary over primary". Wind speed-linked interval adjustments precisely address environmental disturbances and significantly reduce water drift loss (by more than 25%). It not only ensures that the water needs of crops in key areas are met first, but also improves water resource utilization. This makes the alternating irrigation strategy more in line with the actual conditions of farmland and environmental changes, enhances the scientific nature and flexibility of decision-making, and adapts to the differentiated, efficient, and water-saving irrigation needs of large-scale farmland.

[0036] Specifically, such as Figure 2 As shown, the feedback adjustment in step S5 forms a closed-loop control. After a certain zone reaches the irrigation target, the decision module adjusts the irrigation parameters of subsequent zones based on its actual irrigation effect and the real-time soil moisture of the remaining zones to ensure the uniformity of irrigation of the entire farmland.

[0037] Understandably, the feedback adjustment in step S5 constructs a closed-loop control for the entire process. The perception layer transmits soil moisture (temperature, humidity, electrical conductivity) data for each zone in real time at a high-frequency feedback cycle of 2-5 minutes. When the soil moisture in a certain zone reaches the water requirement threshold for the current growth stage of the crop (i.e., the irrigation target is achieved), the decision module automatically compares the actual irrigation effect of that zone (such as the deviation between the actual moisture and the target threshold, and the degree of fit between the irrigation amount and the decision value) with the real-time moisture data of the remaining zones that have not met the target. Combining the water requirement model for multiple crop growth stages, it dynamically adjusts the irrigation amount, irrigation duration, and alternation interval of subsequent zones. For example, it appropriately increases the irrigation amount for zones with a large moisture deficit and reduces the duration for zones that are close to meeting the target, so as to avoid overall irrigation imbalance. In terms of beneficial effects, this design solves the problem of uneven regional irrigation caused by the lack of closed-loop irrigation and fixed parameters in existing irrigation technologies. Through high-frequency feedback and dynamic parameter adjustment, it ensures that the irrigation of each zone is accurately matched to its own water demand gap, significantly improving the overall uniformity of farmland irrigation (uniformity increased to over 90%), avoiding over- or under-irrigation in some areas, reducing water waste and crop drought and flood risks, and making irrigation strategies more flexible and adaptable, providing a reliable guarantee for efficient and precise irrigation of large-scale farmland.

[0038] In a specific embodiment of this application, the above steps are implemented in the following ways: Taking a 1,000-mu (67 hectares) large-scale corn-soybean intercropping planting base in a hilly area as the application scenario, 68 independent irrigation zones were divided into 7-10 mu (0.5-0.67 hectares) / zone. Each zone was equipped with a monitoring unit integrating soil temperature and humidity (buried depth 12-15cm, measurement range -40℃~85℃, 0~100%RH), conductivity sensor (buried depth 10cm, 0~20mS / cm), and canopy temperature sensor (installation height 1.8-2.2m). Environmental sensor group (light intensity 0~200000lux, wind speed 0~60m / s, precipitation resolution 0.1mm) was deployed in the open area of ​​the field. All sensors reached the IP67 protection level.

[0039] S1 data collection cycles are configured differently according to crop type: soil parameters in maize areas are collected every 5 minutes, soybean areas every 6 minutes, canopy temperature is collected every 12 minutes, light and wind speed every 15 minutes, and precipitation is collected in real time. Data is encrypted using AES-128 and transmitted via dual-mode "LoRa (communication distance 3.2km) + 5G (transmission rate 150Mbps)". The gateway integrates a protocol conversion unit and a 32GB cache (capable of storing 96 hours of data even when offline). Collected data is bound to an NTP calibration timestamp (error ≤8ms).

[0040] S2 uses the 3σ criterion to remove outliers and the 8-point moving average filter to reduce noise. After Min-Max normalization, it is compared with the pre-stored water requirement models for the growth period of maize (soil moisture 18%-22% during jointing stage) and soybean (flowering stage 20%-25%) and the soil moisture baseline values ​​to generate a parameter deviation report.

[0041] S3 divides irrigation zones into three categories based on three indicators: water-demand zone (maize soil moisture <18%, canopy temperature >31℃, and 24-hour precipitation <5mm; soybean thresholds are adjusted accordingly), temporarily suspended irrigation zone (parameters close to the threshold), and prohibited irrigation zone (parameters meet the standard or precipitation ≥5mm). Priority is ranked by a weighted score of soil parameter deviation (weight 0.6) and water demand urgency (weight 0.4), and the alternation cycle is dynamically adjusted according to wind speed: ≤3m / s interval 8 minutes, 3-6m / s extended by 25%, 6-10m / s extended by 50%, and >10m / s irrigation of non-core zones is suspended.

[0042] The S4 drive module parses commands within 10ms, controls the waterproof solenoid valve (response time ≤45ms), and adapts the sprinkler head angle to different zones (45°-60° for corn, 30°-45° for soybeans). The flow control module forms a closed loop with the variable frequency water pump through the electromagnetic flow sensor (accuracy ±0.4%FS), with irrigation volume deviation ≤3%.

[0043] The S5 provides high-frequency soil moisture feedback at intervals of 2 minutes for windward slopes, 3 minutes for leeward slopes, and 5 minutes for plain areas. Once a certain zone meets the standard, the decision module dynamically adjusts parameters based on its irrigation effect and the remaining zone's soil moisture (e.g., increasing irrigation when the soil moisture gap in the soybean area is 7%). The system supports dual-end monitoring via local touchscreen and remote APP.

[0044] In the above embodiments, an intelligent irrigation system with a closed loop of "sensing-transmission-processing-decision-execution-feedback" is constructed using Internet of Things (IoT) technology. The sensing layer collects multi-dimensional parameters such as soil temperature and humidity, electrical conductivity, crop canopy temperature, light intensity, wind speed, and precipitation at differentiated cycles through multiple sensors. These parameters are transmitted to the control layer via encrypted dual-mode communication. The control layer performs outlier removal, noise reduction, and normalization on the data, and then compares it with pre-stored multi-crop growth stage water requirement models and soil moisture thresholds. Based on the comparison results, the decision-making module dynamically divides water-demand zones, temporarily suspended irrigation zones, and prohibited irrigation zones. It sorts irrigation priorities according to weighted scores and optimizes the alternation cycle in combination with wind speed to generate precise control commands. The execution layer links the zoned spraying devices and the flow control module to achieve on-demand spraying. At the same time, the sensing layer provides high-frequency feedback on changes in soil moisture, and the decision-making module dynamically corrects subsequent irrigation parameters to ensure that irrigation in each zone is accurately adapted to the actual water requirements of crops and environmental changes, thereby achieving precise, water-saving, and intelligent irrigation for large-scale farmland.

[0045] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program goods. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program goods embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0046] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program goods according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0047] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0048] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0049] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A smart monitoring and spraying system for farmland based on the Internet of Things, characterized in that, It includes a perception layer, a network layer, a control layer, and an execution layer that work together, with each layer forming a closed-loop control based on data interaction and command transmission; The sensing layer is equipped with several monitoring units arranged in zones as needed. Each unit integrates soil temperature and humidity sensors, crop canopy temperature sensors, and environmental sensors to collect soil conditions, crop water requirements, and environmental influencing factors, thereby achieving synchronous collection of multi-dimensional parameters. The network layer includes an IoT communication module and a data relay gateway adapted to the monitoring unit, which undertakes bidirectional data transmission, command issuance and encryption protection functions for each layer; The control layer is the core decision-making unit, including a data processing module, a decision-making module and a storage module. The decision-making module pre-stores water requirement models for different crop growth stages and a dynamic alternating irrigation rule base, and can generate targeted irrigation parameters based on monitoring data. The execution layer includes a zoned spraying device, a flow control module, and a drive module. The drive module receives instructions from the control layer and coordinates the spraying device and the flow control module to achieve precise alternating spraying.

2. The intelligent farmland monitoring and spraying system based on the Internet of Things according to claim 1, characterized in that, The monitoring unit also integrates a soil conductivity sensor, which works in conjunction with a soil temperature and humidity sensor to collect soil state parameters. Together, these parameters are used to reflect soil fertility and salinization, providing comprehensive soil condition support for adjusting irrigation parameters. The environmental sensor is a multi-parameter combined sensor, including at least a light sensor, a wind speed sensor, and a precipitation sensor, which respectively capture light intensity, air flow status, and natural precipitation.

3. The intelligent farmland monitoring and spraying system based on the Internet of Things according to claim 1, characterized in that, The IoT communication module is a wireless communication module adapted to complex agricultural outdoor environments. It supports single or multiple combined communication modes and has the function of adaptively switching communication modes according to signal coverage and transmission requirements when used in combination. The gateway integrates a protocol conversion unit, which can achieve compatible conversion between different communication protocols, and has the functions of data caching when the network is interrupted and retransmission after the network is restored.

4. The intelligent farmland monitoring and spraying system based on the Internet of Things according to claim 1, characterized in that, The alternating irrigation rule base includes dynamic irrigation zone division rules, irrigation priority ranking rules, and alternating cycle adjustment rules. These three work together to divide irrigation demand zones based on soil and crop parameters, rank irrigation according to the urgency of water demand, and adjust irrigation intervals in combination with environmental parameters.

5. The intelligent farmland monitoring and spraying system based on the Internet of Things according to claim 1, characterized in that, The zoned spraying device is configured according to independent irrigation zones. Each zone corresponds to a set of independently controllable spraying components. The spraying components include irrigation nozzles with adjustable spray angle and coverage area, and solenoid valves for controlling the on / off state of the zone. The flow control module integrates flow detection elements and flow regulation equipment to form a closed-loop control, which is used to ensure that the actual irrigation volume is consistent with the decision parameters.

6. A smart farmland monitoring and spraying method based on the Internet of Things (IoT), applied to the smart farmland monitoring and spraying system based on the IoT as described in any one of claims 1-5, characterized in that, Includes the following steps: S1: Each monitoring unit in the sensing layer synchronously collects soil conditions, crop water requirements, and environmental influencing factors related to the corresponding zone according to a preset cycle, and transmits them to the control layer through network encryption. S2: The control layer data processing module performs outlier removal, data noise reduction and normalization on the collected data, and compares the standardized effective data with the crop growth period water requirement model and soil moisture threshold stored in the storage module. S3: The decision module divides irrigation zones, determines irrigation priorities and alternation rules based on the comparison results, and generates control instructions that include solenoid valve switching timing and flow regulation parameters. S4: The execution layer driver module parses instructions, links the zoned spraying device and the flow control module, and realizes alternating zoned spraying according to the decision rules; S5: During irrigation, the sensing layer provides real-time feedback on changes in soil moisture, and the decision-making module dynamically adjusts irrigation parameters until each zone meets the irrigation target.

7. The method for intelligent monitoring and spraying of farmland based on the Internet of Things according to claim 6, characterized in that, In step S1, the collection period for different types of parameters can be configured independently to adapt to the crop growth stage and the rate of environmental change. During collection, timestamps with a unified time base are recorded synchronously to ensure data time sequence consistency.

8. The method for intelligent monitoring and spraying of farmland based on the Internet of Things according to claim 6, characterized in that, In step S3, the irrigation zones are divided into water-demand zones, temporarily suspended irrigation zones, and prohibited irrigation zones. The division is based on whether the soil condition parameters meet the water requirements of the crop at its current growth stage, whether the crop's water requirements are obvious, and whether there is natural precipitation replenishment.

9. A smart monitoring and spraying method for farmland based on the Internet of Things according to claim 6, characterized in that, In step S3, irrigation priorities are ranked based on soil condition differences and the urgency of crop water demand, with higher priority for zones with more urgent water needs. The adjustment of the alternation cycle is related to wind speed in the environmental parameters, and water drift loss is reduced by optimizing the interval duration.

10. A smart monitoring and spraying method for farmland based on the Internet of Things according to claim 6, characterized in that, The feedback adjustment in step S5 forms a closed-loop control. After a certain zone reaches the irrigation target, the decision module adjusts the irrigation parameters of subsequent zones based on its actual irrigation effect and the real-time soil moisture of the remaining zones to ensure the uniformity of irrigation for the entire farmland.

Images