Intelligent water-saving irrigation system based on Internet of Things

Abstract

The invention belongs to the field of irrigation systems, and provides an intelligent water-saving irrigation system based on the Internet of Things, which comprises a control terminal, and the control terminal comprises a control module, a communication module, a data analysis module and a power supply module; the data acquisition module comprises a meteorological sensor, a soil humidity sensor and a plant growth state monitor which are electrically connected with the communication module; the irrigation execution module comprises an adjustable electric valve and a variable frequency water pump which are controlled in a partition mode, and irrigation operation is conducted according to the instruction sent by the control module; by arranging the control terminal, the data acquisition module and the irrigation execution module, the soil humidity and the plant water demand condition can be accurately sensed, the system can avoid unnecessary irrigation, water resource waste is effectively reduced, full automation and intelligentization of the irrigation process are achieved, manual intervention is reduced, and the working efficiency is improved.

Description

Technical Field

[0001] The invention belongs to the field of irrigation systems, in particular to an intelligent water-saving irrigation system based on the Internet of Things. Background Art

[0002] Water resources are unevenly distributed around the world, and many regions are facing serious water shortages. In the process of urban development, landscape gardening, as an important part of improving urban quality and ecological environment, requires a large amount of water resources for irrigation and maintenance; with the increase in population, the acceleration of urbanization and the impact of climate change, traditional extensive irrigation methods can no longer meet the requirements of sustainable development, and more efficient and water-saving irrigation methods are urgently needed.

[0003] The rise of Internet of Things technology has enabled remote monitoring and management of garden irrigation systems. Users can understand the operating status of the irrigation system anytime and anywhere through mobile phones, computers and other terminal devices, and conduct remote control.

[0004] Most existing garden irrigation methods rely on manual or traditional automatic control systems. Traditional irrigation systems have a low degree of automation and usually turn on and off irrigation equipment at a preset time. They are difficult to adapt to changing weather conditions and it is difficult to accurately perceive the real-time growth status of plants. They fail to comprehensively consider factors such as soil moisture and weather changes for precise irrigation, resulting in waste of water resources or unbalanced irrigation.

[0005] To this end, those skilled in the art have proposed an intelligent water-saving irrigation system based on the Internet of Things to solve the problems raised by the background technology. Summary of the invention

[0006] In order to solve the above technical problems, the present invention provides an intelligent water-saving irrigation system based on the Internet of Things to solve the problems of low automation of traditional irrigation systems in the prior art, which may easily lead to waste of water resources or uneven irrigation.

[0007] An intelligent water-saving irrigation system based on the Internet of Things, comprising:

[0008] A control terminal, comprising a control module, a communication module, a data analysis module and a power supply module;

[0009] A data acquisition module, the data acquisition module includes a meteorological sensor, a soil moisture sensor, and a plant growth status monitor electrically connected to the communication module; the data acquisition module continuously monitors meteorological conditions, soil moisture, and plant growth conditions, and sends the collected data to the control module through the communication module; the control module calculates irrigation demand based on the monitoring data of the data acquisition module;

[0010] The irrigation execution module includes an adjustable electric valve and a variable frequency water pump for zone control, and performs irrigation operations according to instructions issued by the control module.

[0011] Preferably, the meteorological data monitored in real time by the meteorological sensor in the data acquisition module include: temperature, humidity, precipitation, wind speed, and light intensity; and the soil moisture sensor detects the soil moisture content of the divided area.

[0012] Preferably, the control module has a built-in irrigation strategy decision system, a reinforcement learning algorithm and a data processing unit for the control algorithm. The control module automatically adjusts the irrigation time, frequency and water volume according to the water demand characteristics of plants in different regions, current meteorological conditions and soil moisture data.

[0013] Preferably, the workflow of the reinforcement learning algorithm includes:

[0014] Initializing a state space, wherein the state space includes meteorological parameters, soil moisture, and plant growth state data;

[0015] Initializing an action space, the action space including a plurality of combined parameters of an irrigation scheme, including irrigation time, irrigation frequency, and water volume;

[0016] The reward function is set to evaluate the effect of the system after executing the irrigation strategy in order to optimize the irrigation plan.

[0017] Preferably, the reward function is expressed as:

[0018] R=w1×f soil_humidity (S)+w2×f plant_growth (S)-w3×f water_usage (A);

[0019] Among them, S represents the current state, A represents the action taken, and f soil_humidity (S) is a function related to soil moisture, f plant_growth (S) is a function related to the plant growth state, f water_usage (A) is a function related to irrigation water volume, and w1, w2, and w3 are weight coefficients.

[0020] Preferably, the control algorithm combines a genetic algorithm and a neural network for optimization control, wherein the genetic algorithm is used to optimize the structure and parameters of the neural network, and the connection weights, bias values, and number of neurons of the neural network are encoded as chromosomes.

[0021] Preferably, the three-layer MLP neural network is expressed as:

[0022] y=f3(W3×f2(W2×f1(W1×x+b1))+b2)+b3;

[0023] Among them, x is the input data, y is the output irrigation decision, W1, W2, W3 are the weight matrices of each layer, b1, b2, b3 are bias vectors, and f1, f2, f3 are activation functions.

[0024] Preferably, the intelligent irrigation scheduling algorithm includes:

[0025] Collect data: obtain information on soil moisture, plant water requirements, and irrigation priorities in different areas;

[0026] Calculate priority: Calculate the irrigation priority of each area according to certain rules;

[0027] Sorting: Sort the areas according to priority;

[0028] Make an irrigation plan: Allocate irrigation time and water volume to each area in order of priority from high to low;

[0029] Execute irrigation: According to the formulated irrigation plan, control the irrigation execution module to perform irrigation operations;

[0030] Monitoring and adjustment: During the irrigation process, the soil moisture changes and system operation status of each area are monitored in real time, and the irrigation plan is adjusted according to the actual situation.

[0031] Preferably, the power module includes a solar panel and a backup battery, the solar panel provides main power for the system, and the backup battery automatically switches to power supply when solar energy is insufficient.

[0032] Preferably, the communication module includes a wireless communication module and a cloud platform interface. The wireless communication module adopts LoRa and NB-IoT low-power wide area network technologies. The cloud platform interface uploads the irrigation data to the cloud server in real time, and the user end remotely monitors and adjusts the irrigation parameters through the terminal device.

[0033] Compared with the prior art, the present invention has the following beneficial effects:

[0034] The present invention can accurately sense soil moisture and plant water requirements by setting up a control terminal, a data acquisition module and an irrigation execution module. The system can avoid unnecessary irrigation, effectively reduce waste of water resources, realize full automation and intelligence of the irrigation process, reduce manual intervention, and improve work efficiency. It can provide personalized irrigation plans according to the water requirements of different plants, soil conditions and climate changes, and adapt to the needs of different gardens and crops. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is a schematic diagram of the overall structure of the present invention;

[0036] Figure 2It is a structural diagram of the receipt collection module;

[0037] Figure 3 It is a structural diagram of the irrigation execution module;

[0038] Figure 4 This is a schematic diagram of the layout of the green wetland. DETAILED DESCRIPTION

[0039] The following is a further detailed description of the embodiments of the present invention in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention but are not intended to limit the scope of the present invention.

[0040] Embodiment 1: As shown in the attached Figure 1 As shown: The present invention provides an intelligent water-saving irrigation system based on the Internet of Things, comprising: a control terminal, the control terminal comprising a control module, a communication module, a data analysis module and a power supply module;

[0041] The data acquisition module includes a meteorological sensor, a soil moisture sensor, and a plant growth status monitor electrically connected to the communication module; the data acquisition module continuously monitors meteorological conditions, soil moisture, and plant growth conditions, and sends the collected data to the control module through the communication module; the control module calculates the irrigation demand based on the monitoring data of the data acquisition module;

[0042] Irrigation execution module, the irrigation execution module includes an adjustable electric valve and a variable frequency water pump for zone control, and performs irrigation operations according to the instructions issued by the control module.

[0043] The meteorological sensors in the data acquisition module monitor the meteorological data in real time, including temperature, humidity, precipitation, wind speed, and light intensity; the soil moisture sensor detects the soil moisture content in the divided area, forming multi-point monitoring.

[0044] Meteorological sensors are used to monitor meteorological parameters such as ambient temperature, humidity, wind speed, rainfall, light intensity, etc. in real time. This sensor can be connected to a weather station to achieve more accurate weather forecasts.

[0045] Soil moisture sensors are used to monitor the moisture content in the soil in different areas, ensuring that the system makes corresponding irrigation adjustments based on the differences in soil moisture in different areas;

[0046] The plant growth status monitor is based on optical and non-contact measurement technology to monitor plant chlorophyll content, leaf temperature and other growth status parameters in real time, and comprehensively judge the plant's water needs.

[0047] The adjustable electric valve accurately adjusts the water flow according to the control instructions, supports multi-point irrigation control, and is suitable for the differentiated needs of different regions; the variable frequency water pump automatically adjusts the water pressure according to irrigation needs to reduce energy consumption.

[0048] The system can achieve differentiated irrigation for different plant species or different areas through regional division to ensure reasonable allocation of resources

[0049] The control module has a built-in irrigation strategy decision system, reinforcement learning algorithm and control algorithm data processing unit. The control module automatically adjusts the irrigation time, frequency and water volume according to the water demand characteristics of plants in different areas, current meteorological conditions and soil moisture data.

[0050] The workflow of the reinforcement learning algorithm includes:

[0051] Initialize the state space, which includes meteorological parameters, soil moisture, and plant growth status data;

[0052] Initialize the action space, which includes multiple combination parameters of the irrigation scheme, including irrigation time, irrigation frequency and water volume;

[0053] The reward function is set to evaluate the effect of the system after executing the irrigation strategy in order to optimize the irrigation plan.

[0054] The reward function is expressed as:

[0055] R=w1×f soil_humidity (S)+w2×f plant_growth (S)-w3×f water_usage (A);

[0056] Among them, S represents the current state, A represents the action taken, and f soil_humidity (S) is a function related to soil moisture, f plant_growth (S) is a function related to the plant growth state, f water_usage (A) is a function related to irrigation water volume, and w1, w2, and w3 are weight coefficients.

[0057] The control algorithm combines genetic algorithm and neural network for optimal control, where the genetic algorithm is used to optimize the structure and parameters of the neural network, and the connection weights, bias values, and number of neurons of the neural network are encoded as chromosomes.

[0058] The specific steps include: forming an initial population by randomly generating a set of chromosomes representing different neural network structures and parameter combinations;

[0059] The effect of each chromosome in processing irrigation data is calculated through fitness evaluation, and the evaluation indicators include irrigation effect and energy saving degree;

[0060] Through genetic operations such as selection, crossover and mutation, the structure and parameters of the neural network are optimized until the preset stopping conditions are reached; after being optimized by the genetic algorithm, the neural network can output accurate irrigation decisions based on the input meteorological data, soil moisture data and plant growth status data, including parameters such as irrigation time, irrigation frequency and water volume, where the neural network can adopt a multi-layer perceptron or convolutional neural network structure.

[0061] The three-layer MLP neural network is represented as:

[0062] y=f3(W3×f2(W2×f1(W1×x+b1))+b2)+b3;

[0063] Among them, x is the input data, y is the output irrigation decision, W1, W2, W3 are the weight matrices of each layer, b1, b2, b3 are bias vectors, and f1, f2, f3 are activation functions.

[0064] Intelligent irrigation scheduling algorithms include:

[0065] Collect data: obtain information on soil moisture, plant water requirements, and irrigation priorities in different areas;

[0066] Calculate priority: Calculate the irrigation priority of each area according to certain rules;

[0067] The difference between soil moisture and plant water requirements is used as the main indicator of priority, and adjustments are made based on factors such as irrigation history and plant species;

[0068] Sorting: Sort the areas according to priority;

[0069] Develop irrigation plans: Allocate irrigation time and water volume to each area in order of priority from high to low; in the allocation process, consider the total water resource limitations and the operating efficiency of the system;

[0070] Execute irrigation: According to the formulated irrigation plan, control the irrigation execution module to perform irrigation operations;

[0071] Monitoring and adjustment: During the irrigation process, the soil moisture changes and system operation status of each area are monitored in real time, and the irrigation plan is adjusted according to the actual situation.

[0072] Priority calculation formula:

[0073] Priority=w1×(Plant_Water_Demand-Soil_Moisture)+w2×f irrigation_history (R)+w3×g plan ;

[0074] Among them, Plant_Water_Demand represents the water demand of plants, Soil_Moisture represents the soil moisture, and f irrigation_history (R) is the irrigation history correlation function, g planttype (T) is a function related to plant species, and w1, w2, and w3 are weight coefficients.

[0075] The power module includes a solar panel and a backup battery. The solar panel provides the main power for the system, and the backup battery automatically switches to power supply when solar energy is insufficient.

[0076] The communication module includes a wireless communication module and a cloud platform interface. The wireless communication module adopts LoRa and NB-I oT low-power wide area network technologies; the cloud platform interface uploads irrigation data to the cloud server in real time, and the user end remotely monitors and adjusts irrigation parameters through terminal devices. The system also supports data docking with third-party platforms (such as weather forecast platforms) through API.

[0077] As can be seen from the above, when the system is working normally, the data acquisition module continuously monitors the environment and plant growth conditions, and sends the collected data to the central control module through the wireless communication module;

[0078] The control module uses the built-in AI algorithm for analysis, combines historical data with preset plant growth models, calculates the current optimal irrigation plan in real time, and sends instructions to the irrigation execution module; users can view the irrigation status in real time through mobile phones or computer terminals, and the system also supports manual adjustment of irrigation plans.

[0079] When the meteorological sensor detects that it is about to rain, the control module will automatically suspend irrigation to prevent over-irrigation; when the soil moisture is lower than the set value and the plant growth monitor determines that the plants need water, the system will automatically turn on the irrigation equipment to ensure that the plants get enough water.

[0080] This system takes into account multiple factors such as weather, soil moisture and plant growth status, and can formulate accurate irrigation strategies for different regions and plant species to avoid over-irrigation or under-irrigation, improve water resource utilization efficiency, and promote plant growth;

[0081] Through the cooperation of the reinforcement learning algorithm and the control algorithm combining the genetic algorithm and the neural network, the reinforcement learning algorithm comprehensively evaluates the irrigation effect through the reward function, prompting the system to optimize the irrigation plan; the genetic algorithm optimizes the neural network structure and parameters, so that the system can more accurately output reasonable irrigation decisions based on the input data, including parameters such as time, frequency and water volume, thereby improving the scientificity and accuracy of irrigation decisions.

[0082] During the irrigation process, the data acquisition module continuously monitors the data, and the control module can adjust the irrigation strategy in time according to the real-time data (such as weather changes, changes in plant growth status, etc.) to better adapt to environmental changes, ensure the plant growth environment, and avoid wasting water resources.

[0083] The variable frequency water pump automatically adjusts the water pressure according to irrigation needs, reducing energy consumption; precise irrigation strategies also reduce unnecessary waste of water resources, achieve energy-saving and water-saving effects, reduce operating costs, and meet the requirements of sustainable development.

[0084] The communication module includes a wireless communication module and a cloud platform interface. It adopts LoRa and NB-I oT low-power wide area network technologies, which can upload irrigation data to the cloud server in real time. The user end remotely monitors and adjusts irrigation parameters through terminal devices, which facilitates management and improves the management efficiency and flexibility of the irrigation system.

[0085] The power module includes solar panels and backup batteries. The solar panels provide the main power for the system, and the backup batteries automatically switch to power supply when solar energy is insufficient, using renewable energy, reducing dependence on traditional energy, and improving the sustainability of the system.

[0086] Embodiment 2:

[0087] In the plantation, the data acquisition module started working, and the meteorological sensor monitored in real time that the summer temperature in the area often reached above 35°C, the humidity was between 30% and 40%, the precipitation was small, the wind speed was moderate, and the light intensity was strong. The soil moisture sensor detected that the soil moisture in different areas varied greatly, and the soil moisture in some areas was below 30% (the soil moisture suitable for fruit tree growth is set at 40% to 60%). The plant growth status monitor showed that the leaves of some fruit trees were slightly curled and the chlorophyll content decreased, indicating that the fruit trees were facing certain water stress.

[0088] The reinforcement learning algorithm built into the control module starts working; first, the state space is initialized, including meteorological parameters (temperature above 35°C, humidity 30% to 40%, little precipitation, moderate wind speed, strong light intensity), soil moisture (below 30% in some areas) and plant growth status (leaf curling, chlorophyll content decreases). The action space includes different combinations of irrigation plans, such as irrigation time (different time periods such as morning and evening can be selected), irrigation frequency (once a day, once every two days, etc.) and water volume (different water volume levels are determined according to the type of fruit tree and the area).

[0089] Set the reward function to R = ω1 × f soil_humidity (S)+w2×f plant_growth (S)-w3×f water_usage(A); Here we set ω1 = 0.4, ω2 = 0.3, ω3 = 0.3. soil_humidity (S) Soil moisture related function. If the soil moisture after irrigation can reach the appropriate range (40% to 60%), the function value will be higher; f plant_growth (S) is a function related to the plant growth status. If the leaves of the fruit tree return to normal and the chlorophyll content increases, the function value will be higher; f water_usage (A) is a function related to irrigation water volume. If the irrigation water volume is reasonable, which can meet the needs of fruit trees without wasting water resources, the function value will be high.

[0090] At the same time, the control algorithm combines genetic algorithms and neural networks for optimization control. The genetic algorithm encodes the connection weights, bias values, and number of neurons of the neural network into chromosomes. For example, a set of chromosomes is randomly generated to represent different neural network structures and parameter combinations to form an initial population. The effect of each chromosome in processing orchard irrigation data is calculated through fitness evaluation. The evaluation indicators include irrigation effect (whether the soil moisture and plant growth status can reach the ideal state) and energy saving degree (whether water resources and energy are used reasonably).

[0091] Through genetic operations such as selection, crossover and mutation, the structure and parameters of the neural network are optimized. After multiple iterations, the optimized neural network structure is obtained, which is represented by a three-layer MLP neural network:

[0092] y=f3(W3×f2(W2×f1(W1×x+b1))+b2)+b3;

[0093] Where x is the input data (weather, soil moisture and plant growth status data), and y is the output irrigation decision (parameters such as irrigation time, frequency and water volume).

[0094] According to the decision of the control module, the irrigation execution module starts working; the adjustable electric valve of the zone control adjusts the opening according to the soil moisture and water demand of the fruit trees in different areas. For areas with soil moisture below 30%, the electric valve opens wider to increase the water flow. The variable frequency water pump automatically adjusts the water pressure according to the irrigation demand. Due to the large area of ​​the orchard, a higher water pressure is required to ensure that water can be delivered to each area.

[0095] The irrigation time is set at 6:00 to 8:00 p.m. every day, the irrigation frequency is once a day, and the amount of water is determined based on the type of fruit trees and the area, with 20 liters of water (set value) for each fruit tree each time.

[0096] During the irrigation process, the data acquisition module continues to monitor the weather, soil moisture and plant growth status data, and the control module adjusts the irrigation strategy based on real-time data; if it suddenly rains during the irrigation process, the meteorological sensor detects that the precipitation reaches a certain standard, the control module will stop irrigation in time and re-evaluate subsequent irrigation needs.

[0097] Embodiment three:

[0098] This system is deployed in the landscape area of ​​the city park. The meteorological sensor monitors that the temperature in the area is between 15℃ and 25℃ in spring, the humidity is between 50% and 60%, the precipitation is moderate, the wind speed is low, and the light intensity is moderate. The soil moisture sensor detects that the soil moisture in different areas is also different. The soil moisture in some areas is around 40% (the soil moisture suitable for flower growth is set at 45% to 55%). The plant growth status monitor shows that the number of flowers of some flowers is not as expected, and there may be certain water supply problems.

[0099] The reinforcement learning algorithm initializes the state space, including meteorological parameters (temperature 15℃-25℃, humidity 50%-60%, moderate precipitation, low wind speed, moderate light intensity), soil moisture (about 40% in some areas), and plant growth status (the number of flowers blooming is not as expected). The action space includes various combinations of irrigation plans.

[0100] Set the reward function, set ω1 = 0.3, ω2 = 0.4, ω3 = 0.3. f soil_humidity (S) is the soil moisture related function, f plant_growth (S) is the function related to plant growth status, f water_usage (A) is the irrigation water volume related function.

[0101] The control algorithm combines genetic algorithm and neural network for optimal control. After similar genetic algorithm operations, the optimized neural network structure is obtained to output irrigation decisions.

[0102] The irrigation execution module operates according to the decision of the control module; for areas where the soil moisture is around 40%, the electric valve can be adjusted to open appropriately to increase the water flow.

[0103] The variable frequency water pump adjusts the water pressure to meet the irrigation needs. The irrigation time is set from 9:00 to 11:00 a.m. every Tuesday, Thursday and Saturday, the irrigation frequency is three times a week, and the water volume is determined according to the flower type and area to 5 liters of water per square meter per irrigation (set value).

[0104] During the irrigation process, data is continuously monitored, and the control module adjusts the irrigation strategy based on real-time data. For example, if it is found that the growth status of flowers in a certain area has improved significantly, the control module may appropriately reduce the subsequent irrigation water volume or frequency in that area.

[0105] Embodiment 4:

[0106] As attached Figure 4 As shown, the system is arranged in the green wetland and the data acquisition module starts working.

[0107] Meteorological sensors detected that the summer temperature in the area was stable at 30°C, the humidity was 50%, the precipitation accumulated in the past week reached 20 mm, the average wind speed was 2 m / s, and the light intensity was 80,000 lux.

[0108] The soil moisture sensor detected the soil moisture in the four monitoring areas as follows:

[0109] The soil moisture in the first monitoring area, which is based on shiitake grass, is 38%. The soil moisture range suitable for plant growth in this area is 42% to 52%. Among them, the soil moisture in the area where the narcissus, rose amaryllis, and longevity flowers are matched with strelitzia and pod fern is slightly higher, at 39%.

[0110] The second monitoring area, where the purple brocade grass is used as the base, has a soil moisture of 39.5%. The soil moisture range suitable for plant growth in this area is 43% to 53%. The soil moisture in the area where papyrus, cyperus, and cattail are used is relatively uniform.

[0111] The third monitoring area, where the Irish pearl grass is used as the base, has a soil moisture of 40%. The soil moisture suitable for the growth of flowers in this area is 44% to 54%. The soil moisture in the locations of hydrangea, allium, calamus, and Mars flower is slightly higher than that of the Irish pearl grass, which is used as the base, at 41%. The soil moisture in the areas bordered by Cineraria and Stachys odoratus is 40.5%.

[0112] The fourth monitoring area, with Irish pearl grass as the base, has a soil moisture of 39%. The soil moisture suitable for plant growth in this area is 43% to 53%. The soil moisture at the location of the solitary rhododendron is 39.5%, and the soil moisture at the location of the shade plant hosta and the aquatic plant pickerel grass is 39.2%.

[0113] The plant growth status monitor displays:

[0114] The number of blooming Kalanchoe flowers in the first monitoring area was 80% of the expected number; the edges of some leaves of Strelitzia reginae and Carthamus tinctorius were slightly curled to 5%; and the growth condition of daffodils and Lycoris radiata was good.

[0115] The color of some leaves of papyrus, Cyperus rotundus and other plants in the second monitoring area was 10% darker than normal.

[0116] The growth trend of Allium grandiflorum and Acorus calamus in the third monitoring area is 8% slower than the optimal state, and the leaves of Cineraria citrifolia and Stachys pubescens show signs of drooping slightly.

[0117] The color brightness of azalea flowers in the fourth monitoring area is 85% of the normal level, while some leaves of hosta, sedge, etc. have slight yellowing, accounting for 3% of the total leaf area.

[0118] The system combines weather data from previous years to predict: the system connects to the meteorological database through the communication module to obtain the summer weather data of the region in previous years; after data analysis, it is found that in the past five years, the average summer temperature in the region is 29℃-31℃, the average humidity is 48%-52%, and the average precipitation is 80-100 mm per month. Based on these data and the current meteorological trends, the system predicts that in the next week, the temperature will remain between 29℃-31℃, and the humidity may rise slightly to 52%-55%, but the precipitation is not expected to increase significantly.

[0119] The reinforcement learning algorithm built into the control module starts working:

[0120] Initialize the state space, including meteorological parameters (temperature 30℃, humidity 50%, precipitation accumulated in the past week reaching 20 mm, average wind speed 2 m / s, light intensity 80,000 lux), soil moisture (soil moisture conditions in each region) and plant growth status (specific growth status of plants in each region).

[0121] The action space includes different combinations of irrigation plans, such as irrigation time (can be accurate to the specific hour, such as 6 o'clock in the morning, 7 o'clock, etc.), irrigation frequency (can be specific to the number of days, such as once every 1.5 days, etc.) and water volume (determined to the exact number of liters according to the plant species and area in different regions, such as 7.8 liters of water per square meter per irrigation in the first monitoring area).

[0122] The reward function is set to R(s, a) = ω1F(s) + ω2G(s) - ω3H(a); here ω1 = 0.32, ω2 = 0.33, and ω3 = 0.35. The soil moisture related function F(s) is higher if the soil moisture in each area can reach the appropriate range after irrigation. For example, when the soil moisture in the first monitoring area reaches more than 42%, the function value begins to increase, and when it reaches 50%, the function value reaches a higher level. The plant growth state related function G(s) is higher if the leaves of plants in each area return to normal, the number of flowers increases, and the colors are bright. For example, the number of flowers of Kalanchoe in the first monitoring area returns to more than 95% of the expected number, and the curling degree of the leaves of Strelitzia and Pteris reginae is reduced to less than 1%, and the function value increases accordingly. The irrigation water related function H(a) is higher if the irrigation water is reasonable, which not only meets the needs of plants but also does not waste water resources. For example, when the irrigation water volume is controlled within the range of the minimum water volume that meets the plant growth requirements to 10% exceeding the required water volume, the function value is high.

[0123] At the same time, the control algorithm combines genetic algorithms and neural networks for optimization control. The genetic algorithm encodes the connection weights, bias values, and number of neurons of the neural network into chromosomes. For example, a set of chromosomes is randomly generated to represent different neural network structures and parameter combinations to form an initial population. The effect of each chromosome in processing green wetland irrigation data is calculated through fitness evaluation. The evaluation indicators include irrigation effect (whether the soil moisture and plant growth status can reach the ideal state) and energy saving degree (whether water resources and energy are used reasonably).

[0124] The irrigation execution module starts working according to the decision of the control module: for areas with low soil moisture, such as the first monitoring area, the second monitoring area, the third monitoring area and the fourth monitoring area, the adjustable electric valve can accurately adjust the opening according to different areas and plant types.

[0125] In the first monitoring area, the valve opening can be set to 45% for the bottom part of the mushroom grass according to the structure of the uneven plants, and the valve opening can be set to 50% for the taller ones such as Strelitzia reginae and pod fern.

[0126] In the second monitoring area, according to the needs of landscape transition, the valve opening of the base part of the purple sedge is set to 42%, and the valve opening of the papyrus, Cyperus rotundus, and Cattail is set to 45%.

[0127] In the third monitoring area, the valve opening for the base of Irish pearl grass is set to 43%, the valve opening for hydrangea, allium, calamus, and Mars flower is set to 48%, and the valve opening for the edging of Cineraria and Stachys linden is set to 45%.

[0128] In the fourth monitoring area, the valve opening of Irish pearl grass around the central island is set to 42%, the valve opening of azalea is set to 45%, and the valve opening of hosta and pickerel grass is set to 43%.

[0129] The variable frequency water pump automatically adjusts the water pressure according to the irrigation demand, taking into account the terrain and plant distribution of the green wetland to ensure that water can be evenly delivered to each area. The water pressure is dynamically adjusted according to the needs of different areas. For example, the required water pressure in the first monitoring area is 2.5 Pa, the second monitoring area is 2.3 Pa, the third monitoring area is 2.4 Pa, and the fourth monitoring area is 2.6 Pa.

[0130] The irrigation time is set from 7:30 to 9:00 every morning, the irrigation frequency is once every 1.8 days, and the amount of water is determined according to the plant species and area of ​​different regions. For example, the first monitoring area is irrigated with 7.8 liters of water per square meter each time; the second monitoring area is irrigated with 7.5 liters of water per square meter each time; the third monitoring area is irrigated with 7.6 liters of water per square meter each time; and the fourth monitoring area is irrigated with 8 liters of water per square meter each time.

[0131] During the irrigation process, the data acquisition module continues to monitor the weather, soil moisture and plant growth status data, and the control module adjusts the irrigation strategy based on real-time data. For example, if it suddenly rains during the irrigation process and the meteorological sensor detects that the precipitation reaches 5 mm, the control module will stop irrigation in time and re-evaluate the subsequent irrigation needs. If it is found that the growth status of plants in a certain area has improved significantly, such as the number of Kalanchoe flowers blooming in the first monitoring area reaches more than 90% of the expected level, the control module may appropriately reduce the subsequent irrigation water volume or frequency in the area, adjusting the irrigation water volume per square meter to 7.5 liters per square meter and the irrigation frequency to once every 2 days.

[0132] The embodiments of the present invention are provided for the purpose of illustration and description. Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations of the present invention. Ordinary technicians in this field can change, modify, replace and deform the above embodiments within the scope of the present invention.

[0133] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. "Multiple" means two or more, unless otherwise clearly and specifically defined.

[0134] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0135] In the present invention, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature may mean that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. Moreover, a first feature being "above", "above" or "above" a second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is higher in level than the second feature. A first feature being "below", "below" or "below" a second feature may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is lower in level than the second feature.

[0136] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples" or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples, unless they are contradictory.

[0137] In the drawings of the embodiments disclosed in the present invention, only the structures involved in the embodiments disclosed in the present invention are involved, and other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of the present invention can be combined with each other.

[0138] Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments, or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent water-saving irrigation system based on the Internet of Things, characterized in that: include: A control terminal, comprising a control module, a communication module, a data analysis module and a power supply module; A data acquisition module, the data acquisition module includes a meteorological sensor, a soil moisture sensor, and a plant growth status monitor electrically connected to the communication module; the data acquisition module continuously monitors meteorological conditions, soil moisture, and plant growth conditions, and sends the collected data to the control module through the communication module; the control module calculates irrigation demand based on the monitoring data of the data acquisition module; The irrigation execution module includes an adjustable electric valve and a variable frequency water pump for zone control, and performs irrigation operations according to instructions issued by the control module.

2. The intelligent water-saving irrigation system based on the Internet of Things as claimed in claim 1, characterized in that: The meteorological sensor in the data acquisition module monitors the meteorological data in real time, including temperature, humidity, precipitation, wind speed, and light intensity; the soil moisture sensor detects the soil moisture content in the divided area.

3. The intelligent water-saving irrigation system based on the Internet of Things as claimed in claim 1, characterized in that: The control module has a built-in irrigation strategy decision system, a reinforcement learning algorithm and a data processing unit for the control algorithm. The control module automatically adjusts the irrigation time, frequency and water volume according to the water demand characteristics of plants in different regions, current meteorological conditions and soil moisture data.

4. The intelligent water-saving irrigation system based on the Internet of Things as claimed in claim 3, characterized in that: The workflow of the reinforcement learning algorithm includes: Initializing a state space, wherein the state space includes meteorological parameters, soil moisture, and plant growth state data; Initializing an action space, the action space including a plurality of combined parameters of an irrigation scheme, including irrigation time, irrigation frequency, and water volume; The reward function is set to evaluate the effect of the system after executing the irrigation strategy in order to optimize the irrigation plan.

5. The intelligent water-saving irrigation system based on the Internet of Things as claimed in claim 4, characterized in that: The reward function is expressed as: R=w1×f soil_humidity (S)+w2×f plant_growth (S)-w3×f water_usage (A); Among them, S represents the current state, A represents the action taken, and f soil_humidity (S) is a function related to soil moisture, f plant_growth (S) is a function related to the plant growth state, f water_usage (A) is a function related to irrigation water volume, and w1, w2, and w3 are weight coefficients.

6. An intelligent water-saving irrigation system based on the Internet of Things as claimed in claim 3 or 5, characterized in that: The control algorithm combines a genetic algorithm and a neural network for optimization control, wherein the genetic algorithm is used to optimize the structure and parameters of the neural network, and the connection weights, bias values, and number of neurons of the neural network are encoded as chromosomes.

7. The intelligent water-saving irrigation system based on the Internet of Things as claimed in claim 6, characterized in that: The three-layer MLP neural network is represented as: y=f3(W3×f2(W2×f1(W1×x+b1))+b2)+b3; Among them, x is the input data, y is the output irrigation decision, W1, W2, W3 are the weight matrices of each layer, b1, b2, b3 are bias vectors, and f1, f2, f3 are activation functions.

8. An intelligent water-saving irrigation system based on the Internet of Things as claimed in claim 3 or 5, characterized in that: The intelligent irrigation scheduling algorithm includes: Collect data: obtain information on soil moisture, plant water requirements, and irrigation priorities in different areas; Calculate priority: Calculate the irrigation priority of each area according to certain rules; Sorting: Sort the areas according to priority; Make an irrigation plan: Allocate irrigation time and water volume to each area in order of priority from high to low; Execute irrigation: According to the formulated irrigation plan, control the irrigation execution module to perform irrigation operations; Monitoring and adjustment: During the irrigation process, the soil moisture changes and system operation status of each area are monitored in real time, and the irrigation plan is adjusted according to the actual situation.

9. The intelligent water-saving irrigation system based on the Internet of Things as claimed in claim 1, characterized in that: The power module includes a solar panel and a backup battery. The solar panel provides main power for the system, and the backup battery automatically switches to supply power when solar energy is insufficient.

10. The intelligent water-saving irrigation system based on the Internet of Things as claimed in claim 1, characterized in that: The communication module includes a wireless communication module and a cloud platform interface. The wireless communication module adopts LoRa and NB-IoT low-power wide area network technologies; the cloud platform interface uploads irrigation data to the cloud server in real time, and the user end remotely monitors and adjusts irrigation parameters through the terminal device.

Images