Water and fertilizer integrated intelligent irrigation system for garden maintenance

Abstract

The invention discloses a garden maintenance water and fertilizer integrated intelligent irrigation system, which relates to the field of garden maintenance and comprises a monitoring subsystem, an interaction module, a storage module, a central control module, a water supply unit, a drip irrigation subsystem and an atomization subsystem. The monitoring subsystem monitors soil parameters of each plant area and environmental parameters of the whole garden maintenance area, and sends the parameters to the central control module; the central control module determines the water demand and fertilizer demand data of each plant by using the trained water and fertilizer demand model according to the environmental parameters, the types of the plants, the growth cycle and the current month; determining the actual water supply amount and the actual fertilizer supply data of the areas where the plants are located according to the soil parameters, the types of the plants and the growth cycles; according to the water demand, the actual water supply, the fertilizer demand data and the actual fertilizer supply data, the drip irrigation subsystem or the atomization subsystem is controlled for watering and / or fertilizing. Water and fertilizer management can be carried out more scientifically and intelligently, so that the water and fertilizer management efficiency of garden maintenance is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of garden maintenance, and more specifically, to an intelligent irrigation system for integrated water and fertilizer management in garden maintenance. Background Art

[0002] Garden maintenance refers to a series of technical measures and management activities taken to maintain the good condition of garden plants and landscape facilities. Among them, watering and fertilizing of garden plants play a crucial role in the healthy growth of plants.

[0003] However, most of the existing garden maintenance still adopts the extensive traditional maintenance method. Maintenance personnel often water by flood irrigation, and the fertilization process is often blindly carried out only according to the experience of maintenance personnel. The traditional water and fertilizer management method has low efficiency, not only causing waste of water and fertilizer, being unfavorable for saving water and fertilizer resources, but also having an adverse impact on the plant growth environment. For example, excessive irrigation is likely to cause soil water saturation, affecting the root respiration of plants and even leading to root rot. Improper use of fertilizers is likely to cause soil salinization and hardening, affecting plant growth, and the deterioration of the sudden environment is also likely to cause pests and diseases.

[0004] Therefore, how to carry out more scientific and intelligent water and fertilizer management in garden maintenance and improve the efficiency of water and fertilizer management is an urgent problem to be solved by those skilled in the art. Summary of the Invention

[0005] In view of this, the present invention provides an intelligent irrigation system for integrated water and fertilizer management in garden maintenance, which improves the efficiency of water and fertilizer management by setting a variety of sensors and using a management system for intelligent water and fertilizer management.

[0006] In order to achieve the above object, the present invention provides the following technical solutions:

[0007] The present invention discloses an intelligent irrigation system for integrated water and fertilizer management in garden maintenance, including: a monitoring subsystem, an interaction module, a storage module, a central control module, a water supply unit, a drip irrigation subsystem and an atomization subsystem;

[0008] The monitoring subsystem monitors the soil parameters of each plant area and the environmental parameters of the entire garden maintenance area, and sends them to the central control module; the staff inputs the numbers, types and growth cycles of each plant through the interaction module and stores them in the storage module; the water supply unit supplies water to the drip irrigation subsystem and the atomization subsystem;

[0009] The central control module determines the water demand and fertilizer demand data of each plant according to the environmental parameters, the type of the plant, the growth cycle, and the current month by using the trained water and fertilizer demand model; determines the actual water supply and actual fertilizer supply data of the area where each plant is located according to the soil parameters, the type of the plant, and the growth cycle; and the central control module controls the drip irrigation subsystem or the atomization subsystem to water and / or fertilize according to the water demand and the actual water supply, and the fertilizer demand data and the actual fertilizer supply data.

[0010] Further, the monitoring subsystem includes: a plurality of soil monitoring units and environmental monitoring units, and each of the soil monitoring units corresponds to one of the plant areas one by one;

[0011] The soil monitoring unit includes: a soil moisture sensor, a potassium ion concentration sensor, a nitrogen ion concentration sensor, and a soil NPK sensor, as well as a data acquisition module, a data transmission module, and a power supply module; the data acquisition module uses the sensors to collect the humidity, temperature, potassium ion concentration, nitrogen ion concentration, and phosphorus ion concentration of the soil to obtain the soil parameters, and sends them to the central control module through the data transmission module;

[0012] The environmental monitoring unit includes: an air temperature sensor, an air humidity sensor, a light sensor, and a wind speed sensor, as well as a data acquisition module, a data transmission module, and a power supply module; the data acquisition module uses the sensors to collect the air temperature, humidity, light intensity, and wind speed to obtain the environmental parameters, and sends them to the central control module through the data transmission module.

[0013] Further, the drip irrigation subsystem includes: a fertilizer storage tank, an irrigation and fertilization machine, and a drip irrigation pipe network;

[0014] The fertilizer storage tank includes storage tanks for storing liquid potassium fertilizer, nitrogen fertilizer, and phosphorus fertilizer respectively, and each storage tank is a pressurized storage tank, and supplies liquid fertilizer to the irrigation and fertilization machine through pipelines respectively;

[0015] There are a plurality of the irrigation and fertilization machines, and each irrigation and fertilization machine corresponds to one of the plant areas one by one. Each irrigation and fertilization machine mixes water and the liquid fertilizer into a water and fertilizer mixture according to the instruction of the central control module, and pumps it to the corresponding irrigation subnet under pressure;

[0016] The drip irrigation pipe network is composed of a plurality of non-connected irrigation subnets, and an electric control flow valve is arranged at each drip head in the irrigation subnet to control the flow rate of each drip head according to the instruction of the central control module.

[0017] Further, the atomization subsystem includes: a foliar fertilizer storage tank, a mixed fertilizer supply module, a spray pipe network, an air compressor, and a compressed air pipe network;

[0018] The foliar fertilizer storage tank includes storage tanks for storing potassium, nitrogen, and phosphorus foliar fertilizers respectively. Each storage tank is a pressure storage tank and supplies foliar fertilizers to the mixing fertilizer supply module through pipelines respectively;

[0019] There are multiple mixing fertilizer supply modules, and each mixing fertilizer supply module corresponds to a plant area one by one. Each mixing fertilizer supply module, according to the instruction of the central control module, uses the water supply of the water supply unit and the foliar fertilizer to prepare a foliar fertilizer mixture, and pumps it to the spray subnet at a set pressure according to the instruction of the central control module;

[0020] The spray pipe network consists of multiple non - connected spray subnets;

[0021] The air compressor, according to the instruction of the central control module, provides compressed air with a set pressure to the compressed air pipe network; the pneumatic atomizing nozzles in the spray subnet use the compressed air to atomize and spray the foliar fertilizer mixture. The liquid inlet pipe and air inlet pipe of the atomizing nozzle are respectively provided with an electric control flow valve and an air flow valve, and the flow rates of the foliar fertilizer mixture and the compressed air are adjusted according to the instruction of the central control module.

[0022] Further, the water supply unit includes: a water source, a water pump, a filter, and a controller; the controller receives the instruction of the central control module, controls the water pump to pump water from the water source, and after filtering through the filter, supplies water to the irrigation and fertilization machine and the mixing fertilizer supply module through the water supply pipe network.

[0023] Further, the water and fertilizer demand model is a trained neural network model. Through experiments, the water consumption and the amounts of nitrogen, phosphorus, and potassium consumed by plants of different types and growth cycles in different months, as well as different temperatures, humidities, and light intensities, are collected; one - hot encoding is performed on the plant types as type features, the growth cycle and month are used as time features, and the temperature, humidity, and light intensity values are used as environmental features. The type features, the time features, and the environmental features are used as sample features of the training samples, and the consumed water amount and the amounts of nitrogen, phosphorus, and potassium are used as the results of the training samples. Multiple training samples are divided into a training set and a test set for supervised training and learning to obtain the water and fertilizer demand model.

[0024] Further, the neural network model is a back - propagation neural network, including an input layer, a hidden layer, and an output layer. The output formula of the hidden layer is:

[0025]

[0026] where, H j represents the output of the j - th hidden layer node, l is the total number of hidden layer nodes, f represents the transfer function, ω ijRepresents the connection weight between the i-th input layer node and the j-th hidden layer node. n is the total number of input nodes, and x i Represents the eigenvalue of the i-th input layer node, a j Represents the bias of the j-th hidden layer node; the output formula of the output layer is:

[0027]

[0028] where, O k Represents the output of the k-th output layer node, ω jk Represents the connection weight between the j-th hidden layer node and the k-th output layer node, b k Represents the bias of the k-th output layer node;

[0029] During training, the connection weights and biases of the neural network are updated backward through the prediction error, and the formula is:

[0030]

[0031] ω j ′ k = ω jk + ηH j e k ;

[0032]

[0033] b k ′ = b k + ηe k ;

[0034] where, ω i ′ j 、ω j ′ k 、a′ j 、b k ′ respectively represent the updated values of ω ij 、ω jk 、a j 、b k ,η represents the learning rate, e k represents the error between the k-th output of the output layer and the sample label, e k = y k - o k 。

[0035] Furthermore, the actual water supply amount and the actual fertilizer supply data are obtained through the following methods:

[0036] Actually measure the average root area and average depth of various plants in each growth period, and calculate the standard root system covering soil volume of various plants in each growth period;

[0037] Determine whether the actual planted soil volume of each plant in each planting area of the landscaping is greater than the standard root system covering soil volume. If it is greater, use the standard root system covering soil volume as the root system covering soil volume of the plant; if it is less, use the actual planted soil volume as the root system covering soil volume of the plant;

[0038] Take the product of the root system covering soil volume of the plant and the soil humidity in the plant area where the plant is located as the actual water supply of the plant; take the products of the actual water supply of the plant and the potassium ion concentration, the nitrogen ion concentration, and the phosphorus ion concentration in the plant area where the plant is located respectively as the actual fertilization data of the plant.

[0039] Further, controlling the drip irrigation subsystem or the atomization subsystem to water and / or fertilize specifically includes:

[0040] Step 1, determine whether the actual fertilization data of each plant is less than the required fertilization data. If it is less, use the difference between the actual fertilization data and the required fertilization data as the nitrogen, phosphorus, and potassium fertilization amounts of each plant, and then calculate the total nitrogen, phosphorus, and potassium fertilization amounts in each plant area; determine whether the actual water supply of each plant is less than the required water supply. If it is less, use the difference between the actual water supply and the required water supply as the watering amount of each plant, and then calculate the total watering amount in each plant area;

[0041] Step 2, determine whether the drip irrigation condition is met. If it is met, enter Step 3; otherwise, enter Step 5; the drip irrigation condition is: the soil temperature is greater than the set threshold, and the soil humidity is less than the set threshold;

[0042] Step 3, determine the minimum water demand of the water-fertilizer mixture in each plant area according to the total nitrogen, phosphorus, and potassium fertilization amounts in each plant area and the maximum threshold of the concentration of the water-fertilizer mixture; send the total nitrogen, phosphorus, and potassium fertilization amounts and the minimum water demand to the irrigation and fertilization machine corresponding to the plant area to mix the water-fertilizer mixture; and control the flow rate of the corresponding electric control flow valve in the drip irrigation pipe network according to the nitrogen, phosphorus, and potassium fertilization amounts of each plant to complete fertilization;

[0043] Step 4, determine the watered amount of each plant according to the fertilization amount of each flow valve in Step 3, and subtract the watered amount from the watering amount of each plant in Step 1 to obtain the supplementary watering amount of each plant and determine the total supplementary watering amount in each plant area; send the total supplementary watering amount to the irrigation and fertilization machine corresponding to the plant area to water, and control the flow rate of the corresponding electric control flow valve in the drip irrigation pipe network according to the supplementary watering amount of each plant to complete watering;

[0044] Step 5, determine whether the spray fertilization condition is met. If it is met, enter Step 6; otherwise, enter Step 7; the spray fertilization condition is: the air temperature is within the set threshold range, and the wind speed is less than the set threshold;

[0045] Step 6: Calculate the actual total amounts of nitrogen, phosphorus, and potassium foliar fertilizers based on the total application amounts of nitrogen, phosphorus, and potassium fertilizers in each plant area and the maximum absorption rate of the foliar fertilizer; determine the minimum water requirements for the foliar fertilizer mixture in each plant area according to the actual total amounts of nitrogen, phosphorus, and potassium foliar fertilizers and the maximum concentration threshold of the foliar fertilizer mixture; send the actual total amounts of nitrogen, phosphorus, and potassium foliar fertilizers and the minimum water requirements to the corresponding mixed fertilizer supply module in the plant area to prepare the water-fertilizer mixture; and control the flow rates of the corresponding electronically controlled flow valves in the drip irrigation pipe network according to the application amounts of nitrogen, phosphorus, and potassium fertilizers for each plant and the maximum absorption rate to complete fertilization.

[0046] Step 7: Wait for the set time interval and return to Step 1.

[0047] Furthermore, the maximum absorption rate is obtained by using the particle swarm optimization algorithm to optimize the compressed air flow rate, pressure, and foliar fertilizer flow rate parameters of the atomizing nozzle based on the trained foliar fertilizer absorption rate model; the central control module controls the flow rates of each electronically controlled flow valve and air flow valve and the output pressure of the compressed air according to the optimization results.

[0048] As can be seen from the above technical solutions, compared with the prior art, the present invention discloses an intelligent irrigation system for integrated water and fertilizer management in garden maintenance. By monitoring the real-time monitoring data of the monitoring subsystem, combining with the plant species, growth cycle, and current month, using the trained neural network model to determine the water requirements and fertilizer requirements data, and determining the actual water supply and actual fertilizer supply data according to the actual measurement situation, so as to accurately control the drip irrigation subsystem and the atomizing subsystem to water and fertilize, avoiding the waste of water and fertilizer caused by the traditional flood irrigation method and blind fertilization. Through accurate water and fertilizer supply, only providing appropriate amounts of water and fertilizer when the plants really need it is beneficial to saving water and fertilizer resources; moreover, the accurate water and fertilizer supply avoids the problems of soil water saturation affecting plant root respiration and even root rot caused by over-irrigation, and also reduces the problems of soil salinization and hardening caused by improper fertilizer use, thereby improving the plant growth environment and reducing the possibility of pest and disease occurrence; furthermore, the system reduces the labor cost of garden maintenance and realizes the intelligent management of water and fertilizer in garden maintenance. The present invention can perform water and fertilizer management more scientifically and intelligently, thereby improving the efficiency of water and fertilizer management in garden maintenance. Description of the Drawings

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to the provided drawings.

[0050] Figure 1It is a schematic diagram of the overall structure of an embodiment of the present invention.

[0051] Figure 2 It is a schematic diagram of the drip irrigation subsystem structure of an embodiment of the present invention.

[0052] Figure 3 It is a schematic diagram of the atomization subsystem structure of an embodiment of the present invention. Detailed implementation manners

[0053] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0054] An embodiment of the present invention discloses an intelligent irrigation system for integrated water and fertilizer in garden maintenance, as Figure 1 shown, including: a monitoring subsystem, an interaction module, a storage module, a central control module, a water supply unit, a drip irrigation subsystem, and an atomization subsystem;

[0055] The monitoring subsystem monitors the soil parameters of each plant area and the environmental parameters of the entire garden maintenance area, and sends them to the central control module; the staff inputs the numbers, types, and growth cycles of each plant through the interaction module and stores them in the storage module; the water supply unit supplies water to the drip irrigation subsystem and the atomization subsystem;

[0056] The central control module determines the water demand and fertilizer demand data of each plant according to the environmental parameters, plant types, growth cycles, and the current month by using the trained water and fertilizer demand model; determines the actual water supply and actual fertilizer supply data of the area where each plant is located according to the soil parameters, plant types, and growth cycles; the central control module controls the drip irrigation subsystem or the atomization subsystem to water and / or fertilize according to the water demand and actual water supply, as well as the fertilizer demand data and actual fertilizer supply data.

[0057] In a specific embodiment, the monitoring subsystem includes: a plurality of soil monitoring units and environmental monitoring units, and each soil monitoring unit corresponds to a plant area one by one;

[0058] The soil monitoring unit includes: a soil moisture sensor, a potassium ion concentration sensor, a nitrogen ion concentration sensor, a soil NPK sensor, as well as a data acquisition module, a data transmission module, and a power supply module; the data acquisition module uses the sensors to collect the soil humidity, temperature, potassium ion concentration, nitrogen ion concentration, and phosphorus ion concentration, obtains the soil parameters, and sends them to the central control module through the data transmission module. Specifically, the soil moisture sensor is inserted into multiple points in the plant area to detect the soil humidity and temperature at different positions and depths in the plant area, and the average value is used as the soil humidity and temperature data of the plant area. The content of potassium fertilizer in the soil can be directly detected by the potassium ion concentration sensor; the content of nitrogen fertilizer can be characterized by detecting the concentration of ammonium ions by the nitrogen ion concentration sensor; at present, there is no direct phosphate ion sensor for the content of phosphorus fertilizer, and the soil NPK sensor can be used to detect the soil conductivity and calculate it according to the set coefficient. In order to improve the accuracy of the soil NPK sensor, after obtaining the accurate value through soil sampling and chemical analysis, the set coefficient can be calibrated to improve the accuracy of phosphorus fertilizer detection.

[0059] The environmental monitoring unit includes: an air temperature sensor, an air humidity sensor, a light sensor, and a wind speed sensor, as well as a data acquisition module, a data transmission module, and a power supply module; the data acquisition module uses the sensors to collect the air temperature, humidity, light intensity, and wind speed, obtains the environmental parameters, and sends them to the central control module through the data transmission module.

[0060] In a specific embodiment, as Figure 2 shown, the drip irrigation subsystem includes: a fertilizer storage tank, an irrigation and fertilization machine, and a drip irrigation pipe network;

[0061] The fertilizer storage tank includes storage tanks for storing liquid potassium fertilizer, nitrogen fertilizer, and phosphorus fertilizer respectively. Each storage tank is a pressurized storage tank and supplies liquid fertilizer to the irrigation and fertilization machine through pipelines respectively;

[0062] There are multiple irrigation and fertilization machines, and each irrigation and fertilization machine corresponds to a plant area one by one. Each irrigation and fertilization machine mixes water and liquid fertilizer into a water-fertilizer mixture according to the instructions of the central control module by using the water supply of the water supply unit, and pumps it to the corresponding irrigation subnet under pressure;

[0063] The drip irrigation pipe network is composed of multiple non-connected irrigation subnets. Electrically controlled flow valves are provided at each drip head in the irrigation subnet to control the flow rate of each drip head according to the instructions of the central control module.

[0064] In a specific embodiment, as Figure 3 shown, the atomization subsystem includes: a foliar fertilizer storage tank, a mixed fertilizer supply module, a spray pipe network, an air compressor, and a compressed air pipe network;

[0065] The foliar fertilizer storage tank includes storage tanks for storing potassium, nitrogen, and phosphorus foliar fertilizers respectively. Each storage tank is a pressure storage tank and supplies foliar fertilizers to the mixed fertilizer supply module through pipelines respectively.

[0066] There are multiple mixed fertilizer supply modules, and each mixed fertilizer supply module corresponds to a plant area one by one. Each mixed fertilizer supply module mixes foliar fertilizer with water supplied by the water supply unit to prepare a foliar fertilizer mixture according to the instructions of the central control module, and pumps it to the spray subnet at a set pressure according to the instructions of the central control module.

[0067] The spray pipe network consists of multiple non-connected spray subnets.

[0068] The air compressor provides compressed air at a set pressure to the compressed air pipe network according to the instructions of the central control module. The pneumatic atomizing nozzles in the spray subnet use the compressed air to atomize and spray the foliar fertilizer mixture. The liquid inlet pipe and air inlet pipe of the atomizing nozzle are respectively provided with an electric control flow valve and an air flow valve, and the flow rates of the foliar fertilizer mixture and the compressed air are adjusted according to the instructions of the central control module.

[0069] Specifically, the maintenance of multiple plants is usually involved in landscaping, and the soil environments in each greening area are also different. Therefore, the landscaping area is divided into multiple plant areas. For example, an area with a set area and planted with the same type of plant is divided into a plant area, or an area with a set area and the same terrain and soil characteristics (i.e., the same terrain height, soil texture, depth, density, porosity) is divided into a plant area, so as to monitor soil parameters and control watering and fertilization in different areas, ensuring the accuracy of soil parameter monitoring while reducing the number of monitoring devices.

[0070] A drip irrigation subsystem and an atomization subsystem are separately set for each plant area, so as to facilitate watering and fertilization according to the soil moisture and fertility conditions of each area. And according to the numbers of each plant, drip heads and pneumatic atomizing nozzles corresponding to the numbers are set, and the corresponding electric control flow valves, air flow valves and air compressors can be adjusted by sending instructions through the central control module, so as to accurately control watering and fertilization for each plant and reduce the waste of water and fertilizer resources.

[0071] In a specific embodiment, the water supply unit includes: a water source, a water pump, a filter and a controller; the controller receives the instructions of the central control module, controls the water pump to pump water from the water source, and supplies water to the irrigation and fertilization machine and the mixed fertilizer supply module through the water supply pipe network after filtering by the filter.

[0072] In a specific embodiment, the water and fertilizer demand model is a trained neural network model. Through experiments, the water consumption and the amounts of nitrogen, phosphorus, and potassium consumed by plants of different species and growth cycles are collected under different months, as well as different temperatures, humidities, and light intensities. One-hot encoding is performed on the plant species as the species feature, the growth cycle and month are used as the time features, and the temperature, humidity, and light intensity values are used as the environmental features. The species feature, time feature, and environmental feature are used as the sample features of the training samples, and the water consumption and the amounts of nitrogen, phosphorus, and potassium are used as the results of the training samples. Multiple training samples are divided into a training set and a test set for supervised training and learning to obtain the water and fertilizer demand model.

[0073] Specifically, different plants have different growth conditions and different water and fertilizer requirements at different growth cycles, different months, and different temperature, humidity, and light conditions. By establishing a water and fertilizer demand model, the water and fertilizer requirements of each plant can be determined according to the growth conditions and environmental conditions of the plants. During the experiment, the environmental parameters around the plants can be monitored within a set time period, and the changes in soil parameters can be measured. The water and fertilizer consumption of the plants can be determined based on the changes in water, nitrogen, phosphorus, and potassium in the soil.

[0074] In a specific embodiment, the neural network model is a backpropagation neural network, including an input layer, a hidden layer, and an output layer. The output formula of the hidden layer is:

[0075]

[0076] where H j represents the output of the j-th hidden layer node, l is the total number of hidden layer nodes, f represents the transfer function, ω ij represents the connection weight between the i-th input layer node and the j-th hidden layer node, n is the total number of input nodes, x i represents the feature value of the i-th input layer node, and a j represents the bias of the j-th hidden layer node; the output formula of the output layer is:

[0077]

[0078] where O k represents the output of the k-th output layer node, ω jk represents the connection weight between the j-th hidden layer node and the k-th output layer node, and b k represents the bias of the k-th output layer node;

[0079] During training, the connection weights and biases of the neural network are updated backward through the prediction error, and the formula is:

[0080]

[0081] ωj ′ k = ω jk + ηH j e k ;

[0082]

[0083] b k ′ = b k + ηe k ;

[0084] where ω i ′ j , ω j ′ k , a′ j , b k ′ represent the updated values of ω ij , ω jk , a j , b k respectively, η represents the learning rate, and e k represents the error between the k-th output of the output layer and the sample label, and e k = y k - o k .

[0085] In a specific embodiment, the actual water supply and actual fertilizer supply data are obtained in the following manner:

[0086] The average root area and average depth of various plants in each growth period are actually measured, and the standard root system coverage soil volume of various plants in each growth period is calculated;

[0087] It is determined whether the actual planted soil volume of each plant in various planting areas of the landscaping is greater than the standard root system coverage soil volume. If it is greater, the standard root system coverage soil volume is used as the root system coverage soil volume of the plant; if it is less, the actual planted soil volume is used as the root system coverage soil volume of the plant. Specifically, the root system development of plants is different at different growth stages. The root depth and coverage area of various plants at different growth stages can be detected to estimate the soil coverage volume of the root system, so as to estimate the actual water supply and fertilizer supply capabilities according to the soil water and fertilizer conditions; while the soil volume at the actual planting positions of various plants in the landscaping may be less than the standard coverage volume, such as flower beds, shrubs in flower beds, or trees with limited tree pit positions, etc. By comparing the actual volume with the standard volume, the actual water supply and fertilizer supply can be estimated more accurately.

[0088] The product of the root system of a plant covering the soil volume and the soil humidity in the plant area where the plant is located is used as the actual water supply of the plant; the products of the actual water supply of the plant and the potassium ion concentration, nitrogen ion concentration, and phosphorus ion concentration in the plant area where the plant is located are used as the actual fertilization data of the plant.

[0089] In a specific embodiment, controlling the drip irrigation subsystem or the atomization subsystem for watering and / or fertilizing specifically includes:

[0090] Step 1, determine whether the actual fertilization data of each plant is less than the fertilization requirement data. If it is less, use the difference between the actual fertilization data and the fertilization requirement data as the nitrogen, phosphorus, and potassium fertilization amounts of each plant, and then calculate the total nitrogen, phosphorus, and potassium fertilization amounts in each plant area; determine whether the actual water supply of each plant is less than the water requirement. If it is less, use the difference between the actual water supply and the water requirement as the watering amount of each plant, and then calculate the total watering amount in each plant area;

[0091] Step 2, determine whether the drip irrigation condition is met. If it is met, enter Step 3; otherwise, enter Step 5; the drip irrigation condition is: the soil temperature is greater than the set threshold, and the soil humidity is less than the set threshold; if the soil temperature is too low, the water and fertilizer mixture will freeze, which is not conducive to plant growth, and if the soil humidity is too high, directly irrigating the water and fertilizer mixture is not conducive to the respiration of plant roots and may even easily cause root rot problems.

[0092] Step 3, determine the minimum water requirement of the water and fertilizer mixture in each plant area according to the total nitrogen, phosphorus, and potassium fertilization amounts in each plant area and the maximum concentration threshold of the water and fertilizer mixture; send the total nitrogen, phosphorus, and potassium fertilization amounts and the minimum water requirement to the irrigation and fertilization machine corresponding to the plant area to prepare the water and fertilizer mixture; and control the flow rate of the corresponding electronically controlled flow valve in the drip irrigation pipe network according to the nitrogen, phosphorus, and potassium fertilization amounts of each plant to complete fertilization;

[0093] Step 4, determine the watered amount of each plant according to the fertilization amount of each flow valve in Step 3, and subtract the watered amount from the watering amount of each plant in Step 1 to obtain the supplementary watering amount of each plant and determine the total supplementary watering amount in each plant area; send the total supplementary watering amount to the irrigation and fertilization machine corresponding to the plant area to water, and control the flow rate of the corresponding electronically controlled flow valve in the drip irrigation pipe network according to the supplementary watering amount of each plant to complete watering. By fertilizing first and then supplementing water, the residue of the water and fertilizer mixture in the pipe network can be reduced, avoiding interference with the accuracy of the next watering and fertilization.

[0094] Step 5: Determine whether the conditions for spray fertilization are met. If yes, proceed to Step 6; otherwise, proceed to Step 7. The conditions for spray fertilization are that the air temperature is within the set threshold range and the wind speed is less than the set threshold. When the soil environment does not meet the fertilization conditions, atomized foliar fertilizer can be used for fertilization. During the spraying of foliar fertilizer, it is necessary to avoid adverse effects on plants caused by too low or too high temperature, and ensure that the environmental wind speed is less than the set threshold to reduce the waste of atomized foliar fertilizer caused by environmental wind.

[0095] Step 6: Calculate the actual total amounts of nitrogen, phosphorus, and potassium foliar fertilizers according to the total fertilization amounts of nitrogen, phosphorus, and potassium in each plant area and the maximum absorption rate of foliar fertilizer. Determine the minimum water requirement of the foliar fertilizer mixture in each plant area according to the actual total amounts of nitrogen, phosphorus, and potassium foliar fertilizers and the maximum concentration threshold of the foliar fertilizer mixture. Send the actual total amounts of nitrogen, phosphorus, and potassium foliar fertilizers and the minimum water requirement to the corresponding mixed fertilizer supply module in the plant area to prepare the water-fertilizer mixture. Control the flow rate of the corresponding electric control flow valve in the drip irrigation pipe network according to the fertilization amounts and maximum absorption rates of nitrogen, phosphorus, and potassium in each plant to complete fertilization.

[0096] Step 7: Wait for the set time interval and return to Step 1.

[0097] In a specific embodiment, the maximum absorption rate is obtained by using the particle swarm optimization algorithm to optimize the compressed air flow rate, pressure, and foliar fertilizer flow rate parameters of the atomizing nozzle based on the trained foliar fertilizer absorption rate model. The central control module controls the flow rates of each electric control flow valve and air flow valve and the output pressure of the compressed air according to the optimization results.

[0098] Specifically, the foliar fertilizer absorption of leaves of different plants in different growth cycles varies under different environmental temperatures and humidities. Moreover, the foliar fertilizer absorption is also affected by the foliar concentration and the atomization condition of the fertilizer, showing differences. The atomization condition of the foliar fertilizer is directly related to the compressed air pressure, flow rate (flow rate per unit time) of the atomizing nozzle, and the flow rate of the foliar fertilizer. Therefore, spray experiments are carried out on different types of plants with different growth cycles under different environmental conditions, different foliar fertilizer concentrations, and different atomizing nozzle parameters. The contents of nitrogen, phosphorus, and potassium in the leaves before and after the spray experiment are collected and the difference is calculated. The absorption amounts of nitrogen, phosphorus, and potassium fertilizers by the plants are estimated based on the difference and the total amount of the plant leaves. The ratio of the absorption amount of nitrogen, phosphorus, and potassium fertilizers to the consumption amount of nitrogen, phosphorus, and potassium fertilizers in the spray experiment is used as the absorption rate. Using the plant species, growth cycle, environmental temperature, humidity, light intensity, as well as the foliar fertilizer concentration, air pressure of the atomizing nozzle, air flow rate, and foliar fertilizer flow rate as sample features, and the corresponding absorption rate as the sample label, multiple training samples are sorted into a training set and a validation set according to the experimental results. Using the training set and the validation set, a backpropagation neural network is trained by a supervised training learning method to obtain a foliar fertilizer absorption rate model. The network structure of the backpropagation neural network is similar to that of the water and fertilizer demand model. According to the number of input features and the number of prediction results, the number of nodes in the input layer, hidden layer, and output layer is adjusted correspondingly.

[0099] When performing spray fertilization, the central control module first obtains the environmental parameters, the species and growth cycle of the plants for spray fertilization, and the foliar fertilizer concentration. Then, the particle swarm optimization algorithm is used to determine the absorption rate under the optimal atomizing nozzle parameters as the maximum absorption rate, calculate the actual total amounts of nitrogen, phosphorus, and potassium foliar fertilizers, and control the atomizing nozzle during the foliar fertilizer fertilization process according to the optimal atomizing nozzle parameters.

[0100] Among them, in the particle swarm optimization algorithm, the three parameters of the air pressure, air flow rate, and foliar fertilizer flow rate of the atomizing nozzle are used as the three-dimensional positions of the particles. Step a, initialize the particle swarm, set the number of particles and the number of iterations, and randomly generate the positions and velocities of each particle; Step b, calculate the fitness value of each particle using the trained foliar fertilizer absorption rate model; Step c, update the individual best position and the optimal individual of the population; Step d, update the positions of each particle according to the particle velocity and position update formula; Step e, finally judge whether the maximum number of iterations is reached. If not, return to Step b. If so, output the optimal individual in the population to obtain the optimal atomizing nozzle parameters determined by the particle swarm optimization algorithm.

[0101] The various embodiments in this specification are described in a progressive manner. The key point of each embodiment is to illustrate the differences from other embodiments. The same or similar parts among the various embodiments can be referred to each other. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the description of the method part.

[0102] The foregoing description of the disclosed embodiments enables those skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An intelligent irrigation system for integrated water and fertilizer management in garden maintenance, characterized in that, Including: A monitoring subsystem, an interaction module, a storage module, a central control module, a water supply unit, a drip irrigation subsystem, and an atomization subsystem; The monitoring subsystem monitors the soil parameters of each plant area and the environmental parameters of the entire garden maintenance area, and sends them to the central control module; The staff inputs the numbers, types, and growth cycles of each plant through the interaction module and stores them in the storage module; The water supply unit supplies water to the drip irrigation subsystem and the atomization subsystem; The central control module determines the water demand and fertilizer demand data of each plant according to the environmental parameters, the type of plant, the growth cycle, and the current month, using the trained water and fertilizer demand model; Determine the actual water supply and actual fertilizer supply data of the area where each plant is located according to the soil parameters, the type of plant, and the growth cycle; The central control module controls the drip irrigation subsystem or the atomization subsystem to water and / or fertilize according to the water demand and the actual water supply, and the fertilizer demand data and the actual fertilizer supply data.

2. The integrated intelligent irrigation system for garden maintenance of water and fertilizer according to claim 1, characterized in that, The monitoring subsystem includes: a number of soil monitoring units and environmental monitoring units, and each soil monitoring unit corresponds to a plant area one by one; The soil monitoring unit includes: a soil moisture sensor, a potassium ion concentration sensor, a nitrogen ion concentration sensor, and a soil NPK sensor, as well as a data acquisition module, a data transmission module, and a power supply module; The data acquisition module uses the sensors to collect the soil humidity, temperature, potassium ion concentration, nitrogen ion concentration, and phosphorus ion concentration to obtain the soil parameters, and sends them to the central control module through the data transmission module; The environmental monitoring unit includes: an air temperature sensor, an air humidity sensor, a light sensor, and a wind speed sensor, as well as a data acquisition module, a data transmission module, and a power supply module; The data acquisition module uses the sensors to collect the air temperature, humidity, light intensity, and wind speed to obtain the environmental parameters, and sends them to the central control module through the data transmission module.

3. An intelligent irrigation system for integrated water and fertilizer management in garden maintenance according to claim 1, characterized in that, The drip irrigation subsystem includes: a fertilizer storage tank, an irrigation and fertilization machine, and a drip irrigation pipe network; The fertilizer storage tank includes storage tanks for storing liquid potassium fertilizer, nitrogen fertilizer, and phosphorus fertilizer respectively. Each storage tank is a pressurized storage tank and supplies liquid fertilizer to the irrigation and fertilization machine through pipelines respectively; There are multiple irrigation and fertilization machines, and each irrigation and fertilization machine corresponds to a plant area one by one. Each irrigation and fertilization machine mixes water and fertilizer with the water supplied by the water supply unit according to the instructions of the central control module and pumps it to the corresponding irrigation subnet under pressure; The drip irrigation pipe network is composed of multiple non-connected irrigation subnets. An electronically controlled flow valve is provided at each drip head in the irrigation subnet to control the flow rate of each drip head according to the instructions of the central control module.

4. The intelligent irrigation system for integrated water and fertilizer management in garden maintenance according to claim 3, wherein The atomization subsystem includes: a foliar fertilizer storage tank, a mixed fertilizer supply module, a spray pipe network, an air compressor, and a compressed air pipe network; The foliar fertilizer storage tank includes storage tanks for storing potassium, nitrogen, and phosphorus foliar fertilizers respectively. Each storage tank is a pressurized storage tank and supplies foliar fertilizer to the mixed fertilizer supply module through pipelines respectively; There are multiple said hybrid fertilizer supply modules, and each hybrid fertilizer supply module corresponds to one of the said plant areas. Each hybrid fertilizer supply module, according to the instruction of the said central control module, uses the water supply of the said water supply unit and the foliar fertilizer to prepare a foliar fertilizer mixture, and pumps it to the spray subnet at a set pressure according to the instruction of the said central control module; The said spray pipe network is composed of multiple non - communicating said spray subnets; The said air compressor, according to the instruction of the said central control module, provides compressed air at a set pressure for the said compressed air pipe network; the pneumatic atomizing nozzles in the said spray subnet use the compressed air to atomize and spray out the foliar fertilizer mixture. The liquid inlet pipe and air inlet pipe of the said atomizing nozzle are respectively provided with an electronically controlled flow valve and an air flow valve, and the flow rates of the foliar fertilizer mixture and the compressed air are adjusted according to the instruction of the said central control module.

5. An intelligent irrigation system for integrated water and fertilizer management in garden maintenance according to claim 4, characterized in that, The said water supply unit includes: a water source, a water pump, a filter and a controller; the controller receives the instruction of the said central control module, controls the water pump to draw water from the water source, and supplies water to the said irrigation and fertilization machine and the said hybrid fertilizer supply module through the water supply pipe network after filtering.

6. The intelligent irrigation system for integrated water and fertilizer management in garden maintenance according to claim 1, characterized in that, The said water and fertilizer demand model is a trained neural network model. Through experiments, the water consumption and the amounts of nitrogen, phosphorus and potassium consumed by plants of different species and growth cycles in different months, as well as under different temperatures, humidities and light intensities, are collected; the one - hot encoding of the plant species is used as the species feature, the growth cycle and month are used as the time feature, and the temperature, humidity and light intensity values are used as the environmental features. The said species feature, the said time feature and the said environmental feature are used as the sample features of the training samples, and the said consumed water amount and the amounts of nitrogen, phosphorus and potassium are used as the results of the training samples. Multiple training samples are divided into a training set and a test set for supervised training and learning to obtain the said water and fertilizer demand model.

7. An integrated intelligent irrigation system for garden maintenance of water and fertilizer according to claim 6, characterized in that, The said neural network model is a back - propagation neural network, including an input layer, a hidden layer and an output layer. The output formula of the said hidden layer is: Among them, H j represents the output of the j-th hidden layer node, l is the total number of hidden layer nodes, f represents the transfer function, ω ij represents the connection weight between the i-th input layer node and the j-th hidden layer node, n is the total number of input nodes, x i represents the eigenvalue of the i-th input layer node, a j represents the bias of the j-th hidden layer node; the output formula of the output layer is: Among them, O k represents the output of the k-th output layer node, ω jk represents the connection weight between the j-th hidden layer node and the k-th output layer node, b k represents the bias of the k-th output layer node; During training, the connection weights and biases of the neural network are updated backward through the prediction error, and the formula is: ω j ′ k = ω jk + ηH j e k ; b k ′ = b k + ηe k ; Among them, ω i ′ j 、ω j ′ k 、a′ j 、b k ′ respectively represent the updated values of ω ij 、ω jk 、a j 、b k , η represents the learning rate, e k represents the error between the k-th output of the output layer and the sample label, e k = y k - o k .

8. An integrated intelligent irrigation system for garden maintenance of water and fertilizer according to claim 2, characterized in that, The said actual water supply amount and the said actual fertilizer supply data are obtained in the following way: Actually measure the average root area and average depth of each growth cycle of various plants, and calculate the standard root - covering soil volume of each growth cycle of various plants; Judge whether the actual planting soil volume of each plant in each planting area of the landscaping is greater than the said standard root - covering soil volume. If it is greater, use the standard root - covering soil volume as the root - covering soil volume of the plant. If it is less, use the actual planting soil volume as the root - covering soil volume of the plant; Take the product of the said root - covering soil volume of the plant and the soil humidity of the plant area where the plant is located as the said actual water supply amount of the plant; take the products of the said actual water supply amount of the plant and the potassium ion concentration, the nitrogen ion concentration and the phosphorus ion concentration in the plant area where the plant is located respectively as the said actual fertilizer supply data of the plant.

9. The intelligent irrigation system for integrated water and fertilizer management in garden maintenance according to claim 8, characterized in that, Controlling the said drip irrigation subsystem or the said atomization subsystem to water and / or fertilize specifically includes: Step 1: Determine whether the actual fertilizer supply data of each plant is less than the fertilizer demand data. If it is less, use the difference between the actual fertilizer supply data and the fertilizer demand data as the nitrogen, phosphorus, and potassium fertilizer application amounts for each plant, and then calculate the total nitrogen, phosphorus, and potassium fertilizer application amounts for each plant area. Determine whether the actual water supply of each plant is less than the water demand. If it is less, use the difference between the actual water supply and the water demand as the watering amount for each plant, and then calculate the total watering amount for each plant area. Step 2: Determine whether the drip irrigation condition is met. If it is met, proceed to Step 3; otherwise, proceed to Step 5. The drip irrigation condition is that the soil temperature is greater than the set threshold and the soil humidity is less than the set threshold. Step 3: Determine the minimum water demand for the water-fertilizer mixture in each plant area according to the total nitrogen, phosphorus, and potassium fertilizer application amounts in each plant area and the maximum concentration threshold of the water-fertilizer mixture. Send the total nitrogen, phosphorus, and potassium fertilizer application amounts and the minimum water demand to the irrigation and fertilization machine corresponding to the plant area to prepare the water-fertilizer mixture. Control the flow rate of the corresponding electronically controlled flow valve in the drip irrigation pipe network according to the nitrogen, phosphorus, and potassium fertilizer application amounts of each plant to complete fertilization. Step 4: Determine the water amount already watered for each plant according to the fertilizer application amounts of each flow valve in Step 3, and subtract the already watered amount from the watering amount of each plant in Step 1 to obtain the additional watering amount for each plant and determine the total additional watering amount for each plant area. Send the total additional watering amount to the irrigation and fertilization machine corresponding to the plant area to water, and control the flow rate of the corresponding electronically controlled flow valve in the drip irrigation pipe network according to the additional watering amount of each plant to complete watering. Step 5: Determine whether the spray fertilization condition is met. If it is met, proceed to Step 6; otherwise, proceed to Step 7. The spray fertilization condition is that the air temperature is within the set threshold range and the wind speed is less than the set threshold. Step 6: Calculate the actual total amount of nitrogen, phosphorus, and potassium foliar fertilizers according to the total nitrogen, phosphorus, and potassium fertilizer application amounts in each plant area and the maximum foliar fertilizer absorption rate. Determine the minimum water demand for the foliar fertilizer mixture in each plant area according to the actual total amount of nitrogen, phosphorus, and potassium foliar fertilizers and the maximum concentration threshold of the foliar fertilizer mixture. Send the actual total amount of nitrogen, phosphorus, and potassium foliar fertilizers and the minimum water demand to the mixed fertilizer supply module corresponding to the plant area to prepare the water-fertilizer mixture. Control the flow rate of the corresponding electronically controlled flow valve in the drip irrigation pipe network according to the nitrogen, phosphorus, and potassium fertilizer application amounts of each plant and the maximum absorption rate to complete fertilization. Step 7: Wait for the set time interval and return to Step 1.

10. The intelligent irrigation system for integrated water and fertilizer management in garden maintenance according to claim 9, wherein, The maximum absorption rate is obtained by using the particle swarm optimization algorithm to optimize the compressed air flow rate, pressure, and foliar fertilizer flow rate parameters of the atomizing nozzle based on the trained foliar fertilizer absorption rate model. The central control module controls the flow rates of each electronically controlled flow valve and air flow valve and the output pressure of the compressed air according to the optimization results.

Images