A cotton drip irrigation-unmanned aerial vehicle cooperative operation field water rapid replenishment system

Abstract

The application discloses a cotton drip irrigation-unmanned aerial vehicle cooperative operation field water rapid replenishing irrigation system and belongs to the technical field of intelligent agricultural irrigation. The physical execution layer comprises a drip irrigation pipe network subsystem and an unmanned aerial vehicle replenishing irrigation subsystem. The intelligent perception layer comprises a soil moisture detection unit and a crop physiological monitoring unit. The decision control layer comprises an air-ground irrigation cooperation module, a pulse replenishing irrigation strategy module and a three-dimensional path planning module. The application can effectively improve work efficiency, provide per mu yield increase and reduce cost.

Description

Technical Field

[0001] This invention relates to the field of smart agricultural irrigation technology, and more specifically to a rapid field water replenishment system for cotton drip irrigation and drone collaborative operation. Background Technology

[0002] Currently, the functions of air-to-ground irrigation equipment are disconnected, and the delay in emergency water replenishment leads to an increase in the cotton boll shedding rate. At the same time, the pulse irrigation parameters are poorly adapted to soil types, the water infiltration rate fluctuates greatly, and the path planning of drone swarms does not take into account the dynamic characteristics of battery degradation, resulting in a low mission completion rate.

[0003] Therefore, how to provide a rapid field water replenishment system that combines cotton drip irrigation with drone collaborative operation is a problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0004] In view of this, the present invention provides a rapid field water replenishment system for cotton drip irrigation and drone collaborative operation, which solves the technical problems of response delay and collaborative failure of air-ground irrigation system, mismatch between pulse irrigation parameters and soil permeability characteristics, and low task allocation balance of drone swarm.

[0005] To achieve the above objectives, the present invention provides the following technical solution:

[0006] A rapid field irrigation system for cotton drip irrigation and drone collaborative operation includes a collaborative architecture of a physical execution layer, an intelligent sensing layer, and a decision control layer.

[0007] The physical execution layer includes:

[0008] The drip irrigation network subsystem includes an array of pressure regulating valves and zoned flow meters for water supply;

[0009] A drone-based irrigation subsystem is used for emergency irrigation.

[0010] The intelligent sensing layer includes:

[0011] The soil moisture detection unit is equipped with a terahertz wave radar to generate a three-dimensional moisture content cloud map.

[0012] The crop physiological monitoring unit captures canopy transpiration characteristics through multispectral imaging to identify the water stress status of cotton plants;

[0013] The decision control layer includes:

[0014] The air-to-ground irrigation coordination module dynamically allocates drip irrigation and drone operation areas based on real-time water data;

[0015] The pulse irrigation strategy module generates atomization parameter control commands based on soil permeability characteristics;

[0016] The 3D path planning module optimizes the flight path of the UAV swarm and outputs the cooperative flight trajectory of the UAV swarm.

[0017] Furthermore, the UAV rehydration subsystem is equipped with a rehydration device, which includes an atomizing nozzle and a liquid storage bladder for emergency rehydration.

[0018] Furthermore, the soil moisture detection unit includes:

[0019] Perform moisture content inversion to generate a three-dimensional moisture content cloud map:

[0020] ;

[0021] In the formula, Equivalent dielectric constant; The dielectric constant of the soil framework; The dielectric constant of free water; This is the porosity correction factor.

[0022] Furthermore, the air-to-ground irrigation coordination module includes:

[0023] Establish a water deficit index:

[0024] ;

[0025] In the formula, The optimal volumetric moisture content for cotton; To detect volumetric moisture content in real time; D is the water deficit index;

[0026] Determine the water deficit index, and trigger emergency irrigation by drone when D≥0.7.

[0027] Furthermore, the pulse replenishment strategy module includes:

[0028] Penetration Acceleration Model:

[0029] ;

[0030] In the formula, This refers to the pulse infiltration rate; The saturated hydraulic conductivity; This is the pulse gain coefficient; This refers to the spray activation time; This refers to the jet shut-off time.

[0031] Furthermore, the three-dimensional path planning module includes:

[0032] Establish the objective function:

[0033] ;

[0034] In the formula, For drone energy consumption; For the assignment time; , For dynamic weights.

[0035] Furthermore, the three-dimensional path planning module optimizes the flight path of the UAV swarm and outputs the cooperative flight trajectory of the UAV swarm. This includes optimizing the flight path of the UAV swarm using a parameter coupling mechanism of Lévy flight strategy and convergence factor, and outputting the cooperative flight trajectory of the UAV swarm.

[0036] In the early stages of iteration: a large-scale Lévy flight step size was adopted, resulting in a high convergence factor;

[0037] Mid-cycle iteration: Dynamically decrease the Lévy step size to linearly reduce the convergence factor;

[0038] Late iteration stage: small-scale Gaussian perturbation, low convergence factor;

[0039] The formula for generating Lévy's flight stride is:

[0040] ;

[0041] The dynamic convergence factor update equation is:

[0042] ;

[0043] The expression for the parameter coupling mechanism is:

[0044] ;

[0045] In the formula, A is the basic stride. β is the step size scaling factor, and β is the distribution parameter. Let λ be the initial convergence factor and λ be the decay rate. The minimum convergence factor, The maximum diagonal distance of the task region is given by 'iter', and the iteration number is given by 'iter'.

[0046] As can be seen from the above technical solution, compared with the prior art, this invention discloses a rapid field water replenishment system for cotton drip irrigation and drone collaborative operation. Based on a dynamic mask matrix air-ground collaborative mechanism, it reduces the end-to-end delay from identifying local drought areas to initiating replenishment; through a dynamic zoning strategy of drone and drip irrigation network collaborative masking, it eliminates irrigation blind spots and ensures the field water uniformity coefficient; through an infiltration acceleration model and droplet size control, it reduces ineffective evaporation and deep seepage, improving water use efficiency; through terahertz radar to achieve three-dimensional moisture content modeling of the tillage layer, the irrigation amount dynamically matches the cotton growth stage requirements, avoiding soil salinization caused by over-irrigation; and by improving the migratory bird algorithm by introducing a Lévy flight strategy and dynamic convergence factor, it improves the task balance of the drone swarm and reduces battery energy consumption differences. Therefore, this invention can effectively improve operational efficiency, increase yield per acre, and reduce costs. Attached Figure Description

[0047] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0048] Figure 1 This is a schematic diagram of the structure of the present invention. Detailed Implementation

[0049] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0050] Example 1:

[0051] See Figure 1 This invention discloses a rapid field water replenishment system for cotton drip irrigation and drone collaborative operation, comprising a collaborative architecture of a physical execution layer, an intelligent sensing layer, and a decision control layer.

[0052] The physical execution layer includes:

[0053] The drip irrigation network subsystem includes an array of pressure regulating valves and zoned flow meters for water supply;

[0054] A drone-based irrigation subsystem is used for emergency irrigation.

[0055] The intelligent sensing layer includes:

[0056] The soil moisture detection unit is equipped with a terahertz wave radar to generate a three-dimensional moisture content cloud map.

[0057] The crop physiological monitoring unit captures canopy transpiration characteristics through multispectral imaging to identify the water stress status of cotton plants;

[0058] The decision control layer includes:

[0059] The air-to-ground irrigation coordination module dynamically allocates drip irrigation and drone operation areas based on real-time water data;

[0060] The pulse irrigation strategy module generates atomization parameter control commands based on soil permeability characteristics;

[0061] The 3D path planning module optimizes the flight path of the UAV swarm and outputs the cooperative flight trajectory of the UAV swarm.

[0062] Specifically, the physical execution layer includes:

[0063] Drip irrigation network subsystem: responsible for regular water supply, achieving precise pressure control (0.2-0.5MPa) in zones through pressure regulating valves, and monitoring irrigation volume with flow sensors with an error of ≤1.5%.

[0064] Drone-based irrigation subsystem: Equipped with a high-precision atomization device for emergency irrigation, with a single drone covering a radius of 15m and a response delay of ≤3min.

[0065] The intelligent perception layer includes:

[0066] Soil moisture detection unit: Terahertz radar (0.3THz) penetrates the topsoil layer (0-50cm) to generate a three-dimensional moisture content cloud map with a spatial resolution of 3cm.

[0067] Crop physiological monitoring unit: The canopy NDVI index is analyzed by multispectral imaging (400-1000nm) to identify the water stress status of cotton plants.

[0068] The decision-making and control layer includes:

[0069] Air-Ground Collaboration Module: Dynamically divides drip irrigation and drone operation areas to avoid overlapping or omissions in irrigation.

[0070] Pulse irrigation module: Matches pulse parameters according to soil type to improve water infiltration efficiency.

[0071] Path planning module: Optimizes the flight path of drone swarms, reduces energy consumption and improves operational coverage.

[0072] In one specific embodiment, the UAV rehydration subsystem is equipped with a rehydration device, which includes an atomizing nozzle and a liquid storage bladder for emergency rehydration.

[0073] Furthermore, the soil moisture detection unit includes:

[0074] Perform moisture content inversion to generate a three-dimensional moisture content cloud map:

[0075] ;

[0076] In the formula, Equivalent dielectric constant; The dielectric constant of the soil framework; The dielectric constant of free water; This is the porosity correction factor.

[0077] In one specific embodiment, the air-to-ground irrigation coordination module includes:

[0078] Establish a water deficit index:

[0079] ;

[0080] In the formula, The optimal volumetric moisture content for cotton; To detect volumetric moisture content in real time; D is the water deficit index;

[0081] Determine the water deficit index, and trigger emergency irrigation by drone when D≥0.7.

[0082] In one specific embodiment, the pulse irrigation strategy module includes:

[0083] Penetration Acceleration Model:

[0084] ;

[0085] In the formula, This refers to the pulse infiltration rate; The saturated hydraulic conductivity; This is the pulse gain coefficient; This refers to the spray activation time; This refers to the jet shut-off time.

[0086] In one specific embodiment, the three-dimensional path planning module includes:

[0087] Establish the objective function:

[0088] ;

[0089] In the formula, For drone energy consumption; For the assignment time; , For dynamic weights.

[0090] Specifically, the constraints are: when the power is low, energy saving is prioritized; when the power is sufficient, efficiency is prioritized.

[0091] In one specific embodiment, the three-dimensional path planning module optimizes the flight path of the UAV swarm and outputs the cooperative flight trajectory of the UAV swarm. This includes optimizing the flight path of the UAV swarm using a parameter coupling mechanism of Lévy flight strategy and convergence factor, and outputting the cooperative flight trajectory of the UAV swarm.

[0092] In the early stages of iteration: a large-scale Lévy flight step size was adopted, resulting in a high convergence factor;

[0093] Mid-cycle iteration: Dynamically decrease the Lévy step size to linearly reduce the convergence factor;

[0094] Late iteration stage: small-scale Gaussian perturbation, low convergence factor;

[0095] The formula for generating Lévy's flight stride is:

[0096] ;

[0097] The dynamic convergence factor update equation is:

[0098] ;

[0099] The expression for the parameter coupling mechanism is:

[0100] ;

[0101] In the formula, A is the basic stride. β is the step size scaling factor, and β is the distribution parameter. Let λ be the initial convergence factor and λ be the decay rate. The minimum convergence factor, The maximum diagonal distance of the task region is given by 'iter', and the iteration number is given by 'iter'.

[0102] Specifically, the synergistic mechanism between the Lévy flight strategy and the convergence factor:

[0103] Initial iteration (iter < 50):

[0104] A large-scale Lévy flight step (α ~ 10-50m) is used to enhance global search capabilities.

[0105] A high convergence factor (Φ ≈ 2.0) expands population diversity.

[0106] Mid-iteration phase (50 ≤ iter < 150):

[0107] Dynamic decay Lévy step size (α ~ 5-20m)

[0108] Linearly reduce the convergence factor (Φ ≈ 1.5 → 0.8)

[0109] Later stages of iteration (iter ≥ 150):

[0110] Small-scale Gaussian perturbations (α ~ 1-5m) improve local optimization accuracy

[0111] A low convergence factor (Φ ≈ 0.5) accelerates convergence.

[0112] As the iteration number iter increases Automatic decay enables a smooth transition from "coarse search to fine tuning," and the convergence factor Φ is achieved through exponential decay and... This creates a linkage, ensuring that step size adjustment and convergence speed are optimized synchronously.

[0113] Example 2:

[0114] The present invention discloses a method for emergency irrigation testing in cotton fields compared to traditional drip irrigation technology, including:

[0115] Test conditions:

[0116] Location: Xinjiang, the testing area

[0117] Soil type: Sandy loam (sand content 62%)

[0118] Test area: 20 mu (3 drones, 8 drip irrigation zones)

[0119] See Table 1 for parameter settings.

[0120] Table 1 Parameter Setting Table

[0121]

[0122] Data collection:

[0123] Terahertz radar scan: 0.3THz center frequency, 50cm×50cm grid;

[0124] Canopy temperature monitoring: FLIR T1040 infrared thermal imager, sensitivity 0.03℃;

[0125] Experimental results:

[0126] Moisture uniformity coefficient CU = 92.4% (ISO 15886 standard);

[0127] Single-machine operation efficiency: 5.8 acres / hour (compared to 3.2 acres / hour for traditional drones).

[0128] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to the method section.

[0129] The above description of the disclosed embodiments enables those skilled in the art to make or use the 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 invention. Therefore, the invention is not 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. A rapid field irrigation system for cotton drip irrigation and drone-assisted operation, characterized in that, The collaborative architecture includes the physical execution layer, the intelligent perception layer, and the decision control layer: The physical execution layer includes: The drip irrigation network subsystem includes an array of pressure regulating valves and zoned flow meters for water supply; A drone-based irrigation subsystem is used for emergency irrigation. The intelligent sensing layer includes: The soil moisture detection unit is equipped with a terahertz wave radar to generate a three-dimensional moisture content cloud map. The crop physiological monitoring unit captures canopy transpiration characteristics through multispectral imaging to identify the water stress status of cotton plants; The decision control layer includes: The air-to-ground irrigation coordination module dynamically allocates drip irrigation and drone operation areas based on real-time water data; The pulse irrigation strategy module generates atomization parameter control commands based on soil permeability characteristics; The 3D path planning module optimizes the flight path of the UAV swarm and outputs the cooperative flight trajectory of the UAV swarm. The air-to-ground irrigation coordination module includes: Establish a water deficit index: ； In the formula, The optimal volumetric moisture content for cotton; To detect volumetric moisture content in real time; D is the water deficit index; Determine the water deficit index; when D ≥ 0.7, trigger emergency irrigation by drone. The pulse irrigation strategy module includes: Penetration Acceleration Model: ； In the formula, This refers to the pulse infiltration rate; Saturated hydraulic conductivity; This is the pulse gain coefficient; This refers to the spray activation time; This refers to the jet shut-off time.

2. The rapid field irrigation system for cotton drip irrigation and drone collaborative operation as described in claim 1, characterized in that, The UAV rehydration subsystem is equipped with a rehydration device, which includes an atomizing nozzle and a liquid storage bladder for emergency rehydration.

3. The rapid field irrigation system for cotton drip irrigation and drone collaborative operation as described in claim 1, characterized in that, The soil moisture detection unit includes: Perform moisture content inversion to generate a three-dimensional moisture content cloud map: ； In the formula, Equivalent dielectric constant; The dielectric constant of the soil framework; The dielectric constant of free water; This is the porosity correction factor.

4. The rapid field irrigation system for cotton drip irrigation and drone collaborative operation as described in claim 1, characterized in that, The three-dimensional path planning module includes: Establish the objective function: ； In the formula, For drone energy consumption; For the assignment time; , For dynamic weights.

5. A rapid field irrigation system for cotton drip irrigation and drone-assisted operation as described in claim 1, characterized in that, The three-dimensional path planning module optimizes the flight path of the UAV swarm and outputs the cooperative flight trajectory of the UAV swarm. This includes optimizing the flight path of the UAV swarm using a parameter coupling mechanism of Lévy flight strategy and convergence factor, and outputting the cooperative flight trajectory of the UAV swarm. In the early stages of iteration: a large-scale Lévy flight step size was adopted, resulting in a high convergence factor; Mid-cycle iteration: Dynamically decrease the Lévy step size to linearly reduce the convergence factor; Late iteration stage: small-scale Gaussian perturbation, low convergence factor; The formula for generating Lévy's flight stride is: ； The dynamic convergence factor update equation is: ； The expression for the parameter coupling mechanism is: ； In the formula, A is the basic stride. β is the step size scaling factor, and β is the distribution parameter. Let λ be the initial convergence factor and λ be the decay rate. The minimum convergence factor, The maximum diagonal distance of the task region is given by 'iter', and the iteration number is given by 'iter'.

Images