Intelligent regulation and control system for cotton growth in arid region

Abstract

The invention discloses an intelligent regulation and control system for cotton growth in an arid region, and the system comprises the steps: carrying out the periodic fixed-point scanning type soil conductivity detection of a cotton planting region through a conductivity sensor carried by an unmanned plane, and obtaining a soil conductivity time sequence; the camera collects a plurality of remote sensing images of a cotton planting area in real time; the regulation and control terminal performs cotton region division on the complete orthoimage of the cotton planting region according to the position coordinates of the fixed points of the conductivity sensor; constructing a time-varying vector autoregression model, calculating the dynamic influence of a soil conductivity time sequence and meteorological data on the water and salt content through an impulse response function, and determining the contribution degree of each variable to the change of the water and salt content through variance decomposition; screening a to-be-irrigated area, and generating a transverse and longitudinal operation connection path of the irrigation equipment by considering the U-turn area constraint. According to the method, the dynamic influence relation between variables is fully considered, and irrigation requirements are accurately reflected; and the operation path of the irrigation equipment is generated through the path planning module, so that intelligent regulation and control of cotton growth are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of agricultural intelligent regulation and control, and in particular to an intelligent regulation and control system for cotton growth in arid areas. Background Art

[0002] In arid areas, water shortage and soil salt accumulation are the main factors limiting cotton growth. Traditional irrigation and fertilization methods often rely on experience and lack scientific basis, resulting in serious water waste and soil salinization. Intelligent systems for precise control of irrigation and fertilization are of great significance for improving cotton yield and quality.

[0003] Currently, there are a variety of technologies and methods used for crop management in arid areas: obtaining the salt content in the soil to help assess the degree of soil salinization. Using ground images to monitor crop growth and terrain characteristics. Using efficient irrigation systems such as drip irrigation and sprinkler irrigation, combined with timers or manual control for irrigation, etc.

[0004] Although these technologies have improved the efficiency of crop management to a certain extent, they still have the following shortcomings: the collection range of soil conductivity is limited, and the water-salt content obtained by conventional linear calculation methods is difficult to fully reflect soil changes. At present, there is still a lack of effective models and algorithms, which cannot accurately calculate the soil water-salt content and predict future irrigation needs. As a result, it is impossible to effectively irrigate the cotton planting areas that really need irrigation.

[0005] Therefore, how to provide an intelligent regulation system for cotton growth in arid areas that can improve the effectiveness of regulation is a technical problem that needs to be urgently solved by those skilled in the art. Summary of the invention

[0006] In view of the above research status and existing problems, the present invention provides an intelligent control system for cotton growth in arid areas based on soil electrical conductivity and meteorological data, which can realize precise irrigation and fertilization, improve water resource utilization efficiency, reduce soil salinization, and improve cotton yield and quality.

[0007] The present invention provides an intelligent cotton growth control system in arid areas, comprising: a control terminal, and a drone equipped with a conductivity sensor and a camera; wherein:

[0008] The UAV carries a conductivity sensor to perform periodic fixed-point scanning soil conductivity detection in the cotton planting area to obtain a soil conductivity time series;

[0009] The camera is used to collect multiple remote sensing images of the cotton planting area in real time;

[0010] The control terminal comprises:

[0011] A region division module is used to perform mosaic processing on the multiple remote sensing images to generate a complete orthophoto image of the cotton planting area; and to perform region division on the complete orthophoto image of the cotton planting area according to the position coordinates of the conductivity sensor fixed point to obtain a plurality of cotton areas;

[0012] The data storage module is used to store meteorological data;

[0013] The water-salt measurement module is used to construct a time-varying vector autoregression model. The model input variables are soil conductivity time series and meteorological data, and the output target variable is water-salt content. The dynamic impact between different variables is calculated through the impulse response function, and the contribution of each variable to the change of water-salt content is determined through variance decomposition.

[0014] The path planning module is used to screen the areas to be irrigated according to the water and salt content of several cotton areas, and generate the horizontal and vertical operation connection path of the irrigation equipment according to the coordinates of the areas to be irrigated and considering the constraints of the turning area.

[0015] Preferably, the conductivity sensor is located at the bottom of the drone and includes a signal transmitting end and a signal receiving end;

[0016] The signal transmitting end is used to transmit a magnetic field to the earth and stimulate the earth to generate an AC induced magnetic field;

[0017] The signal receiving end is used to receive the AC induced magnetic field signal, and obtain the soil conductivity time series after calculation processing.

[0018] Preferably, the UAV obtains the position coordinates of periodic fixed-point scanning based on the RTK positioning algorithm, and the position coordinates are spliced ​​with the soil conductivity time series collected at the current fixed point as the attribute information of the cotton area.

[0019] Preferably, the step of dividing the complete orthophoto of the cotton planting area into regions according to the position coordinates of the fixed points of the conductivity sensor to obtain a plurality of cotton areas comprises the following steps:

[0020] Construct a complete orthophoto map of the cotton growing area;

[0021] dividing the map into regular grids, each grid representing a cotton region;

[0022] Import the attribute information of the cotton area and distribute it to the corresponding grid.

[0023] Preferably, the step of constructing a time-varying vector autoregression model by the water-salt measurement module includes:

[0024] Setting the parameters of the time-varying vector autoregression model includes:

[0025] Time-varying influence coefficients between soil conductivity time series, meteorological data, and water-salinity content;

[0026] The time-varying vector autoregression model is constructed as:

[0027]

[0028] In the formula, two time series variables y t and x t , represent water-salt content and soil conductivity, respectively, z t is a set of meteorological data, p is the lag order, α is the coefficient that changes with time t, β, γ and δ are the time-varying influence coefficients between the soil conductivity time series, meteorological data and water-salt content, ∈ yt and ∈ xt are the disturbance terms of soil conductivity and meteorological data, respectively;

[0029] The causal relationship matrix is ​​estimated according to the time-varying vector autoregression model, and the impulse response function is calculated using the causal relationship matrix;

[0030] The covariance matrix is ​​calculated according to the model disturbance terms, and the contribution of each input variable to the change of water salt content is obtained through the covariance matrix and impulse response function.

[0031] Preferably, the step of the path planning module screening the areas to be irrigated according to the water-salt content of the plurality of cotton areas comprises: screening out the areas whose water-salt content exceeds the threshold value according to a set threshold value:

[0032] Area to be irrigated = {(x i ,y i )|Water salt content (x i ,y i )>threshold};

[0033] In the formula, the position of each region is expressed by two-dimensional coordinates (x i ,y i )express.

[0034] Preferably, the path planning module generates a horizontal and vertical operation connection path for the irrigation equipment taking into account the U-turn area constraint, comprising:

[0035] Use the path search algorithm to find the shortest horizontal and vertical connection path of irrigation equipment from the starting point through all the areas to be irrigated;

[0036] For each path segment (x i ,y i ) to (x j ,y j ) Check if the path complies with the U-turn area constraints:

[0037] x left≤x min ≤x right and y bottom ≤y min ≤y top ;

[0038] In the formula, x left 、x right ,y bottom ,y top Represents the four boundary points of the U-turn area, x min is the minimum horizontal coordinate of the path segment, y min is the minimum ordinate of the path segment;

[0039] If the path segment meets the U-turn area constraint, an arc U-turn path is automatically generated, and any point (x, y) on the arc is:

[0040]

[0041] Where r is the minimum turning radius of the irrigation equipment, (x c ,y c ) is the center of the circle, and θ is the angle of the arc.

[0042] Preferably, the generation of the U-turn area includes:

[0043] Analyze the shortest equipment horizontal and vertical operation connection path and select turning points in the path;

[0044] Perform U-turn space recognition on the complete orthophoto of the cotton planting area in the cotton area where the turning point is located to obtain the operating width;

[0045] Determine whether the operating width meets the minimum width and minimum length requirements of the U-turn area. If so, perform arc U-turn path calculation; if not, use the path search algorithm to re-plan the shortest equipment horizontal and vertical operation connection path.

[0046] Preferably, it also includes an area calculation module, which is used to calculate the area of ​​the area to be irrigated and calculate the irrigation amount according to the area.

[0047] Preferably, the control terminal is mounted on the irrigation equipment, and the control terminal is wirelessly connected to the drone via a communication module for receiving the soil conductivity time series and the remote sensing image in real time.

[0048] The intelligent control system for cotton growth in arid areas proposed by the present invention has the following beneficial effects compared with the prior art:

[0049] The present invention proposes an intelligent control system for cotton growth in arid areas. It collects soil conductivity data and remote sensing images through drones, combines meteorological data, and uses a time-varying vector autoregression model to calculate water and salt content, fully considering the dynamic influence relationship between variables and accurately reflecting irrigation needs; and generates the operation path of irrigation equipment through a path planning module, realizing intelligent control of cotton growth. The system can significantly improve the accuracy of irrigation and fertilization, improve the efficiency of water resource utilization, reduce soil salinization, and increase the yield and quality of cotton. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without creative work.

[0051] Figure 1 This is a block diagram of an intelligent control system for cotton growth in arid areas provided by an embodiment of the present invention;

[0052] Figure 2 This is a flow chart of intelligent regulation of cotton growth in arid areas provided by an embodiment of the present invention;

[0053] Figure 3 It is a method flow chart of a path planning module provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0054] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0055] like Figure 1 As shown, an embodiment of the present invention provides an intelligent control system for cotton growth in arid areas, comprising: a control terminal, and a drone equipped with a conductivity sensor and a camera; wherein the drone carries the conductivity sensor to perform periodic fixed-point scanning soil conductivity detection in the cotton planting area to obtain a soil conductivity time series; the camera is used to collect multiple remote sensing images of the cotton planting area in real time;

[0056] The control terminals include:

[0057] The regional division module is used to stitch multiple remote sensing images to generate a complete orthophoto of the cotton planting area; the complete orthophoto of the cotton planting area is divided into regions according to the position coordinates of the conductivity sensor fixed point to obtain several cotton areas; the data storage module is used to store meteorological data; the water and salt measurement module is used to construct a time-varying vector autoregression model, the model input variables are soil conductivity time series and meteorological data, the output target variable is water and salt content, the dynamic influence between different variables is calculated through the impulse response function, and the contribution of each variable to the change of water and salt content is determined through variance decomposition; the path planning module is used to screen the areas to be irrigated according to the water and salt content of several cotton areas, and generate the horizontal and vertical operation connection path of the irrigation equipment according to the coordinates of the areas to be irrigated, considering the constraints of the U-turn area.

[0058] The influence of soil conductivity and meteorological data on salt water content is complex and dynamic, rather than static. The relationship between these variables may change with time, season and environmental conditions. Therefore, using only a static linear fitting model may not accurately capture these dynamic changes, resulting in inaccurate prediction results. This embodiment fully clarifies the influence of soil conductivity and meteorological data on real-time soil water and salt content, and provides guidance for implementing regional irrigation and fertilization. The time-varying vector autoregression model allows model parameters to change over time, and when processing non-stationary time series data, it can effectively capture the dynamic relationship between variables and their changes over time.

[0059] In one embodiment, the conductivity sensor is located at the bottom of the drone and includes a signal transmitting end and a signal receiving end;

[0060] The signal transmitting end is used to transmit the magnetic field to the earth and stimulate the earth to generate an AC induced magnetic field;

[0061] The signal receiving end is used to receive the AC induced magnetic field signal, and obtain the soil conductivity time series after calculation processing.

[0062] The working principle of this embodiment is:

[0063] There is a transmitting coil at the signal transmitting end TX, which can generate a primary magnetic field H that changes with time and whose strength gradually weakens with increasing depth in the earth. S This magnetic field can generate a very weak AC induced current in the earth, which in turn induces a secondary magnetic field H P The signal receiving end of the sensor is responsible for receiving the secondary electromagnetic field signal generated by the soil conduction current. The electrical signal received by the sensor, which is proportional to the soil conductivity, is displayed as the soil apparent conductivity δ after calculation and processing. The calculation formula is:

[0064]

[0065] Where: ω = 2πf, f is the transmission frequency (Hz), S is the distance between the transmitter and the receiver (m), μ0 is the spatial magnetic field transmission coefficient, and V is the vertical dipole mode.

[0066] In one embodiment, the drone obtains the position coordinates of periodic fixed-point scanning based on the RTK positioning algorithm, and the position coordinates are spliced ​​with the soil conductivity time series collected at the current fixed point as the attribute information of the cotton area, which is convenient for calling when constructing the cotton area.

[0067] In one embodiment, dividing the complete orthophoto of the cotton planting area into regions according to the position coordinates of the conductivity sensor fixed point to obtain a plurality of cotton regions includes the following steps:

[0068] Construct a complete orthophoto map of the cotton growing area;

[0069] Divide the map into regular grids, each grid representing a cotton area. For example, a 10m x 10m grid can be selected, and each grid is assigned a unique number or identifier for subsequent management and query;

[0070] Import the attribute information of the cotton area and assign it to the corresponding grid. It should be noted that it includes a coordinate matching step: matching the location coordinates of the conductivity sensor with the center point coordinates of the grid to determine the grid to which each conductivity data belongs.

[0071] In one embodiment, Figure 2 As shown, the steps of constructing a time-varying vector autoregression model in the water and salt measurement module include:

[0072] Setting the parameters of the time-varying vector autoregression model includes:

[0073] Time-varying influence coefficients between soil conductivity time series, meteorological data, and water-salinity content;

[0074] The time-varying vector autoregression model is constructed as:

[0075]

[0076] In the formula, two time series variables y t and x t , representing water salt content and soil conductivity, respectively, and a set of meteorological data z t , p is the lag order, α is the coefficient that changes with time t, β, γ and δ are the time-varying influence coefficients between soil conductivity time series, meteorological data and water and salt content, ∈ yt and ∈ xt are the disturbance terms of soil conductivity and meteorological data, respectively;

[0077] The causal relationship matrix is ​​estimated based on the time-varying vector autoregression model, and the impulse response function is calculated using the causal relationship matrix; the impulse response function describes the change of another variable at time t+s after a standard deviation shock is applied to a certain variable at time t; the causal relationship matrix is ​​a lower triangular matrix, the horizontal and vertical coordinates correspond to the influence coefficients of the input variable on the output variable, and its non-zero elements are used to represent the immediate impact of one variable on another variable. In the study of the relationship between soil conductivity, meteorological data and water-salt content, if the water-salt content variable is directly affected by the soil conductivity and meteorological data variables at a certain point in time, then there will be a non-zero value at the corresponding position in the causal relationship matrix to represent this immediate impact.

[0078] The covariance matrix is ​​calculated according to the model disturbance terms, and the contribution of each input variable to the change of water salt content is obtained through the covariance matrix and impulse response function.

[0079] In this embodiment, the variance decomposition can be expressed as:

[0080]

[0081] In the formula, V(y t+h ) is the variance of water-salinity content during the h-step prediction period, σ 2 is the variance of the ith variable, VD i (h) is the contribution of the ith variable to the variance of the h-step forecast period.

[0082] In the specific implementation, the contribution of soil conductivity time series and meteorological data variables to the change of water-salt content is learned using the time-varying vector autoregression model based on the soil conductivity time series, meteorological data and actual water-salt content in the historical time interval. In the real-time testing phase, the real-time soil conductivity time series and meteorological data in the future time interval are used to estimate the real-time water-salt content based on the learned contribution.

[0083] In one embodiment, the step of the path planning module selecting the areas to be irrigated according to the water-salt content of the plurality of cotton areas comprises: selecting the areas whose water-salt content exceeds the threshold according to the set threshold:

[0084] Area to be irrigated = {(x i ,y i )|Water salt content (x i ,y i )>threshold};

[0085] In the formula, the position of each region is expressed by two-dimensional coordinates (x i ,y i )express.

[0086] In one embodiment, Figure 3As shown, the path planning module considers the U-turn area constraint to generate the horizontal and vertical operation connection path of the irrigation equipment, including the following steps:

[0087] A path search algorithm is used to find the shortest horizontal and vertical connection path of the irrigation equipment from the starting point through all the areas to be irrigated; in this embodiment, the area to be irrigated closest to the initial position of the irrigation equipment can be selected as the starting area. The path search algorithm can use the Dijkstra algorithm or the A* algorithm to find the shortest path from the starting point to all nodes.

[0088] For each path segment (x i ,y i ) to (x j ,y j ) Check if the path complies with the U-turn area constraints:

[0089] x left ≤x min ≤x right and y bottom ≤y min ≤y top ;

[0090] In the formula, x left 、x right ,y bottom ,y top Represents the four boundary points of the U-turn area, x min is the minimum horizontal coordinate of the path segment, y min is the minimum ordinate of the path segment;

[0091] If the path segment meets the U-turn area constraint, an arc U-turn path is automatically generated. Any point (x, y) on the arc is:

[0092]

[0093] Where r is the minimum turning radius of the irrigation equipment, (x c ,y c ) is the center of the circle, and θ is the angle of the arc.

[0094] In this embodiment, the boundary of the U-turn area is calculated as follows:

[0095]

[0096] In the formula, the minimum width of the U-turn area is w, the minimum length is l, and the position of the U-turn area is represented by the center point coordinate x d ,y d and the direction angle θ of the U-turn area.

[0097] In one embodiment, generating a U-turn area includes:

[0098] Analyze the shortest equipment horizontal and vertical operation connection path and select the turning points in the path;

[0099] The complete orthophoto of the cotton planting area in the cotton region where the turning point is located is used to perform spatial recognition of the U-turn to obtain the operating width;

[0100] Determine whether the working width meets the minimum width and minimum length requirements of the U-turn area. If so, perform arc U-turn path calculation; if not, use the path search algorithm to re-plan the shortest equipment horizontal and vertical operation connection path.

[0101] It should be noted that irrigation equipment usually operates in both horizontal and vertical directions. Define the horizontal and vertical operation sequence to ensure that the equipment's operation path in each direction is continuous. Connect the paths between horizontal and vertical operations to ensure that the equipment can smoothly switch to the other direction after completing the operation in one direction.

[0102] Horizontal operation path: starting from a horizontal starting point, visit all horizontal areas to be irrigated in sequence.

[0103] Longitudinal operation path: starting from a longitudinal starting point, visit all longitudinal areas to be irrigated in sequence.

[0104] In one embodiment, it also includes an area calculation module for calculating the area of ​​the irrigation area, and calculating the irrigation amount according to the area to meet the irrigation needs of the irrigation equipment when traveling on a single path.

[0105] In one embodiment, the control terminal is mounted on the irrigation equipment, and the control terminal is wirelessly connected to the drone via a communication module for receiving soil conductivity time series and remote sensing images in real time.

[0106] The above is a detailed introduction to the intelligent control system for cotton growth in arid areas provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

[0107] In this article, relational terms such as first and second, etc. are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

Claims

1. An intelligent control system for cotton growth in arid areas, characterized in that: include: Control terminal, and drone equipped with conductivity sensor and camera; among them, The UAV carries a conductivity sensor to perform periodic fixed-point scanning soil conductivity detection in the cotton planting area to obtain a soil conductivity time series; The camera is used to collect multiple remote sensing images of the cotton planting area in real time; The control terminal comprises: A region division module is used to perform mosaic processing on the multiple remote sensing images to generate a complete orthophoto image of the cotton planting area; and to perform region division on the complete orthophoto image of the cotton planting area according to the position coordinates of the conductivity sensor fixed point to obtain a plurality of cotton areas; The data storage module is used to store meteorological data; The water-salt measurement module is used to construct a time-varying vector autoregression model. The model input variables are soil conductivity time series and meteorological data, and the output target variable is water-salt content. The dynamic impact between different variables is calculated through the impulse response function, and the contribution of each variable to the change of water-salt content is determined through variance decomposition. The path planning module is used to screen the areas to be irrigated according to the water and salt content of several cotton areas, and generate the horizontal and vertical operation connection path of the irrigation equipment according to the coordinates of the areas to be irrigated and considering the constraints of the turning area.

2. The intelligent control system for cotton growth in arid areas according to claim 1, characterized in that: The conductivity sensor is located at the bottom of the drone and includes a signal transmitting end and a signal receiving end; The signal transmitting end is used to transmit a magnetic field to the earth and stimulate the earth to generate an AC induced magnetic field; The signal receiving end is used to receive the AC induced magnetic field signal, and obtain the soil conductivity time series after calculation processing.

3. The intelligent control system for cotton growth in arid areas according to claim 1, characterized in that: The UAV obtains the position coordinates of periodic fixed-point scanning based on the RTK positioning algorithm, and the position coordinates are spliced ​​with the soil conductivity time series collected at the current fixed point as the attribute information of the cotton area.

4. The intelligent control system for cotton growth in arid areas according to claim 3, characterized in that: The step of dividing the complete orthophoto image of the cotton planting area into regions according to the position coordinates of the fixed points of the conductivity sensor to obtain a plurality of cotton regions comprises the following steps: Construct a complete orthophoto map of the cotton growing area; dividing the map into regular grids, each grid representing a cotton region; Import the attribute information of the cotton area and distribute it to the corresponding grid.

5. The intelligent control system for cotton growth in arid areas according to claim 1, characterized in that: The step of constructing a time-varying vector autoregression model by the water-salt measurement module includes: Setting the parameters of the time-varying vector autoregression model includes: Time-varying influence coefficients between soil conductivity time series, meteorological data, and water-salinity content; The time-varying vector autoregression model is constructed as: In the formula, two time series variables y t and x t , represent water-salt content and soil conductivity respectively, z t is a set of meteorological data, p is the lag order, α is the coefficient that changes with time t, β, γ and δ are the time-varying influence coefficients between the soil conductivity time series, meteorological data and water-salt content, ∈ yt and ∈ xt are the disturbance terms of soil conductivity and meteorological data, respectively; The causal relationship matrix is ​​estimated according to the time-varying vector autoregression model, and the impulse response function is calculated using the causal relationship matrix; The covariance matrix is ​​calculated according to the model disturbance terms, and the contribution of each input variable to the change of water salt content is obtained through the covariance matrix and impulse response function.

6. The intelligent control system for cotton growth in arid areas according to claim 1, characterized in that: The step of the path planning module selecting the area to be irrigated according to the water-salt content of the plurality of cotton areas comprises: selecting the area whose water-salt content exceeds the threshold value according to the set threshold value: Area to be irrigated = {(x i ,y i )|Water salt content (x i ,y i )>threshold}; In the formula, the position of each region is expressed by two-dimensional coordinates (x i ,y i )express.

7. The intelligent control system for cotton growth in arid areas according to claim 1, characterized in that: The steps of generating a horizontal and vertical operation connection path of the irrigation equipment by the path planning module taking into account the U-turn area constraint include: Use the path search algorithm to find the shortest horizontal and vertical connection path of irrigation equipment from the starting point through all the areas to be irrigated; For each path segment (x i ,y i ) to (x j ,y j ) Check if the path complies with the U-turn area constraints: x left ≤x min ≤x right andy bottom ≤y min ≤y top ; In the formula, x left 、x right ,y bottom ,y top Represents the four boundary points of the U-turn area, x min is the minimum horizontal coordinate of the path segment, y min is the minimum ordinate of the path segment; If the path segment meets the U-turn area constraint, an arc U-turn path is automatically generated, and any point (x, y) on the arc is: Where r is the minimum turning radius of the irrigation equipment, (x c ,y c ) is the center of the circle, and θ is the angle of the arc.

8. The intelligent control system for cotton growth in arid areas according to claim 7, characterized in that: The generation of the U-turn area includes: Analyze the shortest equipment horizontal and vertical operation connection path and select turning points in the path; Perform U-turn space recognition on the complete orthophoto of the cotton planting area in the cotton area where the turning point is located to obtain the operating width; Determine whether the operating width meets the minimum width and minimum length requirements of the U-turn area. If so, perform arc U-turn path calculation; if not, use the path search algorithm to re-plan the shortest equipment horizontal and vertical operation connection path.

9. The intelligent control system for cotton growth in arid areas according to claim 1, characterized in that: It also includes an area calculation module, which is used to calculate the area of ​​the area to be irrigated and calculate the irrigation amount according to the area.

10. The intelligent control system for cotton growth in arid areas according to claim 1, characterized in that: The control terminal is mounted on the irrigation equipment, and the control terminal is wirelessly connected to the drone via a communication module, so as to receive the soil conductivity time series and the remote sensing image in real time.

Images