Variable irrigation control system of translation type sprinkling machine

Abstract

The invention relates to the technical field of crop irrigation, in particular to a variable irrigation control system of a translation type sprinkler, which comprises an irrigation demand acquisition module used for respectively determining irrigation demands corresponding to grid units in a target farmland according to remote sensing data and ground actual measurement data corresponding to the grid units delimited in advance in the target farmland; the control module is used for controlling the translation type sprinkling irrigation machine to execute an irrigation task on the target farmland according to the irrigation requirements corresponding to the grid units in the target farmland and the obtained coordinate information of the translation type sprinkling irrigation machine in the current translation type sprinkling irrigation system; the translation type sprinkling irrigation system comprises a translation type sprinkling irrigation machine and a pump station connected with the translation type sprinkling irrigation machine. According to the variable irrigation control system of the translation type sprinkling machine, the calculation precision of irrigation requirements is remarkably improved, and the problem of uneven irrigation caused by single data deviation is avoided.

Description

Technical Field

[0001] The invention relates to the technical field of crop irrigation, and in particular to a variable irrigation control system for a translational sprinkler. Background Art

[0002] DescriptionWith the development of agricultural technology, modern intelligent irrigation technology has been gradually promoted and applied in agricultural production. Traditional agricultural irrigation methods mostly rely on manual operation or simple timed and quantitative irrigation equipment. This method often cannot accurately irrigate according to the actual needs of the farmland, resulting in water resource waste and uneven crop growth, which restricts the further development of agriculture.

[0003] In recent years, variable rate irrigation (VRI) technology has gradually attracted attention as an important part of precision agriculture. This technology can adjust the irrigation amount according to the actual needs of different areas of farmland and significantly improve the efficiency of water resource utilization. However, the current variable irrigation technology still has the following shortcomings: In the existing technology, the variable irrigation system usually relies on a single data source, such as remote sensing data or a small amount of ground measured data, to calculate the irrigation demand. This method may be affected by problems such as incomplete data and single information source errors in practical applications, resulting in large deviations in the calculation results of irrigation demand, affecting irrigation accuracy. Existing sprinkler irrigation systems mostly use fixed irrigation rates or manually controlled movement speeds. This method cannot dynamically adjust irrigation parameters according to the needs of different regions, resulting in insufficient water in some areas, while other areas may be over-irrigated, which is not conducive to the balanced growth of crops. Although some sprinkler irrigation equipment has automation functions, it still requires a high degree of human intervention in actual operation. For example, the movement trajectory and spraying parameters of the sprinkler need to be set manually, lacking the ability to dynamically optimize based on real-time data. Summary of the invention

[0004] In view of the above-mentioned shortcomings and deficiencies of the prior art, the present invention provides a variable irrigation control system for a translational sprinkler.

[0005] In order to achieve the above object, the main technical solutions adopted by the present invention include:

[0006] The embodiment of the present invention provides a variable irrigation control system for a translational sprinkler, comprising:

[0007] The irrigation demand acquisition module is used to determine the irrigation demand corresponding to each grid unit in the target farmland according to the remote sensing data and ground measured data corresponding to the pre-demarcated grid units in the target farmland;

[0008] A control module, for controlling the translational sprinkler to perform irrigation tasks on the target farmland according to the irrigation demand corresponding to each grid unit in the target farmland and the acquired coordinate information of the translational sprinkler in the current translational sprinkler system;

[0009] The translational sprinkler irrigation system comprises a translational sprinkler irrigation machine and a pump station connected to the translational sprinkler irrigation machine.

[0010] Preferably,

[0011] The translation type sprinkler comprises:

[0012] The sprinkler main body is arranged on a mobile platform;

[0013] A GPS module is provided on the sprinkler body and is used to obtain coordinate information of the translation sprinkler and transmit the coordinate information to the control module;

[0014] A mobile platform connected to the control module, used to drive the sprinkler body to move along a set trajectory in the target farmland under the control of the control module;

[0015] The intelligent sprinkler head is arranged on the sprinkler body and connected to the control module, and is used to irrigate the target farmland according to the working parameters controlled by the control module;

[0016] The working parameters include: the spraying width of the smart sprinkler head and the spraying rate of the smart sprinkler head;

[0017] The pump station comprises:

[0018] A water source pump is used to draw water from a water source and send it to the sprinkler body through a pipeline;

[0019] The flow control valve is used to adjust the water flow delivered to the sprinkler body under the control of the control module.

[0020] Preferably, the control module controls the translational sprinkler to perform the irrigation task on the target farmland according to the irrigation prescription map and the acquired coordinate information of the translational sprinkler in the current translational sprinkler system, specifically including:

[0021] The coordinate information of the translational sprinkler in the current translational sprinkler system is compared with the coordinate range of each grid unit in the target farmland obtained in advance. If the coordinate information of the translational sprinkler in the current translational sprinkler system belongs to the coordinate range of any grid unit, it is determined that the translational sprinkler is located in the grid unit, and according to the irrigation demand corresponding to the grid unit, the moving speed of the translational sprinkler and the working parameters of the intelligent sprinkler head are controlled so that the moving speed and the working parameters meet the first preset condition;

[0022] The first preset condition is: irrigation demand = moving speed × spraying width of the smart sprinkler head × spraying rate of the smart sprinkler head.

[0023] Preferably,

[0024] Remote sensing data is generated based on the surface image data collected by drones equipped with visible light cameras and multispectral cameras, which collect surface image data of grid units through aerial photography;

[0025] The remote sensing data includes raw vegetation index;

[0026] The ground measured data corresponding to the grid unit includes soil data collected by multiple sampling points set in the grid unit;

[0027] The soil data includes soil moisture and soil texture.

[0028] Preferably, the irrigation demand acquisition module determines the irrigation demand corresponding to each grid unit in the target farmland according to the remote sensing data and ground measured data corresponding to the pre-demarcated grid units in the target farmland, specifically including:

[0029] According to the ground measured data corresponding to the pre-delineated grid cells in the target farmland, the corresponding initial vegetation index is obtained;

[0030] Obtaining a final vegetation index according to the initial spectral data and the original vegetation index in the remote sensing data;

[0031] Obtaining initial soil moisture according to the original vegetation index in the remote sensing data;

[0032] Based on the initial soil moisture and the original soil moisture in the ground measured data, a final soil moisture is obtained;

[0033] The original soil moisture is the average value of the soil moisture collected by multiple sampling points set in the grid unit;

[0034] Based on the final vegetation index and final soil moisture, the irrigation demand corresponding to the grid cell is obtained.

[0035] Preferably, the obtaining of the corresponding initial vegetation index according to the ground measured data corresponding to the pre-defined grid cells in the target farmland specifically includes:

[0036] According to the ground measured data corresponding to the pre-delineated grid cells in the target farmland, the corresponding initial vegetation index is obtained using formula (1);

[0037] The formula (1) is:

[0038]

[0039] in,

[0040] A=R NIR，0 -R Red，0 ; B=R NIR，0 +R Red，0 ;

[0041] C=β NIN R NIR，0 -β Red R Red，0 ; D = β NIN R NIR，0 +β Red R Red，0 ;

[0042] R Red，0 is the red light reflectance of the soil in water-free condition obtained in advance;

[0043] β Red is the pre-acquired sensitivity coefficient of soil moisture to the red light band;

[0044] R NIR，0 is the near-infrared reflectivity of the soil in water-free conditions obtained in advance;

[0045] β NIN is the pre-acquired sensitivity coefficient of soil moisture to the near-infrared band;

[0046] SM s is the original soil moisture in the ground-truth data;

[0047] NDVI s is the initial vegetation index.

[0048] Preferably, obtaining the final vegetation index according to the initial spectral data and the original vegetation index in the remote sensing data specifically includes:

[0049] According to the initial spectral data and the original vegetation index in the remote sensing data, the final vegetation index is obtained using formula (2);

[0050] The formula (2) is:

[0051] NDVI f =w1·NDVI d +w2·NDVI s ;

[0052] NDVI f is the final vegetation index;

[0053] NDVI d is the original vegetation index;

[0054]

[0055] Q d The minimum value between the resolution value of the image collected by the visible light camera of the UAV and the resolution value of the image collected by the multispectral camera;

[0056] Q s The number of sampling points set in the grid cell.

[0057] Preferably, obtaining the initial soil moisture according to the original vegetation index in the remote sensing data specifically includes:

[0058] According to the original vegetation index in the remote sensing data, the initial soil moisture is obtained using formula (3);

[0059] The formula (3) includes:

[0060]

[0061] SM g is the value of initial soil moisture;

[0062] a is the first empirical parameter;

[0063] b is the second empirical parameter;

[0064] c is the third empirical parameter.

[0065] Preferably, obtaining the final soil moisture based on the initial soil moisture and the original soil moisture in the ground measured data specifically includes:

[0066] Based on the initial soil moisture and the original soil moisture in the ground measured data, the final soil moisture is obtained using formula (4);

[0067] The formula (4) includes:

[0068]

[0069] SM t is the final soil moisture value;

[0070] α is a first preset weight value;

[0071] β is a second preset weight value;

[0072] γ is the third preset weight value;

[0073] tanh() is the hyperbolic tangent function;

[0074] E corr =k1·P+k2·T+k3·W d;

[0075] P is the current rainfall value;

[0076] T is the current ambient temperature value;

[0077] W d is the current wind speed value;

[0078] k1 is the first preset adjustment parameter;

[0079] k2 is the second preset adjustment parameter;

[0080] k3 is the third preset adjustment parameter;

[0081] β g is the difference between the maximum and minimum initial soil moisture corresponding to the grid cell in the historical time period;

[0082] β s It is the difference between the maximum and minimum values ​​of the original soil moisture corresponding to the grid cell in the historical time period.

[0083] Preferably, based on the final vegetation index and the final soil moisture, the irrigation demand corresponding to the grid unit is obtained, specifically including:

[0084] Based on the final vegetation index and final soil moisture, the inversion model is used to obtain the irrigation demand corresponding to the grid cell;

[0085] The inversion model is:

[0086]

[0087] WD is the irrigation demand corresponding to the grid unit;

[0088] NDVI max The maximum value of the vegetation index corresponding to the crops in the target farmland during the historical period;

[0089] SM opt is the optimal soil moisture value corresponding to the crops in the target farmland obtained in advance;

[0090] ET is the current evapotranspiration rate;

[0091]

[0092] ε is the first preset contribution value;

[0093] σ is the second preset contribution value;

[0094] μ is the calibration coefficient;

[0095] δ is the evapotranspiration correction factor.

[0096] The beneficial effects of the present invention are as follows: the variable irrigation control system of the present invention combines remote sensing data and ground measured data, uses drones to collect multispectral images of farmland, generates original vegetation indexes; and combines measured data such as soil moisture and texture to calculate the irrigation demand of each grid unit. The complementary dual data sources significantly improve the calculation accuracy of irrigation demand and avoid the problem of uneven irrigation caused by single data deviation.

[0097] In the variable irrigation control system of a translational sprinkler of the present invention, the control module dynamically adjusts the movement speed of the sprinkler and the spraying parameters (including spraying width and spraying rate) of the intelligent sprinkler head according to the real-time coordinate information of the sprinkler and the irrigation demand of the target grid unit. This real-time control method ensures that the sprinkler can flexibly respond to the irrigation needs of different areas and realize precise variable irrigation.

[0098] The variable irrigation control system of the translational sprinkler of the present invention automatically obtains the current position of the sprinkler through the synergistic effect of the GPS module and the control module, and compares it with the coordinate range of the farmland grid unit, so as to realize automatic path adjustment and irrigation task execution without manual intervention. The system is intelligent, efficient and easy to operate, which greatly reduces the labor cost and improves the automation level of irrigation operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0099] Figure 1 The present invention is a schematic structural diagram of a variable irrigation control system for a translational sprinkler. DETAILED DESCRIPTION

[0100] In order to better explain the present invention and facilitate understanding, the present invention is described in detail below through specific implementation modes in conjunction with the accompanying drawings.

[0101] In order to better understand the above technical solution, exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to enable a clearer and more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.

[0102] Embodiment 1

[0103] See also Figure 1 This embodiment provides a variable irrigation control system for a translational sprinkler, including:

[0104] The irrigation demand acquisition module is used to determine the irrigation demand corresponding to each grid unit in the target farmland according to the remote sensing data and ground measured data corresponding to the pre-demarcated grid units in the target farmland;

[0105] In this embodiment, the irrigation demand of each grid unit in the target farmland is accurately calculated through remote sensing data and ground measurement data to avoid excessive or insufficient irrigation.

[0106] A control module, for controlling the translational sprinkler to perform irrigation tasks on the target farmland according to the irrigation demand corresponding to each grid unit in the target farmland and the acquired coordinate information of the translational sprinkler in the current translational sprinkler system;

[0107] The translational sprinkler irrigation system comprises a translational sprinkler irrigation machine and a pump station connected to the translational sprinkler irrigation machine.

[0108] Specifically, the translational sprinkler includes:

[0109] The sprinkler main body is arranged on a mobile platform;

[0110] A GPS module is provided on the sprinkler body and is used to obtain coordinate information of the translation sprinkler and transmit the coordinate information to the control module;

[0111] In this embodiment, the GPS location information of the sprinkler body can be obtained in real time through the GPS module and matched with the grid unit coordinates of the farmland to ensure accurate positioning of the irrigation operation.

[0112] A mobile platform connected to the control module, used to drive the sprinkler body to move along a set trajectory in the target farmland under the control of the control module;

[0113] The intelligent sprinkler head is arranged on the sprinkler body and connected to the control module, and is used to irrigate the target farmland according to the working parameters controlled by the control module;

[0114] The working parameters include: the spraying width of the smart sprinkler head and the spraying rate of the smart sprinkler head;

[0115] The pump station comprises:

[0116] A water source pump is used to draw water from a water source and send it to the sprinkler body through a pipeline;

[0117] The flow control valve is used to adjust the water flow delivered to the sprinkler body under the control of the control module.

[0118] In this embodiment, remote sensing data is acquired by a drone (equipped with a visible light camera and a multispectral camera) and transmitted to the irrigation demand acquisition module; ground measured data is collected by on-site sampling equipment and input into the irrigation demand acquisition module. The irrigation demand acquisition module calculates the irrigation demand of each grid unit in the target farmland based on the input data and sends the calculation results to the control module.

[0119] The control module receives the grid unit irrigation demand from the irrigation demand acquisition module and receives the real-time location information provided by the GPS module on the translational sprinkler. It sends control instructions to the mobile platform of the translational sprinkler to adjust the movement speed and trajectory of the sprinkler. It sends control instructions to the intelligent sprinkler head on the sprinkler body to adjust the spraying width and spraying rate. It sends adjustment instructions to the flow control valve of the pump station to control the water flow.

[0120] The sprinkler body includes an intelligent sprinkler head, which is connected to the control module and receives working parameters (spraying width, spraying rate) for variable irrigation. The integrated GPS module is connected to the control module to provide the coordinate information of the sprinkler in real time.

[0121] The mobile platform is connected to the sprinkler body, used to carry the sprinkler and move along the set trajectory according to the instructions of the control module. It is connected to the control module to receive control signals of the moving speed and trajectory. The water source pump draws water from an external water source (such as a canal or reservoir) and transports the water to the sprinkler body through a pipeline. The flow control valve is connected to the control module and receives adjustment instructions to dynamically adjust the water flow to ensure that the irrigation needs are met. The target farmland is divided into grid units, and each grid unit corresponds to a set of irrigation demand data. The translational sprinkler can complete the irrigation task grid by grid unit according to the instructions of the control module.

[0122] In the practical application of this embodiment, the control module controls the translational sprinkler to perform the irrigation task on the target farmland according to the irrigation prescription map and the coordinate information of the translational sprinkler in the current translational sprinkler system obtained, specifically including:

[0123] The coordinate information of the translational sprinkler in the current translational sprinkler system is compared with the coordinate range of each grid unit in the target farmland obtained in advance. If the coordinate information of the translational sprinkler in the current translational sprinkler system belongs to the coordinate range of any grid unit, it is determined that the translational sprinkler is located in the grid unit, and according to the irrigation demand corresponding to the grid unit, the moving speed of the translational sprinkler and the working parameters of the intelligent sprinkler head are controlled so that the moving speed and the working parameters meet the first preset condition;

[0124] The first preset condition is: irrigation demand = moving speed × spraying width of the smart sprinkler head × spraying rate of the smart sprinkler head.

[0125] In this embodiment, the control module can dynamically adjust the parameters of the sprinkler so that each grid unit can accurately meet its irrigation needs, avoiding the phenomenon of excessive or insufficient water in traditional irrigation methods, and improving the yield and quality of farmland crops. At the same time, the coordinated control of the moving speed and spraying parameters ensures the efficient use of irrigation water and avoids the waste of water resources. This embodiment realizes a fully automated variable irrigation process through real-time coordinate positioning and dynamic parameter adjustment. It eliminates the tediousness of traditional manual operations, improves irrigation efficiency and reduces labor costs.

[0126] Compared with the traditional translation sprinkler method that relies on fixed procedures for uniform irrigation, this solution forms a dynamic adjustment mechanism through coordinate positioning combined with grid unit irrigation needs, which significantly improves irrigation accuracy.

[0127] In this embodiment, remote sensing data is generated based on the collected surface image data of the grid unit by using a drone equipped with a visible light camera and a multispectral camera to collect the surface image data of the grid unit through aerial photography;

[0128] The remote sensing data includes raw vegetation index;

[0129] The ground measured data corresponding to the grid unit includes soil data collected by multiple sampling points set in the grid unit;

[0130] The soil data includes soil moisture and soil texture.

[0131] For example, in this embodiment, a drone equipped with a visible light camera and a multispectral camera is used to obtain farmland surface image data through aerial photography. For example, the surface image captured by the visible light camera can reflect the overall distribution of the farmland, the growth status of plants, etc. The multispectral camera generates the original vegetation index (that is, NDVI, i.e., vegetation index) by capturing spectral information of different bands (such as red light, near-infrared bands, etc.). This index can be used to evaluate vegetation coverage, plant health, etc.

[0132] For example, a farmland is divided into multiple 10×10 meter grid cells. After the surface image data captured by the drone during flight is processed, the vegetation index of each grid cell is generated. For example, grid cell A: the original vegetation index = 0.6, indicating that the vegetation is growing well; grid cell B: the original vegetation index = 0.4, indicating that the vegetation growth is weak and may need additional irrigation.

[0133] Several sampling points are set in each grid unit to collect soil-related data, such as soil moisture: measured by a portable moisture meter. Soil texture: the proportion of sand, loam and clay is obtained by particle analysis. For example, the sampling point of grid unit A measures: soil moisture content: 25%; soil texture: mainly sandy soil with low water holding capacity; the sampling point of grid unit B measures: soil moisture content: 15%; soil texture: mainly loam with medium water holding capacity.

[0134] In this embodiment, remote sensing data provides the health status of vegetation from a macro perspective, while ground-measured data provides soil information at a micro level. By comprehensively analyzing these two types of data, the specific irrigation needs of the grid unit can be obtained, for example: Grid unit A: The soil is relatively dry and the original vegetation index is low, so the irrigation amount needs to be increased; Grid unit B: The soil moisture content is good, but the original vegetation index shows that the plant growth is weak, and it may be necessary to add appropriate amount of irrigation and pay attention to other agronomic measures.

[0135] In this embodiment, remote sensing data provides macro-scale surface vegetation information, which helps to quickly identify differences in irrigation needs in farmland. Ground-measured data provides information on specific soil conditions, which can supplement the deficiencies of remote sensing data and ensure the accuracy of irrigation decisions. Traditional methods rely on manual measurement, which is inefficient and difficult to cover large areas of farmland; the use of drone remote sensing technology combined with ground sampling can quickly and comprehensively obtain farmland status data, greatly reducing manpower input and improving efficiency. Accurate grid data provides a scientific basis for variable irrigation, enabling each grid unit to adjust the irrigation amount according to actual needs, avoid over-irrigation or under-irrigation, and improve water resource utilization efficiency.

[0136] In the practical application of this embodiment, the irrigation demand acquisition module determines the irrigation demand corresponding to each grid unit in the target farmland according to the remote sensing data and ground measured data corresponding to the pre-demarcated grid units in the target farmland, specifically including:

[0137] According to the ground measured data corresponding to the pre-delineated grid cells in the target farmland, the corresponding initial vegetation index is obtained; specifically, it includes:

[0138] According to the ground measured data corresponding to the pre-delineated grid cells in the target farmland, the corresponding initial vegetation index is obtained using formula (1);

[0139] The formula (1) is:

[0140]

[0141] in,

[0142] A=R NIR，0 -R Red，0 ; B=R NIR，0+R Red，0 ;

[0143] C=β NIN R NIR，0 -β Red R Red，0 ; D = β NIN R NIR，0 +β Red R Red，0 ;

[0144] R Red，0 is the red light reflectance of the soil in water-free condition obtained in advance; β Red is the pre-acquired sensitivity coefficient of soil moisture to the red light band; R NIR，0 is the near-infrared reflectivity of the soil in anhydrous conditions obtained in advance; β NIN is the pre-acquired sensitivity coefficient of soil moisture to the near-infrared band; SM s is the original soil moisture in the ground-measured data; NDVI s is the initial vegetation index.

[0145] In this embodiment, the formula (1) can calculate the vegetation index more accurately by considering the sensitivity coefficient of soil moisture to the red light and near-infrared bands, thereby improving the accuracy of monitoring the vegetation status of farmland. In addition, the sensitivity coefficient of soil moisture to the red light and near-infrared bands is also introduced into the formula (1), which can effectively correct the influence of soil moisture on the vegetation index, making the calculation result more reliable. This is an innovation of the traditional NDVI calculation method, which can more accurately reflect the influence of soil moisture on the vegetation index. At the same time, the formula (1) is applicable to the calculation of vegetation index under different soil types and moisture conditions, which enhances the adaptability and generalization ability of the model.

[0146] Obtaining a final vegetation index according to the initial spectral data and the original vegetation index in the remote sensing data;

[0147] According to the initial spectral data and the original vegetation index in the remote sensing data, the final vegetation index is obtained using formula (2);

[0148] The formula (2) is:

[0149] NDVI f =w1·NDVI d +w2·NDVI s ;

[0150] NDVI f is the final vegetation index; NDVI d is the original vegetation index;

[0151]

[0152] Q d Q is the minimum value between the resolution of the image collected by the UAV visible light camera and the resolution of the image collected by the multispectral camera; s The number of sampling points set in the grid cell.

[0153] In this embodiment, by comprehensively considering the resolution of the drone visible light camera and the multispectral camera and the number of sampling points in the grid unit, the final vegetation index can be calculated more accurately. Formula (2) balances the influence of the original vegetation index and the initial vegetation index through w1 and w2 to ensure that the final vegetation index is more reliable. w1 and w2 are calculated based on the resolution and the number of sampling points to ensure that the weights of different data sources are reasonably distributed. Therefore, the final vegetation index NDVI is f It is obtained by integrating the original vegetation index and the initial vegetation index and performing weighted averaging based on the weight coefficient. The calculated result is more comprehensive and accurate.

[0154] Obtaining initial soil moisture according to the original vegetation index in the remote sensing data; specifically comprising: obtaining initial soil moisture according to the original vegetation index in the remote sensing data using formula (3);

[0155] The formula (3) includes:

[0156]

[0157] SM g is the value of initial soil moisture; a is the first empirical parameter; b is the second empirical parameter; c is the third empirical parameter.

[0158] Formula (3) of this embodiment can more accurately reflect the nonlinear relationship between soil moisture and vegetation index by combining the exponential function and empirical parameters, thereby improving the accuracy of calculation. The empirical parameters a, b and c in the formula can be adjusted according to different environmental conditions, making the formula more flexible and adaptable. to describe the relationship between soil moisture and vegetation index, which can better capture nonlinear changes.

[0159] Based on the initial soil moisture and the original soil moisture in the ground measured data, a final soil moisture is obtained;

[0160] The original soil moisture is the average value of the soil moisture collected by multiple sampling points set in the grid unit;

[0161] Based on the initial soil moisture and the original soil moisture in the ground measured data, the final soil moisture is obtained using formula (4);

[0162] The formula (4) includes:

[0163]

[0164] SM t is the final soil moisture value; α is the first preset weight value; β is the second preset weight value; γ is the third preset weight value; tanh() is the hyperbolic tangent function;

[0165] E corr =k1·P+k2·T+k3·W d ;

[0166] P is the current rainfall value; T is the current ambient temperature value; W d is the current wind speed value; k1 is the first preset adjustment parameter; k2 is the second preset adjustment parameter; k3 is the third preset adjustment parameter; β g is the difference between the maximum and minimum initial soil moisture corresponding to the grid unit in the historical time period; β s It is the difference between the maximum and minimum values ​​of the original soil moisture corresponding to the grid cell in the historical time period.

[0167] In this embodiment, formula (4) can more accurately calculate the final soil moisture by comprehensively considering the initial soil moisture, the original soil moisture in the ground measured data, and the current environmental factors (rainfall, temperature, wind speed). The weight values ​​α, β, and γ are used to balance the influence of different data sources to ensure that the final soil moisture calculation is more reliable. In addition, formula (4) balances the influence of different data sources by introducing weight coefficients and hyperbolic tangent functions, which can more accurately reflect the contributions of different data sources. The hyperbolic tangent function tanh() can capture the nonlinear relationship between soil moisture and different data sources.

[0168] For example, if the current rainfall is 10 mm, then P = 10; the current ambient temperature is 20 °C, then T = 20; the current wind speed is 5 m / s, then W d =5; the first preset adjustment parameter k1 is 0.5; the second preset adjustment parameter k2 is 0.3; the third preset adjustment parameter k3 is 0.2; then E corr The specific value of is calculated to be 12.

[0169] Assume that the value of initial soil moisture SM g is 0.4; the difference between the maximum and minimum initial soil moisture values ​​of the grid cell in the historical time period is β g is 0.2; the difference between the maximum and minimum original soil moisture values ​​of the grid cell in the historical time period is β sis 0.1; the original soil moisture value SM in the ground measured data s is 0.3, then Assuming α = 0.6, β = 0.3, and γ = 0.1, then the final soil moisture value SM calculated by formula (4) is t Approximately 2.0769.

[0170] Based on the final vegetation index and final soil moisture, the irrigation demand corresponding to the grid cell is obtained, including:

[0171] Based on the final vegetation index and final soil moisture, the inversion model is used to obtain the irrigation demand corresponding to the grid cell;

[0172] The inversion model is:

[0173]

[0174] WD is the irrigation demand corresponding to the grid unit; NDVI max is the maximum vegetation index corresponding to the crops in the target farmland during the historical period; SM opt is the value of the optimal soil moisture corresponding to the crops in the target farmland obtained in advance; ET is the current evapotranspiration rate (reflecting the transpiration and evaporation loss of water (for example, in mm / day));

[0175]

[0176] ε is the first preset contribution value; σ is the second preset contribution value; μ is the calibration coefficient (used to adjust the formula result to the actual unit of water demand (such as mm or m 3 / mu); δ is the evapotranspiration correction coefficient (reflecting the dynamic adjustment of water demand under current meteorological conditions).

[0177] In this embodiment, the inversion model can more accurately calculate the irrigation demand by comprehensively considering the final vegetation index and the final soil moisture. Multiple parameters and correction coefficients are introduced into the inversion model to make the calculation result more accurate. The inversion model balances the influence of the vegetation index and soil moisture through weight coefficients ε and σ to ensure that the final irrigation demand calculation is more reliable.

[0178] Embodiment 2

[0179] This embodiment relates to a variable irrigation control system for a translational sprinkler, which aims to achieve efficient and precise irrigation of each grid unit in the target farmland through accurate irrigation demand assessment and intelligent control. The system is particularly suitable for large agricultural areas, and can significantly improve water resource utilization efficiency, reduce waste, and optimize the crop growth environment.

[0180] The second embodiment provides a variable irrigation control system for a translational sprinkler, including:

[0181] The irrigation demand acquisition module is responsible for determining the irrigation demand of each grid cell based on the remote sensing data and ground measured data corresponding to the pre-demarcated grid cells in the target farmland.

[0182] Remote sensing data is collected by drones equipped with visible light cameras and multispectral cameras to generate information such as the original vegetation index (NDVI). Ground-measured data include parameters such as soil moisture and soil texture, which are obtained by setting multiple sampling points in each grid cell. The initial vegetation index, final vegetation index, initial soil moisture, and final soil moisture are calculated using formulas (1) to (4), thereby obtaining the irrigation requirements of each grid cell.

[0183] The control module is used to receive data from the irrigation demand acquisition module and the current position coordinates of the translational sprinkler provided by the GPS module. The current sprinkler coordinates are compared with the coordinate range of each grid unit. When the sprinkler enters a grid unit, the control module adjusts the working parameters of the sprinkler to meet the irrigation demand of the grid unit. The working parameters include the spraying width and spraying rate of the smart sprinkler head to ensure that the preset condition of "irrigation demand = moving speed × spraying width of the smart sprinkler head × spraying rate of the smart sprinkler head" is met.

[0184] The translational sprinkler irrigation system includes a sprinkler machine, a GPS module, a mobile platform, and an intelligent sprinkler head. The sprinkler machine is installed on the mobile platform, and the GPS module provides real-time location information to the control module. The mobile platform moves along the set trajectory according to the instructions of the control module to ensure coverage of the entire target farmland. The intelligent sprinkler head performs the sprinkler irrigation task according to the working parameters set by the control module.

[0185] The pump station includes a water source pump and a flow control valve. The water source pump draws water from the water source and delivers it to the sprinkler body through a pipeline. The flow control valve adjusts the water flow delivered to the sprinkler body under the command of the control module to ensure the stability and accuracy of the water volume during the irrigation process.

[0186] Specific implementation steps

[0187] Use drones to take aerial photos, collect surface image data and generate remote sensing data.

[0188] Several sampling points are arranged in the target farmland to collect soil samples regularly and analyze soil moisture, texture and other properties.

[0189] Combining remote sensing data with ground-based measured data, the irrigation demand of each grid cell is calculated using formulas (1) to (4).

[0190] The GPS module continuously monitors the location of the sprinkler and sends the coordinate information to the control module.

[0191] The control module dynamically plans the optimal path based on the irrigation prescription map and the current position of the sprinkler to ensure that the sprinkler moves along the predetermined route.

[0192] When the sprinkler enters a specific grid unit, the control module adjusts the movement speed of the sprinkler and the working parameters of the smart sprinkler head according to the irrigation needs of the grid unit.

[0193] For example, in arid areas with high water demand, the spraying rate of the sprinkler head is increased; in moist areas or areas with low water demand, the spraying rate is reduced to save water resources.

[0194] The efficient variable irrigation control system for a translational sprinkler provided in the second embodiment continuously collects feedback on actual irrigation effects during operation, such as soil moisture changes, crop growth conditions, etc. The irrigation strategy is further optimized based on the feedback information to improve overall irrigation efficiency and crop yield. It combines advanced remote sensing technology with ground-measured data analysis to achieve precision irrigation. By dynamically adjusting the working parameters of the sprinkler, it not only improves the utilization rate of water resources, but also provides a scientific basis and technical support for modern agricultural production.

[0195] In the description of the present invention, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0196] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium; it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0197] In the present invention, unless otherwise clearly specified and limited, when a first feature is “on” or “below” a second feature, it may be that the first and second features are in direct contact, or that the first and second features are in indirect contact through an intermediate medium. Moreover, when a first feature is “above”, “above” or “above” a second feature, it may be that the first feature is directly above or obliquely above the second feature, or it may simply mean that the first feature is higher in level than the second feature. When a first feature is “below”, “below” or “below” a second feature, it may be that the first feature is directly below or obliquely below the second feature, or it may simply mean that the first feature is lower in level than the second feature.

[0198] In the description of this specification, the description of the terms "one embodiment", "some embodiments", "embodiment", "example", "specific example" or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.

[0199] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may alter, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A variable irrigation control system for a translational sprinkler, characterized in that: include: The irrigation demand acquisition module is used to determine the irrigation demand corresponding to each grid unit in the target farmland according to the remote sensing data and ground measured data corresponding to the pre-demarcated grid units in the target farmland; A control module, for controlling the translational sprinkler to perform irrigation tasks on the target farmland according to the irrigation demand corresponding to each grid unit in the target farmland and the acquired coordinate information of the translational sprinkler in the current translational sprinkler system; The translational sprinkler irrigation system comprises a translational sprinkler irrigation machine and a pump station connected to the translational sprinkler irrigation machine.

2. The variable irrigation control system of a translational sprinkler according to claim 1, characterized in that: The translation type sprinkler comprises: The sprinkler main body is arranged on a mobile platform; A GPS module is provided on the sprinkler body and is used to obtain coordinate information of the translation sprinkler and transmit the coordinate information to the control module; A mobile platform connected to the control module, used to drive the sprinkler body to move along a set trajectory in the target farmland under the control of the control module; The intelligent sprinkler head is arranged on the sprinkler body and connected to the control module, and is used to irrigate the target farmland according to the working parameters controlled by the control module; The working parameters include: the spraying width of the smart sprinkler head and the spraying rate of the smart sprinkler head; The pump station comprises: A water source pump is used to draw water from a water source and send it to the sprinkler body through a pipeline; The flow control valve is used to adjust the water flow delivered to the sprinkler body under the control of the control module.

3. The variable irrigation control system of a translational sprinkler according to claim 2, characterized in that: The control module controls the translational sprinkler to perform the irrigation task on the target farmland according to the irrigation prescription map and the acquired coordinate information of the translational sprinkler in the current translational sprinkler system, specifically including: The coordinate information of the translational sprinkler in the current translational sprinkler system is compared with the coordinate range of each grid unit in the target farmland obtained in advance. If the coordinate information of the translational sprinkler in the current translational sprinkler system belongs to the coordinate range of any grid unit, it is determined that the translational sprinkler is located in the grid unit, and according to the irrigation demand corresponding to the grid unit, the moving speed of the translational sprinkler and the working parameters of the intelligent sprinkler head are controlled so that the moving speed and the working parameters meet the first preset condition; The first preset condition is: irrigation demand = moving speed × spraying width of the smart sprinkler head × spraying rate of the smart sprinkler head.

4. The variable irrigation control system of a translational sprinkler according to claim 3, characterized in that: Remote sensing data is generated based on the surface image data collected by drones equipped with visible light cameras and multispectral cameras, which collect surface image data of grid units through aerial photography; The remote sensing data includes raw vegetation index; The ground measured data corresponding to the grid unit includes soil data collected by multiple sampling points set in the grid unit; The soil data includes soil moisture and soil texture.

5. The variable irrigation control system for a translational sprinkler according to claim 4, characterized in that: The irrigation demand acquisition module determines the irrigation demand corresponding to each grid unit in the target farmland according to the remote sensing data and ground measured data corresponding to the pre-demarcated grid units in the target farmland, including: According to the ground measured data corresponding to the pre-delineated grid cells in the target farmland, the corresponding initial vegetation index is obtained; Obtaining a final vegetation index according to the initial spectral data and the original vegetation index in the remote sensing data; Obtaining initial soil moisture according to the original vegetation index in the remote sensing data; Based on the initial soil moisture and the original soil moisture in the ground measured data, a final soil moisture is obtained; The original soil moisture is the average value of the soil moisture collected by multiple sampling points set in the grid unit; Based on the final vegetation index and final soil moisture, the irrigation demand corresponding to the grid cell is obtained.

6. The variable irrigation control system for a translational sprinkler according to claim 5, characterized in that: The step of obtaining the corresponding initial vegetation index according to the ground measured data corresponding to the pre-defined grid cells in the target farmland specifically includes: According to the ground measured data corresponding to the pre-delineated grid cells in the target farmland, the corresponding initial vegetation index is obtained using formula (1); The formula (1) is: in, A=R NIR，0 -R Red，0 ;B=R NIR，0 +R Red，0 ; C=β NIN R NIR，0 -b Red R Red，0 ;D=β NIN R NIR，0 +b Red R Red，0 ; R Red，0 is the red light reflectance of the soil in water-free condition obtained in advance; β Red is the pre-acquired sensitivity coefficient of soil moisture to the red light band; R NIR，0 is the near-infrared reflectivity of the soil in water-free conditions obtained in advance; β NIN is the pre-acquired sensitivity coefficient of soil moisture to the near-infrared band; SM s is the original soil moisture in the ground-truth data; NDVI s is the initial vegetation index.

7. The variable irrigation control system for a translational sprinkler according to claim 6, characterized in that: The step of obtaining a final vegetation index according to the initial spectral data and the original vegetation index in the remote sensing data specifically includes: According to the initial spectral data and the original vegetation index in the remote sensing data, the final vegetation index is obtained using formula (2); The formula (2) is: NDVI f =w1·NDVI d +w2·NDVI s ; NDVI f is the final vegetation index; NDVI d is the original vegetation index; Q d The minimum value between the resolution value of the image collected by the visible light camera of the UAV and the resolution value of the image collected by the multispectral camera; Q s The number of sampling points set in the grid cell.

8. The variable irrigation control system for a translational sprinkler according to claim 7, characterized in that: The step of obtaining initial soil moisture according to the original vegetation index in the remote sensing data specifically includes: According to the original vegetation index in the remote sensing data, the initial soil moisture is obtained using formula (3); The formula (3) includes: SMg is the value of initial soil moisture; a is the first empirical parameter; b is the second empirical parameter; c is the third empirical parameter.

9. The variable irrigation control system for a translational sprinkler according to claim 8, characterized in that: Based on the initial soil moisture and the original soil moisture in the ground measured data, the final soil moisture is obtained, specifically including: Based on the initial soil moisture and the original soil moisture in the ground measured data, the final soil moisture is obtained using formula (4); The formula (4) includes: SM t is the final soil moisture value; α is a first preset weight value; β is a second preset weight value; γ is the third preset weight value; tanh() is the hyperbolic tangent function; E corr =k1·P+k2·T+k3·W d ; P is the current rainfall value; T is the current ambient temperature value; W d is the current wind speed value; k1 is the first preset adjustment parameter; k2 is the second preset adjustment parameter; k3 is the third preset adjustment parameter; β g is the difference between the maximum and minimum initial soil moisture corresponding to the grid cell in the historical time period; β s It is the difference between the maximum and minimum values ​​of the original soil moisture corresponding to the grid cell in the historical time period.

10. The variable irrigation control system for a translational sprinkler according to claim 9, characterized in that: Based on the final vegetation index and final soil moisture, the irrigation demand corresponding to the grid cell is obtained, including: Based on the final vegetation index and final soil moisture, the inversion model is used to obtain the irrigation demand corresponding to the grid cell; The inversion model is: WD is the irrigation demand corresponding to the grid unit; NDVI max The maximum value of the vegetation index corresponding to the crops in the target farmland during the historical period; SM opt is the optimal soil moisture value corresponding to the crops in the target farmland obtained in advance; ET is the current evapotranspiration rate; ε is the first preset contribution value; σ is the second preset contribution value; μ is the calibration coefficient; δ is the evapotranspiration correction factor.

Images