A sensor-based greening maintenance irrigation control system

Abstract

The application belongs to the technical field of garden maintenance irrigation, and specifically relates to a greening maintenance irrigation control system based on sensors, which calls a corresponding precise water demand model of a planned irrigation unit, combines environmental data collected in a current period that influences plant evapotranspiration, calculates a theoretical water demand, synchronously introduces a visual correction signal for adjustment, forms a multi-dimensional water demand evaluation system that integrates climate, soil moisture and plant physiological state, helps to accurately quantify the water demand state of plants in the greening area, then converts the adjusted water demand and geographical coordinate boundary into a control instruction set containing valve opening and closing time and nozzle angle parameters, establishes an accurate spatial mapping from the plant water demand area to the execution equipment, ensures that the irrigation coverage range is consistent with the plant root distribution height, and further performs self-adaptive optimization on the precise water demand model according to feedback data after executing irrigation, so as to realize full-process closed-loop control.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of garden maintenance irrigation, and specifically relates to a green maintenance irrigation control system based on sensors. BACKGROUND

[0002] Green maintenance is a key link for maintaining the ecological and landscape quality of a city, and the fine and intelligent level of irrigation operation directly affects the water resource utilization efficiency and the plant growth state. With the development of the Internet of Things and sensing technology, the green irrigation control technology has gradually evolved from the early manual experience and fixed time sequence control to the automatic control stage based on environmental feedback.

[0003] In the prior art, there are several technical solutions aimed at improving irrigation accuracy. For example, a green maintenance garden irrigation method and device disclosed in Chinese Patent Publication No. CN111109057A intelligently judges the garden water demand condition by fusing air temperature and ground humidity data, accurately calculates the irrigation water quantity and matches the optimal irrigation mode according to the green area, and realizes the upgrading from extensive irrigation to precise water and fertilizer management.

[0004] Another Chinese Patent Publication No. CN116267542A discloses an internet-based grape water and fertilizer irrigation remote monitoring system and method, which automatically obtains key parameters such as the variety, growth period and growth of grapes through image recognition technology, and dynamically corrects the irrigation strategy in combination with real-time meteorological, soil and prediction data, so as to realize the precise self-adaptive adjustment of water and fertilizer ratio and irrigation quantity.

[0005] However, the above-mentioned prior art still has the following obvious limitations: in the water demand analysis aspect, although multi-source environmental and visual data are introduced, there is a lack of dynamic modeling capability for the spatial conduction law of soil moisture and the complex coupling relationship between vegetation transpiration and microenvironment, resulting in that the water demand evaluation is still in a static and isolated analysis mode, and the forward-looking prediction of water stress in the time and space dimensions cannot be realized, and the decision lag problem is prominent.

[0006] In the control execution aspect, the irrigation instruction generation process fails to establish a precise spatial mapping mechanism from the geographical boundary of the plant water demand area to the jet range and angle parameters of the sprinkler, and it is difficult to optimize the coverage range and delivery trajectory of the sprinkler according to the complex planting layout, so that the irrigation operation has a significant deviation in the spatial dimension, and the water resource utilization efficiency still needs to be further improved. SUMMARY

[0007] In order to overcome the shortcomings in the background art, the embodiments of the present application provide a green maintenance irrigation control system based on sensors, which can effectively solve the problems involved in the above background art.

[0008] The purpose of the application can be realized by the following technical scheme: a sensor-based greening maintenance irrigation control system, comprising: an information repository, an environmental monitoring module, a water demand analysis module, an irrigation decision module, and an irrigation execution module.

[0009] The information repository and the environmental monitoring module are connected with the water demand analysis module, the water demand analysis module is connected with the irrigation decision module, the irrigation decision module is connected with the irrigation execution module, and the irrigation execution module is connected with the information repository.

[0010] The information repository pre-stores the identity of a plurality of planned irrigation units in the greening area, the corresponding precise water demand model, and the geographic coordinate boundary thereof on the electronic map.

[0011] The environmental monitoring module collects environmental data affecting plant evapotranspiration in real time, and the environmental data at least includes weather station data and soil moisture data.

[0012] The water demand analysis module calls the corresponding precise water demand model according to the identity, combines the collected environmental data in the current period, calculates the theoretical water demand of each planned irrigation unit, and introduces a visual correction signal to adjust the theoretical water demand.

[0013] The irrigation decision module converts the adjusted theoretical water demand of each planned irrigation unit and the geographic coordinate boundary thereof into a control instruction set for specific irrigation execution equipment, and the control instruction set at least includes the opening and closing time of the target valve and the nozzle angle parameter.

[0014] The irrigation execution module executes the control instruction set and adaptively optimizes the precise water demand model according to the feedback data after irrigation.

[0015] Compared with the prior art, the embodiments of the application have at least the following advantages or beneficial effects: (1) The precise water demand model constructed by the application realizes deep fusion of multi-source environmental data. Firstly, the reference crop evapotranspiration is calculated based on the weather station data collected in the current period to establish a climate-driven water demand benchmark. At the same time, the soil volume water content change sequence is conducted and deduced through a spatial graph structure to output the predicted soil volume water content in a specified time window in the future, realizing the spatio-temporal prediction of soil moisture. On this basis, a visual correction signal is also introduced to dynamically adjust the theoretical water demand by analyzing the normalized vegetation index and leaf color saturation of the plant crown digital image. Finally, a multi-dimensional water demand evaluation system considering climate conditions, soil moisture dynamics and plant physiological state is formed, overcoming the defects of insufficient data fusion of the prior art, thereby accurately quantifying the plant water demand state.

[0016] (2) The application realizes accurate spatial mapping from plant water demand geographic coordinate boundary to nozzle angle parameter. Firstly, the geographic coordinate boundary of each planning irrigation unit is superimposed on an electronic map to form a spatial aggregation area, and the spatial relationship is calculated based on the effective coverage range of the nozzle to determine the valve and nozzle number that need to be started. Then, the maximum overlap of the nozzle coverage range and the plant root distribution area of the corresponding planning irrigation unit is taken as the target, and the optimal pitch angle and horizontal deflection angle are calculated for each nozzle that needs to be started. The finally optimized angle combination is output to the nozzle driving device to ensure that the water resource delivery range is highly consistent with the plant root distribution area, and the irrigation deviation problem caused by the lack of spatial mapping mechanism in the prior art is fundamentally overcome. BRIEF DESCRIPTION OF DRAWINGS

[0017] The application will be further described with reference to the accompanying drawings, but the embodiments in the drawings do not constitute any limitation on the application. For ordinary skilled persons in the art, other drawings can be obtained without creative labor on the basis of the following drawings.

[0018] Figure 1 It is a schematic diagram of module connection of the application.

[0019] Figure 2 It is a logic diagram for determining the valve and nozzle number that need to be started in the control instruction set of the application.

[0020] Figure 3 It is a logic diagram for obtaining the nozzle angle parameter in the control instruction set of the application. DETAILED DESCRIPTION

[0021] The technical solutions in the embodiments of the application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, not all the embodiments. Based on the embodiments in the application, all other embodiments obtained by ordinary skilled persons in the art without creative labor are within the protection scope of the application.

[0022] Referring to Figure 1 The application provides a sensor-based greening maintenance irrigation control system, which comprises an information repository, an environment monitoring module, a water demand analysis module, an irrigation decision module and an irrigation execution module.

[0023] The information repository and the environment monitoring module are connected with the water demand analysis module, the water demand analysis module is connected with the irrigation decision module, the irrigation decision module is connected with the irrigation execution module, and the irrigation execution module is connected with the information repository to form a closed loop.

[0024] The information repository pre-stores the identity of a plurality of planning irrigation units in the green area, corresponding precise water demand models, and geographical coordinate boundaries on an electronic map.

[0025] The planning irrigation unit is a basic unit for independent irrigation management by the system, which can be pre-defined according to the plant type and the expected growth scale, as an example, for the same tree category A, a plurality of sub-areas such as tree A1 area, tree A2 area, and tree A3 area can be divided according to a specific number or planting cluster layout, each sub-area has an independent identity and a precise water demand model.

[0026] The environment monitoring module collects environmental data affecting plant evapotranspiration in real time, and the environmental data at least includes weather station data and soil moisture data.

[0027] The water demand analysis module calls the corresponding precise water demand model according to the identity, combines the collected environmental data in the current period, calculates the theoretical water demand of each planning irrigation unit, and introduces a visual correction signal to adjust the theoretical water demand.

[0028] In a preferred embodiment of the present application, the construction and calling of the precise water demand model includes the following steps: according to the preset crop coefficient curve of different types of plants, a specific crop coefficient corresponding to the current phenophase of the plant in the planning irrigation unit is matched.

[0029] According to the weather station data collected in the current period, the weather station data at least includes the average temperature, humidity, wind speed and solar net radiation value of each day in the current period, the weather parameters of each day are substituted into the Penman-Monteith formula, and the calculation results of the formula are accumulated to obtain the reference crop evapotranspiration of the planning irrigation unit. It should be noted that the Penman-Monteith formula is a standard calculation formula for existing crop evapotranspiration, which is not described in detail.

[0030] The soil volume water content change sequence of each monitoring point in the current period soil moisture data is extracted, and the soil water stress coefficient of the planning irrigation unit is dynamically calculated in combination with the plant stress critical water content.

[0031] The plant stress critical water content refers to the soil water content threshold at which the plant root system starts to have difficulty in absorbing water when the soil water content decreases to a certain level, resulting in inhibition of its physiological activity, and the data is derived from special scientific research on the water stress physiology of various plants, and the specific assignment follows one or a combination of the following principles: directly quoting the recommended value in the published physiological research literature or garden maintenance specifications of the category of plants.

[0032] According to the drought tolerance category of the dominant plant in the planning irrigation unit, an empirical water content interval is assigned to it, and the lower limit is the stress threshold.

[0033] The specific crop coefficient, the soil water stress coefficient, and the cumulative operation result of the reference crop evapotranspiration are used as the theoretical water requirement of the planning irrigation unit.

[0034] Therefore, the construction of the precise water requirement model follows the core principles of plant physiology driving, environmental factor regulation, and soil state feedback. Specifically, the specific crop coefficient defines the potential maximum water requirement of the plant, the soil water stress coefficient reflects the actual inhibition degree of soil water conditions on plant growth, and the reference crop evapotranspiration represents the evaporation driving force exerted by the current meteorological conditions. The plant identity, meteorological environment, and soil moisture are coupled in a unified product mathematical framework to evolve into a mathematical model, aiming to dynamically simulate the actual water consumption of the plant in the planning irrigation unit under real environment.

[0035] In addition, the existing method considers each monitoring point as an independent individual for calculation, which is difficult to reflect the conduction rule and continuous change of soil moisture in space, resulting in lag and one-sidedness in stress coefficient evaluation. To solve this problem, the present application organizes discrete monitoring points into a network that can represent their spatial correlation to achieve more accurate simulation and deduction of soil moisture dynamics.

[0036] Therefore, in a preferred embodiment of the present application, the soil water stress coefficient dynamic calculation process includes defining the spatial graph structure of the planning irrigation unit, wherein the monitoring points are nodes, and the weighted edges are constructed between the nodes based on the spatial Euclidean distance and the soil water conductivity characteristics.

[0037] Specifically, the weight value of the edge follows the principle of decreasing with the increase of the spatial Euclidean distance between nodes and increasing with the increase of the soil water conductivity characteristics between nodes. As a calculation example of the edge weight value, the spatial Euclidean distance between two nodes is taken as the denominator, and the soil saturated hydraulic conductivity between two nodes is taken as the numerator. The operation result of the ratio is taken as the edge weight value. It should be particularly noted that this example is only a direct mathematical implementation method, which aims to make a relative comparison of the scale and has been normalized in dimension, and does not involve specific physical unit conversion. In other embodiments, the implementer can use more complex functions or models to define the calculation method as long as the final result meets the above principle.

[0038] The soil volume moisture content change sequence of each monitoring point obtained in the current period is input into the spatial graph structure, and the predicted soil volume moisture content and the predicted change slope of each monitoring point after a specified time window in the future are output through soil moisture space conduction deduction in the graph structure, and the specific deduction process is as follows: for each monitoring point, linear regression analysis is performed based on the soil volume moisture content change sequence to obtain the best fitting function of the soil moisture content change with time of the monitoring point.

[0039] The target time point after the specified time window in the future is substituted into the best fitting function to calculate the predicted soil volume moisture content of the monitoring point based on the time level.

[0040] Based on the spatial graph structure, a first-order graph convolution operation is performed to aggregate the prediction information of each monitoring point and its neighbor nodes.

[0041] The specific process of the first-order graph convolution is to construct an adjacency matrix, the row and column of which correspond to the monitoring point number, and the matrix element When there is an edge between nodes i and j, the edge weight is equal to 0, otherwise, the adjacency matrix completely records the connection relationship and spatial correlation strength between all nodes in the spatial graph structure.

[0042] A degree matrix is constructed, which is a diagonal matrix, and the diagonal line element is the sum of all elements in the i-th row of the adjacency matrix, and the degree matrix quantifies the connection importance or influence of each node in the spatial network.

[0043] The symmetric normalized adjacency matrix is calculated using the degree matrix.

[0044] The vector composed of the predicted soil volume moisture content of all monitoring points based on the time level is multiplied by the normalized adjacency matrix to obtain the predicted soil volume moisture content of all monitoring points based on the spatial level.

[0045] The fitting determination coefficient corresponding to the time level prediction of each monitoring point is calculated, and an adaptive weight is assigned to the time level prediction according to the size of the determination coefficient, and the principle of the assignment is that the larger the determination coefficient, the higher the time weight allocation, and the difference between 1 and the time weight allocation is further taken as the spatial weight allocation.

[0046] As an example, the default weight allocation under the time dominance is set to 0.7, when the determination coefficient is high, the default weight allocation is modified to 0.8, and when the determination coefficient is low, the default weight allocation is modified to 0.6.

[0047] According to the adaptive weight, the weighted average calculation of the predicted soil volume moisture content of each monitoring point at the time level and the spatial level is performed to obtain the final predicted soil volume moisture content.

[0048] The predicted soil volumetric water content is compared with the critical water content of plant stress of the planning irrigation unit, and when the predicted value is not lower than the critical value, the negative correlation mapping result of the predicted change slope is taken as the soil moisture stress coefficient of the monitoring point, otherwise the highest stress coefficient is directly assigned.

[0049] As an example of the negative correlation mapping result of the predicted change slope, the predicted change slope can be substituted into a standard exponential decay function. In other embodiments, the implementer can also follow the core principle of negative correlation mapping and use other types of monotonically decreasing functions to achieve similar proportional mapping, such as piecewise functions or S-shaped functions, the essence of which is to convert trend information into a standardized regulation parameter that can be used for subsequent calculation.

[0050] Based on the weight of the connected edge of each monitoring point in the spatial graph structure, its representative weight is determined.

[0051] The soil moisture stress coefficients of all monitoring points in the planning irrigation unit are weighted and fused with the representative weight, and the output is the soil moisture stress coefficient of the planning irrigation unit. It should be noted that the weighted fusion here is a weighted average method, that is, the product of the soil moisture stress coefficient of all monitoring points and the corresponding representative weight is accumulated, and the accumulated result is divided by the sum of all representative weights.

[0052] In a preferred embodiment of the present application, a visual correction signal is introduced to adjust the theoretical water requirement, including: periodically collecting digital images of plant canopy through cameras deployed in the green area.

[0053] The digital images are analyzed to calculate the normalized vegetation index and leaf color saturation.

[0054] It should be noted that the calculation of the normalized vegetation index is based on the near-infrared band reflectance and the red band reflectance in the digital image. The basic principle is that healthy vegetation has significant differences in spectral response at different bands: in the near-infrared band, the sponge tissue inside the plant leaves scatters the incident light strongly, resulting in high reflectivity.

[0055] In the red band, chlorophyll absorbs a large amount of visible light in this interval for photosynthesis, resulting in low reflectivity.

[0056] Therefore, the healthier and denser the vegetation, the higher the near-infrared reflectivity and the lower the red reflectivity.

[0057] Based on the above characteristics, the calculation of the normalized vegetation index consists of two key steps: subtracting the near-infrared and red band reflectance, and using the resulting difference to represent the vigor state of the vegetation. The larger the difference, the more significant the spectral characteristics of the vegetation, which generally reflects its more vigorous and healthy growth.

[0058] The sum of the two-band reflectance is taken as a reference, and the aforementioned difference is divided by the sum to finally obtain the normalized vegetation index.

[0059] The ratio structure effectively eliminates part of the light and terrain interference, and constrains the result in the standard range of -1 to 1, thereby realizing stable quantitative evaluation of the vegetation coverage condition.

[0060] The leaf color saturation specifically refers to the average saturation of all pixels in the canopy area after the digital image is converted to the HSL color space.

[0061] If the normalized vegetation index is lower than the health threshold or the leaf color shows wilting signs, a visual correction signal is generated.

[0062] The health threshold of the normalized vegetation index is obtained based on historical image data of plants in the target area in the vigorous growth period. To construct the health reference interval, the following exemplary division method can be used: all normalized vegetation index values obtained from the historical data are arranged in ascending order to determine the statistical distribution. The lower quartile of the sequence is taken as the lower limit of the health reference interval, and the upper quartile is taken as the upper limit, thereby defining the typical value range of healthy vegetation. In this scheme, the lower limit value of the health reference interval is specifically defined as the health threshold for judging the health condition of the vegetation.

[0063] In addition, if the current normalized vegetation index is lower than the health threshold, it is determined that there is a biomass decay phenomenon, and the decrease amplitude ratio of the current normalized vegetation index relative to the health threshold is taken as the biomass decay trend indicator.

[0064] The wilting sign is determined by calculating the decrease amplitude of the current leaf color saturation relative to the recent reference level, and combining the ratio change of the specific color channel. Specifically, when the vegetation shows a continuous decrease in leaf color saturation within a preset time window, accompanied by a simultaneous increase in the red / green channel ratio, the coordinated change of such spectral characteristics constitutes a typical sign of wilting of the vegetation.

[0065] The absolute values of the decrease amplitude of the leaf color saturation and the increase amplitude of the red / green channel ratio at the start time point and the end time point of the preset time window are calculated, and the sum of the two absolute values is taken as the severity indicator of the wilting sign.

[0066] By combining the biomass decay trend represented by the normalized vegetation index and the severity of the wilting sign, a visual correction factor is obtained to adjust the theoretical water requirement upward.

[0067] To control the upward adjustment amplitude of the theoretical water requirement, the value range of the visual correction factor needs to be controlled to Those skilled in the art should know that this value range is only an example, where 1 indicates that there is no need for additional visual adjustment, and 1.5 indicates that the preset maximum visual adjustment amplitude has been reached. The implementer can also customize the upper limit value of this interval according to factors such as the drought tolerance of specific crops, climate regions, and irrigation strategies.

[0068] According to this value range constraint, first, the biomass decay trend index represented by the normalized vegetation index and the severity index of the wilting indicator are accumulated to obtain a comprehensive stress index.

[0069] Subsequently, the comprehensive stress index is substituted into the function designed for value range scaling for calculation.

[0070] An exemplary formula is given here, which only shows how to scale the input value of unbounded or wide-bounded to the interval: .

[0071] wherein is a visual correction factor, is a comprehensive stress index, and the formula structure ensures that the output value is mapped to the interval, and then this interval is linearly scaled to the target value range .

[0072] This formula is only one of the mathematical means to achieve value range constraints, and no more detailed explanation is given. The implementer can replace it with other functions with saturation characteristics for the same purpose.

[0073] The precision water demand model constructed by the embodiment of the present application realizes deep fusion of multi-source environmental data. First, the reference crop evapotranspiration is calculated based on the meteorological station data collected in the current period to establish a climate-driven water demand benchmark. At the same time, the soil volume water content change sequence is conducted and deduced through a spatial graph structure to output the predicted soil volume water content in a specified time window in the future, realizing the spatio-temporal prediction of soil moisture. On this basis, a visual correction signal is also introduced, and the theoretical water demand is dynamically adjusted by analyzing the normalized vegetation index and leaf color saturation of the plant canopy digital image. Finally, a multi-dimensional water demand evaluation system that comprehensively considers climate conditions, soil moisture dynamics, and plant physiological state is formed, overcoming the defects of insufficient data fusion of the prior art, thereby accurately quantifying the plant water demand state.

[0074] The irrigation decision module converts the adjusted theoretical water demand of each planned irrigation unit and its geographic coordinate boundary into a control instruction set for specific irrigation execution equipment, and the control instruction set at least includes the opening and closing time of the target valve and the nozzle angle parameter.

[0075] ​To ensure the accuracy of flow control, during the system debugging stage, the water flow at different opening degrees of the valve is monitored and recorded by the flow sensor, the opening degree is adjusted to the corresponding position where the flow is stable at the rated flow value of the valve, and this opening degree parameter is set as the default working opening degree of the whole system. The calibration result provides a reliable flow basis for subsequent accurate calculation of the valve opening time.

[0076] On this basis, in a preferred embodiment of the present application, the control instruction set conversion process of the specific irrigation execution device includes: marking the adjusted theoretical water demand as the actual water demand.

[0077] Marking the planned irrigation unit whose actual water demand reaches the irrigation start standard value as having irrigation demand.

[0078] The irrigation start standard value is defined as the minimum threshold of the allowable water demand for triggering an effective irrigation operation, directly reflecting the decision sensitivity and management economy of the irrigation system. The setting of this standard value is based on the following: management decision level: it represents the minimum effective irrigation amount set by the system manager to balance plant water demand and operation cost. When the water demand is lower than this standard, the operation cost of starting irrigation may be higher than the agronomic benefit it brings, so it is considered as uneconomical operation.

[0079] Technical system level: this value can be linked to the minimum effective water supply amount of a single operation of the irrigation system. For example, to ensure irrigation uniformity or avoid surface runoff, the system must reach a minimum water amount for a single irrigation to be considered effective.

[0080] Exemplarily, the irrigation start standard value is set to 8mm in the present application.

[0081] Superimpose the geographical coordinate boundaries of all planned irrigation units with irrigation demand on the electronic map to form a spatial aggregation area.

[0082] According to the spatial relationship calculation of the spatial aggregation area and the effective coverage range of each nozzle in the green area execution unit, determine the valve and nozzle numbers that need to be started.

[0083] According to the actual water demand of each planned irrigation unit with irrigation demand, the rated flow of the corresponding irrigation pipe network and the irrigation efficiency, calculate the theoretical opening time of each valve that needs to be started to plan the opening and closing time.

[0084] Taking the maximum coincidence of the nozzle coverage range and the plant root distribution area of the corresponding planned irrigation unit as the goal, calculate the optimal pitch angle and horizontal deflection angle for each nozzle that needs to be started.

[0085] Referring to Figure 2As shown, in a preferred embodiment of the present application, the process of determining the number of valves and nozzles to be started includes: modeling the effective coverage range of each nozzle as a polygonal area with the installation position as the center and the nominal range as the radius.

[0086] Calculate the intersection ratio of the effective coverage range of each nozzle and the geometric boundary of the spatial aggregation area.

[0087] According to the size of the intersection ratio, sort all nozzles with non-empty intersection with the spatial aggregation area in descending order.

[0088] Select nozzles in order from the first position of the list until the union set of the effective coverage range of the selected nozzles can completely cover the spatial aggregation area, and determine the selected nozzles as the nozzles to be started and record their numbers.

[0089] According to the preset nozzle and valve control relationship mapping table, determine and output the numbers of all valves to be linked.

[0090] In a preferred embodiment of the present application, the process of calculating the theoretical opening duration includes: accumulating the actual water demand of the planning irrigation unit associated with the valve and having irrigation demand to obtain the total irrigation volume required to be provided by the valve.

[0091] The nominal flow rate of the irrigation pipe network to which the valve belongs and the irrigation efficiency, which is a predefined empirical value between 0 and 1, are used to represent the water loss from the valve outlet to the plant root zone due to evaporation and drift. The product of the nominal flow rate and the irrigation efficiency is used as the analytical result of the effective water delivery capacity of the valve per unit time.

[0092] Based on the ratio of the total irrigation volume to the unit time effective water delivery capacity, determine the theoretical opening duration of the valve.

[0093] Referring to Figure 3 As shown, in a preferred embodiment of the present application, the process of calculating the optimal pitch angle and horizontal deflection angle includes: dividing the plant root distribution area of the planning irrigation unit into a plurality of continuous polygonal areas, and synchronously obtaining the installation position coordinates of the corresponding adjustable nozzle and the range-angle relationship function.

[0094] Specifically, the above-mentioned division operation for the polygonal area aims to effectively improve the spatial matching calculation precision of the nozzle wetting range and the actual water demand area of the plant, thereby ultimately improving the targeting and utilization rate of irrigation water.

[0095] The above-mentioned range-angle relationship function establishes a mathematical relationship between the nozzle operating parameters and the wetting range, and as a specific example, can be represented as: .

[0096] represents the jet radius under current working conditions, is the jet radius under the reference working conditions, represents the current nozzle working pressure, represents the current pitch angle, represents the current horizontal deflection angle, respectively represent the rated nozzle working pressure, the reference pitch angle, and the reference horizontal deflection angle, all represent the equipment characteristic coefficients determined by experiments, which are dimensionless constants used to adjust the formula to adapt to the characteristics of specific nozzles, and respectively reflect the sensitivity of pressure, pitch angle, and horizontal deflection angle to the range.

[0097] is the power-law relationship term of pressure and range, which describes the nonlinear relationship between nozzle working pressure and range. When the pressure increases, the range usually increases, but the change rate is controlled by the exponential , which is established based on the similarity criterion in fluid mechanics, which shows that in turbulent flow or jet flow, pressure and flow rate often have a power-law relationship, and in turn, the range also has a power-law relationship.

[0098] is the pitch angle influence term, which reflects the physical law that the trajectory of the jet flow is affected by the launch angle. The use of the sine function emphasizes the importance of the angle to the trajectory of the projectile, which is mainly based on the projectile motion theory, which indicates that under ideal conditions, the range is proportional to the sine value of the launch angle. However, in reality, due to factors such as water flow breaking and air resistance, the relationship may be nonlinear, so the exponential is introduced to ensure that the formula can accurately predict the range under different pitch angles through experimental correction, and is suitable for adjustable-angle nozzles or inclined installation scenarios.

[0099] is the horizontal deflection angle influence term, which indicates that when the nozzle deviates from the reference horizontal direction, the range will linearly decrease, which is derived from experimental observations of the water distribution pattern of rotating nozzles. In rotating nozzles, horizontal deflection may cause water flow distribution asymmetry or range loss.

[0100] According to this example formula, a comprehensive mathematical model is established for the range of the nozzle, which relates the key working parameters to the range. In other embodiments, the implementer can select or construct different function forms according to the working principle, structural characteristics of the nozzle, and the type and accuracy of available data, which will not be described in detail.

[0101] Initialize the value space and iteration step of the pitch angle and horizontal deflection angle of the nozzle, and set the convergence criterion of maximizing the overlap between the wetting range and the water demand area.

[0102] Within the value space, based on the current angle combination and the range-angle relationship function, the actual wetting polygon of the nozzle is simulated, and the intersection area of the polygon and the plant root distribution area is calculated.

[0103] According to the change of the intersection area, iterative optimization is performed: if increasing the pitch angle leads to an increase in the intersection area, continue to adjust the pitch angle in this direction, and adjust the horizontal deflection angle in the same way, until the convergence criterion or the upper limit of the number of iterations is reached.

[0104] The final optimized pitch angle and horizontal deflection angle are combined and output to the nozzle driving device.

[0105] In a preferred embodiment of the present application, the optimization process is terminated when the upper limit of the number of iterations is reached, and a multi-nozzle coordinated irrigation mechanism is started, which includes: the plant root distribution polygon of the planned irrigation unit is automatically divided into two or more sub-irrigation areas according to its geometric shape and the layout of the adjacent nozzles.

[0106] For each of the sub-irrigation areas, one or more adjacent nozzles that can achieve effective coverage are re-assigned.

[0107] Based on the reassignment results, a coordinated irrigation instruction sequence is generated, which includes the start sequence of the nozzles, the respective theoretical opening time, and the optimal pitch angle and horizontal deflection angle.

[0108] The embodiment of the present application realizes accurate spatial mapping from the plant water demand geographic coordinate boundary to the nozzle angle parameters. First, the geographic coordinate boundary of each planned irrigation unit is superimposed on the electronic map to form a spatial aggregation area, and spatial relationship calculation is performed based on the effective coverage range of the nozzle to determine the valve and nozzle number that need to be started. Then, the maximum overlap of the nozzle coverage range and the plant root distribution area of the corresponding planned irrigation unit is taken as the target, and the optimal pitch angle and horizontal deflection angle are calculated for each nozzle that needs to be started. The final optimized angle combination is output to the nozzle driving device to ensure that the delivery range of water resources is highly consistent with the plant root distribution area, and the irrigation deviation problem caused by the lack of spatial mapping mechanism in the prior art is fundamentally overcome.

[0109] The irrigation execution module executes the control instruction set and performs adaptive optimization on the accurate water demand model according to the feedback data after irrigation.

[0110] In a preferred embodiment of the present application, adaptive optimization of the accurate water demand model includes: after the irrigation work is completed and a preset water infiltration equilibrium duration has elapsed, the soil volume water content data before and after irrigation of the target area is obtained, and the actual increment volume is calculated.

[0111] The volume efficiency ratio of the current irrigation is calculated by comparing the theoretical volume of the expected soil moisture increase with the actual volume of the soil moisture increase.

[0112] The reciprocal of the volume efficiency ratio is used as a model calibration factor for correcting the theoretical water requirement in the subsequent irrigation cycle.

[0113] In the subsequent irrigation calculation, the calculated theoretical water requirement is multiplied by the model calibration factor to output a calibrated water requirement for generating control instructions.

[0114] Specifically, the adaptive optimization of the above-mentioned precise water requirement model regards each irrigation as a learning opportunity, effectively compensates for the water estimation deviation caused by soil spatial variability, equipment performance fluctuation or model initial error, thereby significantly improving the long-term precision and water resource utilization efficiency of irrigation, and enabling the system to intelligently adapt to complex field conditions.

[0115] The above formulas are dimensionless numerical calculations, and the formulas are obtained by software simulation of a large amount of data to reflect the current real situation. The preset parameters in the formula are set by a person skilled in the art according to the actual situation.

[0116] The above embodiments can be realized wholly or partially by software, hardware, firmware or any combination thereof. When realized by software, the above embodiments can be realized wholly or partially in the form of a computer program product.

[0117] Those skilled in the art can realize that the modules and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized by hardware or software depends on the specific application and design constraints of the technical solution. A person skilled in the art can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0118] In addition, the functional modules in each embodiment of the present application can be integrated in one processing module, or each module can exist physically alone, or two or more modules can be integrated in one module.

[0119] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0120] Finally, the above only is the preferred embodiment of the present application, and is not used to limit the present application, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A sensor-based greening maintenance and irrigation control system, characterized in that, include: The environmental monitoring module collects environmental data affecting plant evapotranspiration in real time, including at least meteorological station data and soil moisture data. The water demand analysis module calls the corresponding precise water demand model based on the identity identifier, combines the environmental data collected in the current period, calculates the theoretical water demand of each planned irrigation unit, and introduces a visual correction signal to adjust the theoretical water demand. The irrigation decision module converts the adjusted theoretical water demand and its geographical coordinate boundaries of each planned irrigation unit into a set of control instructions for specific irrigation execution equipment. The set of control instructions includes at least the opening and closing time of the target valve and the nozzle angle parameters. The irrigation execution module executes the control instruction set and adaptively optimizes the precise water demand model based on feedback data after irrigation. The information repository contains the identification of several planned irrigation units within the green area, their corresponding precise water demand models, and their geographical coordinate boundaries on the electronic map. Based on the pre-set crop coefficient curves of different plant types, the specific crop coefficient corresponding to the current phenological stage of the plant is matched for the planned irrigation unit; the reference crop evapotranspiration of the planned irrigation unit is calculated based on the meteorological station data collected in the current period; the soil volumetric water content change sequence of each monitoring point in the soil moisture data of the current period is extracted, and combined with the critical water content of plant stress in the planned irrigation unit, the soil water stress coefficient of the planned irrigation unit is dynamically calculated; the cumulative calculation results of the specific crop coefficient, the soil water stress coefficient, and the reference crop evapotranspiration are used as the theoretical water requirement of the planned irrigation unit. Define a spatial graph structure for the planned irrigation unit, where monitoring points are nodes, and weighted edges are constructed between nodes based on spatial Euclidean distance and soil water conductivity. Input the soil volumetric moisture content change sequence of each monitoring point obtained in the current period into the spatial graph structure. Through the spatial transmission of soil moisture in the graph structure, output the predicted soil volumetric moisture content and predicted change slope of each monitoring point after a specified time window. Compare the predicted soil volumetric moisture content with the critical moisture content of plant stress in the planned irrigation unit. If the predicted value is not lower than the critical value, the negative correlation mapping result of the predicted change slope is used as the soil moisture stress coefficient of the monitoring point; otherwise, the highest stress coefficient is directly assigned. Based on the weight of the edge connected to each monitoring point in the spatial graph structure, its representative weight is determined. Using the aforementioned representative weights, the soil moisture stress coefficients of all monitoring points within the planned irrigation unit are weighted and fused to output the soil moisture stress coefficient of the planned irrigation unit.

2. The sensor-based greening maintenance and irrigation control system according to claim 1, characterized in that, The theoretical water requirement is adjusted by introducing a visual correction signal, including: Digital images of the plant canopy are collected regularly by cameras deployed in green areas; The digital images are analyzed to calculate the normalized vegetation index and leaf color saturation. If the normalized vegetation index is below the health threshold or the leaves show signs of wilting, a visual correction signal is generated. By combining the biomass decline trend represented by the normalized vegetation index with the severity of wilting indicators, a visual correction factor is obtained to adjust the theoretical water requirement upward.

3. The sensor-based greening maintenance and irrigation control system according to claim 1, characterized in that, The control instruction set conversion process for the specific irrigation execution equipment includes: Mark the adjusted theoretical water demand as the actual water demand; Planned irrigation units whose actual water demand reaches the irrigation start-up standard value are marked as having irrigation needs; The geographical coordinate boundaries of all planned irrigation units with irrigation needs are overlaid on the electronic map to form a spatial aggregation area; Based on the effective coverage of each sprinkler head in the spatial aggregation area and green area execution unit, the spatial relationship is calculated to determine the valves and sprinkler head numbers that need to be activated; Based on the actual water demand of each planned irrigation unit with irrigation needs, the rated flow rate of the irrigation network to which it belongs, and the irrigation efficiency, calculate the theoretical opening time of each valve that needs to be activated, and plan the opening and closing time accordingly. With the goal of maximizing the overlap between the sprinkler coverage area and the plant root distribution area of ​​the corresponding planned irrigation unit, the optimal pitch angle and horizontal deflection angle are calculated for each sprinkler that needs to be activated.

4. The sensor-based greening maintenance and irrigation control system according to claim 3, characterized in that, The process for determining the valve and nozzle numbers that need to be activated includes: The effective coverage area of ​​each nozzle is modeled as a polygonal region centered on the installation location and with the rated range as the radius; Calculate the intersection-to-union ratio of the effective coverage area of ​​each nozzle with the geometric boundary of the spatial aggregation region; Based on the intersection-union ratio, all nozzles that have non-empty intersections with the spatial aggregation region are arranged in descending order; Starting from the first nozzle in the list, select nozzles sequentially until the union of the effective coverage areas of the selected nozzles can completely cover the spatial aggregation area. Then, identify the selected nozzles as the nozzles that need to be activated and record their numbers. Based on the preset mapping table of nozzle and valve control relationships, determine and output the numbers of all valves that need to be linked.

5. A sensor-based greening maintenance and irrigation control system according to claim 3, characterized in that, The theoretical start-up duration calculation process includes: The total irrigation volume required by the valve is obtained by summing the actual water demand of the planned irrigation units associated with the valve that have irrigation needs; Based on the rated flow rate and irrigation efficiency of the irrigation network to which the valve belongs, the effective water delivery capacity of the valve per unit time can be analyzed. Based on the calculation result of the ratio of the total irrigation volume to the effective water delivery capacity per unit time, the theoretical opening time of the valve is determined.

6. A sensor-based greening maintenance and irrigation control system according to claim 3, characterized in that, The calculation process for the optimal pitch angle and yaw angle includes: The plant root distribution area of ​​the planned irrigation unit is divided into several continuous polygonal areas, and the installation position coordinates and range-angle relationship function of the corresponding adjustable sprinkler head are obtained simultaneously. Initialize the value space and iteration step size of the pitch angle and horizontal deflection angle of the nozzle, and set the convergence criterion with the goal of maximizing the overlap between the wetting range and the water demand area. Within the value space, based on the current angle combination and the range-angle relationship function, the actual wetting polygon of the nozzle is simulated, and the intersection area of ​​the polygon and the plant root distribution area is calculated. Based on the change in the intersection area, perform iterative optimization: if increasing the pitch angle leads to an increase in the intersection area, continue to adjust the pitch angle in this direction, and similarly adjust the horizontal deflection angle until the convergence criterion or the upper limit of the number of iterations is reached. The final optimized values ​​of the pitch angle and horizontal deflection angle are combined and output to the nozzle drive unit.

7. A sensor-based greening maintenance and irrigation control system according to claim 6, characterized in that, If the optimization process terminates due to reaching the maximum number of iterations, a multi-sprinkler coordinated irrigation mechanism will be activated, which includes: The polygon of plant root distribution in the planned irrigation unit is automatically divided into two or more sub-irrigation areas based on its geometry and the layout of adjacent sprinklers. For each of the sub-irrigation zones, one or more adjacent sprinklers that can effectively cover it are reallocated; Based on the redistribution results, a coordinated irrigation command sequence is generated, which includes the sprinkler activation order, their respective theoretical start-up time, and optimal pitch and horizontal deflection angles.

8. A sensor-based greening maintenance and irrigation control system according to claim 1, characterized in that, Adaptive optimization of the precise water demand model includes: After the irrigation operation is completed and the preset water infiltration equilibrium time has elapsed, the soil volumetric moisture content data before and after irrigation in the target area are obtained, and the actual increase in soil moisture volume is calculated. The volumetric efficiency ratio of this irrigation is calculated by comparing the theoretical water demand with the actual water increase. The reciprocal of the volumetric efficiency ratio is used as a model calibration factor for correcting the theoretical water demand in subsequent irrigation cycles. In subsequent irrigation calculations, the calculated theoretical water demand is multiplied by the model calibration factor, and the output is used as the calibration water demand for generating control commands.

Images