Drip irrigation pipe network partition irrigation control method and system based on multi-objective optimization

Abstract

The application relates to a drip irrigation pipe network partition irrigation control method and system based on multi-objective optimization and belongs to the technical field of artificial intelligence. The method comprises the following steps: collecting multi-source heterogeneous data and sampling point spatial coordinates, splicing features and normalized coordinates to form a joint feature vector after abnormal value elimination and normalization processing, and obtaining spatial continuity and feature similar irrigation partitions through K-means clustering; a multi-objective optimization model is constructed with partition irrigation time length and inlet target flow as decision variables; a hybrid strategy multi-objective evolutionary algorithm with chaotic mapping initialization and adaptive hybrid variation is used to obtain a Pareto optimal solution set; finally, optimal irrigation parameters are determined by combining an entropy weight method and a decision maker preference through a good-bad solution distance method, and a real-time soil moisture monitoring feedback correction parameter is introduced. The application can realize accurate partition irrigation of a drip irrigation pipe network, balance multiple optimization objectives, improve irrigation effect and resource utilization efficiency, and reduce system energy consumption.

Description

Technical Field

[0001] This invention belongs to the field of artificial intelligence technology, specifically relating to a method and system for zoned irrigation control of drip irrigation networks based on multi-objective optimization. Background Technology

[0002] With the increasingly severe global water shortage and the escalating contradiction between agricultural water supply and demand, developing efficient water-saving irrigation technologies has become a strategic choice for ensuring food security and sustainable water resource utilization. Drip irrigation, as an advanced irrigation technology, delivers water and nutrients directly to the vicinity of crop roots through a pipeline system, offering significant advantages such as water conservation, increased yield, and strong adaptability. It has been widely used in arid and semi-arid regions and facility agriculture in my country. However, in the actual operation of drip irrigation systems, due to the spatial variability in soil type, terrain slope, crop variety, and growth stage within the irrigation area, traditional unified irrigation management methods often employ fixed irrigation durations and flow rates. This fails to provide differentiated water supply based on the actual water needs of different regions, leading to problems such as poor irrigation uniformity, severe deep water infiltration, and significant energy waste, seriously restricting the full realization of the water-saving potential of drip irrigation systems.

[0003] Existing technologies suffer from the following drawbacks: Conventional irrigation zoning methods either rely solely on geometric division based on spatial coordinates, leading to significant differences in soil moisture content, crop coefficients, and other characteristics within each zoning area, thus failing to achieve precise irrigation on demand; or they rely solely on clustering based on feature similarity, resulting in spatially fragmented and dispersed zoning areas, with the same color point scattered across different regions, causing difficulties in pipeline layout and chaotic water and fertilizer management. Conventional irrigation optimization models often neglect the coupled impact of pipeline pressure constraints on zoning flow, fail to consider the spatial variability of soil moisture, or optimize only a single objective, failing to achieve a balance between the three conflicting objectives of irrigation uniformity, system energy consumption, and water resource utilization efficiency. Effective trade-offs exist; conventional multi-objective evolutionary algorithms, when solving complex high-dimensional optimization problems, either suffer from insufficient population diversity due to improper initialization, easily getting trapped in local optima, or have a single search strategy that fails to fully explore the global space in the early stages of iteration and finely search favorable regions in the later stages, resulting in low quality of the final solution set and Pareto front deviating from the ideal region; existing irrigation control methods are mostly open-loop control, lacking objective weights when selecting the optimal solution in the Pareto solution set, often relying on subjective experience, and unable to make real-time adjustments based on changes in soil moisture during actual irrigation. When encountering uncertainties such as model errors, weather changes, or sensor noise, irrigation accuracy is difficult to guarantee. Summary of the Invention

[0004] To achieve the above objectives, the present invention employs the following technical solution:

[0005] This invention provides a multi-objective optimization-based method for zoned irrigation control of drip irrigation networks, comprising the following steps:

[0006] S1. Distribute multiple sampling points evenly within the target irrigation area, record the spatial coordinates of each sampling point, and collect multi-source heterogeneous farmland data for each sampling point.

[0007] S2. Perform outlier removal and normalization on multi-source heterogeneous farmland data to obtain normalized features;

[0008] S3. By constructing a joint feature vector and using the K-means clustering method to combine the normalized features with spatial coordinates, the partition label of each sampling point is obtained.

[0009] S4. Construct a multi-objective irrigation optimization model based on zoning characteristics, taking the irrigation duration and inlet target flow of each zone as decision variables, and linking the zone flow and pressure through the pipeline hydraulic model. Define three objective functions: irrigation uniformity, system energy consumption, and water resource utilization efficiency to achieve multi-objective irrigation optimization modeling.

[0010] S5. A hybrid strategy multi-objective evolutionary algorithm is adopted, which obtains the Pareto optimal solution set through chaotic mapping initialization, adaptive hybrid mutation, fast non-dominated sorting and crowding distance selection.

[0011] S6. The superior-inferior solution distance method is combined with the entropy weight method and decision-maker preferences to introduce real-time feedback adjustment and correct irrigation parameters based on actual soil moisture monitoring.

[0012] Furthermore, in step S1, the key features in the multi-source heterogeneous farmland data of each sampling point include soil moisture content, soil saturated hydraulic conductivity, topographic slope, crop coefficient, and reference evapotranspiration.

[0013] Further, in step S2, for each key feature, the mean and standard deviation of all sampling points are calculated. If a feature value at a point exceeds the range of the mean plus or minus three times the standard deviation, it is considered an outlier and replaced with the median of that feature across all points. The features of the data after outlier removal are then linearly mapped to... To eliminate the influence of intervals, for each feature dimension, the minimum and maximum values ​​of the cleaned feature values ​​of all sampling points in that dimension are calculated. Then, the minimum-maximum normalization method is used to perform a linear transformation on the feature value of each sampling point to obtain the normalized feature value, and thus obtain the normalized feature vector of each sampling point; define Indicates the first The sampling point The normalized value of the dimensional feature, dimensionless, with a range of values ​​of . After minimum-maximum normalization, the th The feature vector of each sampling point is denoted as . .

[0014] To achieve spatially continuous and feature-similar irrigation zones, normalized features are combined with spatial coordinates for clustering. Conventional clustering methods only consider feature similarity and ignore spatial adjacency, which can easily lead to fragmented zones or unreasonable boundaries.

[0015] Further, in step S3, the spatial coordinates of each sampling point are normalized to obtain normalized coordinates. The normalized feature vector is then concatenated with the normalized coordinates to form a joint feature vector: Define the first... The joint feature vector of the sampling points is The dimension is 7. , Indicates the first The normalized value of the x-coordinate of each sampling point. Indicates the first The normalized values ​​of the ordinates of each sampling point. This invention obtains spatially continuous and feature-uniform irrigation units by constructing a joint feature vector and employing K-means clustering.

[0016] Further, in step S4, the decision variables for each partition are irrigation duration and target inlet flow rate. The soil moisture state within the partition is described by the average soil moisture content and coefficient of variation. The partition irrigation uniformity is defined as the expected value of the soil moisture coefficient of variation after irrigation, and the overall system uniformity is the weighted average of the areas of each partition. The energy consumption of the drip irrigation system is determined by the power required for the pump to overcome the pipeline resistance and topographic elevation difference. The pressure required at the partition inlet is determined by the minimum working pressure, topographic elevation difference, and head loss along the pipeline. The total energy consumption of the system is calculated based on the total flow rate, pump head, and maximum irrigation duration. The partition water resource utilization efficiency is defined as the ratio of the increased crop evapotranspiration after irrigation to the irrigation water volume, and the overall system water resource utilization efficiency is the weighted average of the areas of each partition. Constraints are set, including flow balance, pressure constraints, irrigation duration constraints, and non-negativity constraints.

[0017] Further, in step S5, the decision variables of each partition are encoded as individuals, and a chaotic sequence is generated using logistic mapping and mapped to the decision space to obtain the initial population. Combining the ideas of differential evolution and particle swarm optimization, for the initial population, two mutation strategies are fused based on a hybrid strategy, and different velocity-position updates are selected according to the adaptive probability to generate an intermediate population. The intermediate population and the parent population are merged to obtain the merged population.

[0018] In the zoned irrigation control of drip irrigation networks, there are three conflicting objectives (uniformity, energy consumption, and water resource efficiency). Non-dominated sorting can find a set of trade-off solutions (Pareto front), and crowding distance ensures that the solutions on the front are evenly distributed, avoiding clustering in a certain area, thus providing decision-makers with multiple choices. Specifically, a fast non-dominated sort is performed on the merged population, calculating the non-dominated level and crowding distance of each individual to provide a basis for selection. The top individuals are selected to form the next generation population in order of non-dominated level from low to high and crowding distance within the same level from large to small. After iteration, all non-dominated solutions are merged and deduplicated to obtain the Pareto optimal solution set.

[0019] Furthermore, in step S6, for each solution in the Pareto optimal solution set, its three objective function values ​​are standardized, entropy weights are calculated to determine objective weights, and comprehensive weights are obtained by combining them with decision-maker preferences; the weighted Euclidean distance from each solution to the ideal solution is calculated, and the solution with the highest relative closeness is selected as the final decision solution. The final decision solution Includes optimal irrigation parameters , Indicates the first Optimal ingress target traffic for each partition. Indicates the first The optimal irrigation duration for each zone is determined; the irrigation parameters corresponding to the final decision solution are converted into control commands for each zone, and feedback corrections are made based on real-time soil moisture monitoring during the actual irrigation process.

[0020] This invention also provides a multi-objective optimization-based zoned irrigation control system for drip irrigation networks, which executes the above-described multi-objective optimization-based zoned irrigation control method for drip irrigation networks, including:

[0021] Data acquisition module: used to collect multi-source heterogeneous farmland data;

[0022] Data preprocessing module: used to remove outliers and normalize multi-source heterogeneous farmland data to obtain normalized features;

[0023] Sampling point partitioning module: This module is used to construct a joint feature vector and use the K-means clustering method to combine normalized features with spatial coordinates to perform clustering, thereby obtaining the partitioning label for each sampling point;

[0024] Multi-objective irrigation optimization model construction module: used to construct a multi-objective irrigation optimization model based on zoning characteristics. The irrigation duration and inlet target flow rate of each zone are used as decision variables. The flow rate and pressure of each zone are associated through the pipeline hydraulic model. Three objective functions are defined: irrigation uniformity, system energy consumption and water resource utilization efficiency, so as to realize the modeling of multi-objective irrigation optimization.

[0025] The optimal solution calculation module is used to obtain the Pareto optimal solution set by employing a hybrid strategy multi-objective evolutionary algorithm through chaotic mapping initialization, adaptive hybrid mutation, fast non-dominated sorting, and crowding distance selection.

[0026] Irrigation parameter correction module: This module uses a combination of superior and inferior solution distance method, entropy weight method, and decision-maker preferences to introduce real-time feedback adjustments and correct irrigation parameters based on actual soil moisture monitoring.

[0027] The advantages of this invention are:

[0028] This invention combines agronomic features such as soil properties and crop parameters with geographic coordinates to form a joint feature vector for clustering. This ensures that the divided irrigation units maintain a continuous block structure in space while guaranteeing high similarity of features within each unit, thus resolving the contradiction of traditional partitioning methods that result in either spatial fragmentation or uneven feature distribution. Furthermore, it constructs a multi-objective optimization model with the target flow rate at the partition inlet and irrigation duration as decision variables. This model simultaneously considers three conflicting objectives: irrigation uniformity, system energy consumption, and water resource utilization efficiency. It also introduces hydraulic constraints on the pipeline network, flow balance constraints, and irrigation duration constraints, making the optimization results more aligned with practical engineering applications. A multi-objective evolutionary algorithm employing an adaptive hybrid mutation strategy ensures population diversity through chaotic mapping initialization, dynamically adjusts the differential evolution mutation time based on population diversity, and adaptively switches the differential evolution and particle swarm mutation probabilities according to the iteration process, achieving a dynamic balance between global exploration and local development. A closed-loop control architecture combining offline optimization and online feedback is adopted, selecting the optimal solution from the Pareto solution set through a combination of the superior-inferior solution distance method, entropy weight method, and decision-maker preferences. Irrigation duration and flow rate are dynamically adjusted based on real-time soil moisture monitoring, while simultaneously verifying pipeline pressure constraints, effectively addressing uncertainties in actual irrigation. Attached Figure Description

[0029] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used together with the embodiments of the invention to explain the invention and do not constitute a limitation thereof.

[0030] Figure 1 This is a flowchart of the steps of the method of the present invention;

[0031] Figure 2 The irrigation zoning effect of the feature clustering method;

[0032] Figure 3 The irrigation zoning effect of spatial coordinate clustering method;

[0033] Figure 4 This demonstrates the irrigation zoning effect of the combined clustering method of this invention.

[0034] Figure 5This paper compares the performance of the hybrid strategy multi-objective evolutionary algorithm of the present invention with two conventional multi-objective algorithms in solving irrigation optimization problems.

[0035] Figure 6 Box plots comparing irrigation uniformity for three irrigation control methods;

[0036] Figure 7 A box plot comparison of system energy consumption for three irrigation control methods;

[0037] Figure 8 Box plots comparing the water resource utilization efficiency of three irrigation control methods;

[0038] Figure 9 To provide real-time feedback on the impact of adjustments on irrigation accuracy. Detailed Implementation

[0039] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0040] Example 1

[0041] In this embodiment, as Figure 1 As shown, this invention provides a method for zoned irrigation control of drip irrigation networks based on multi-objective optimization, the specific steps of which include:

[0042] S1, Multi-source heterogeneous farmland data collection

[0043] To achieve precise control of zoned irrigation in drip irrigation networks, it is first necessary to collect multi-source heterogeneous farmland data covering the entire irrigation area. In one embodiment, the present invention evenly distributes 100 representative sampling points in the target irrigation area, and records the spatial geographical coordinates of each sampling point. The horizontal and vertical coordinate values ​​are obtained by measuring with high-precision GPS equipment to ensure the accuracy of spatial location.

[0044] For soil properties, soil moisture sensors were used to monitor soil moisture content in real time at each sampling point. Simultaneously, soil saturated hydraulic conductivity was determined through ring sampling and indoor infiltration tests. These parameters reflect the soil's water-holding capacity and water movement characteristics. Topographic slope data was extracted using UAV aerial photography or digital elevation models to obtain the slope percentage at each sampling point, characterizing the impact of surface undulation on irrigation uniformity. Crop coefficients were assigned based on the varieties and growth stages of the main crops in the irrigation area, referencing the FAO-56 manual or standard values ​​provided by local agricultural extension departments to ensure the reliability of crop water requirement estimation. Additionally, root zone depth was determined by consulting agricultural technical manuals based on crop type; this parameter is used to calculate the water storage capacity of the root zone. Reference evapotranspiration data was obtained from daily meteorological data at the nearest weather station to the irrigation area, including temperature, humidity, wind speed, and sunshine duration, and calculated using the Penman-Montis formula to reflect atmospheric evaporation capacity. In addition, to describe the soil moisture deficit limit, it is necessary to collect typical soil samples from the irrigation area for texture analysis and to determine the field water holding capacity and wilting coefficient. These two parameters are used to determine irrigation targets in the future.

[0045] Basic data of the pipeline system were collected, including the pipeline layout, pipe diameter, pipe length, sprinkler model and its minimum and maximum working pressure, and pump model and its efficiency curve for each zone. This data was obtained by consulting engineering design drawings and product manuals. Based on the pipe material and hydraulic characteristics, the irrigation water utilization coefficient was estimated, and the maximum total flow rate that the system could provide was determined according to the pump performance curve, serving as a constraint for subsequent optimization. Topographic elevation information was obtained through GIS analysis to obtain the elevation difference between the highest point and the water source point in each zone.

[0046] To facilitate subsequent feedback and adjustments, several soil moisture sensors are deployed in each zone to monitor changes in soil moisture content in real time during irrigation and at the end of the planned irrigation period, so as to compare with the actual target value and perform corrections.

[0047] S2, Multi-source heterogeneous farmland data preprocessing

[0048] Optimizing farmland irrigation requires collecting multiple key parameters, but the raw data often contains outliers and dimensional differences, directly affecting the accuracy of subsequent analysis. This invention obtains normalized features through outlier removal and normalization. The specific steps are as follows:

[0049] 1) Outlier removal

[0050] Five key characteristics were collected for each sampling point: soil moisture content (unit: ), soil saturated hydraulic conductivity (unit: ), terrain slope (unit: ), crop coefficient (dimensionless) and reference evapotranspiration (unit: ), outliers were removed using statistical methods;

[0051] Specifically, for each key feature, the mean and standard deviation of all sampling points are calculated. If a feature value at a point exceeds the range of the mean plus or minus three times the standard deviation, it is considered an outlier and replaced with the median of that feature across all points, as shown below:

[0052] ,

[0053] In the formula, Indicates the first The sampling point The original acquired values ​​of the dimensional features; This is the sampling point index, with a value range of [value range missing]. ; This represents the total number of sampling points, which is set to 100 here. This is the feature dimension index, with a value range of [value range missing]. These correspond to soil moisture content, soil saturated hydraulic conductivity, topographic slope, crop coefficient, and reference evapotranspiration, respectively. Indicates the first The arithmetic mean of the original values ​​of all sampled points of a feature reflects the overall level of that feature. Indicates the first The standard deviation of the original values ​​of all sampled points in the dimension feature characterizes the degree of dispersion of the data; Indicates the first The median of the original values ​​of all sampled points for the dimensional feature is used to replace outliers to maintain the data distribution characteristics; Indicates the first The sampling point The values ​​of the dimensional features after outlier removal retain the distribution characteristics of the original data, but by removing outliers and replacing them with the median, the data becomes more robust and the impact of extreme values ​​on subsequent analysis is reduced.

[0054] 2) Minimum-maximum normalization

[0055] Linearly map each feature of the data after outlier removal to... The interval is used to eliminate the influence of dimensions. Specifically, for each feature dimension, the minimum and maximum values ​​of the feature values ​​after cleaning are calculated for all sampling points of that dimension. Then, the minimum and maximum value normalization method is used to perform a linear transformation on the value of that dimension of each sampling point to obtain the normalized value.

[0056] definition Indicates the first The sampling point The normalized value of the dimensional feature, dimensionless, with a range of values ​​of . After minimum-maximum normalization, the th The feature vector of each sampling point is denoted as . The feature matrix of all sampling points after normalization is , dimension .

[0057] S3. Irrigation unit partitioning based on feature-space joint clustering

[0058] To achieve spatially continuous and feature-similar irrigation zones, normalized features are combined with spatial coordinates for clustering. Conventional clustering methods only consider feature similarity and ignore spatial adjacency, which can easily lead to fragmented zones or unreasonable boundaries. This invention constructs a joint feature vector and uses K-means clustering to obtain spatially continuous and feature-uniform irrigation units, represented as:

[0059] 1) Constructing joint feature vectors

[0060] For each sampling point, its spatial coordinates need to be normalized to be consistent with the feature dimensions. Then, the normalized feature vector is concatenated with the normalized coordinates to form a joint feature vector.

[0061] Definition of the first The joint feature vector of the sampling points is It has 7 dimensions and integrates soil properties, crop parameters, and geographic location information, namely... ;

[0062] in, Indicates the first The normalized values ​​of the x-coordinates of each sampling point, dimensionless, with a range of [value missing]. , Indicates the first The normalized values ​​of the ordinates of each sampling point are dimensionless. Both are obtained through minimum-maximum normalization. The coordinate normalization uses the same linear mapping as the feature to ensure that the spatial distance and feature distance are comparable during clustering.

[0063] 2) K-means clustering

[0064] The K-means algorithm is used to cluster the joint feature vectors to obtain the partition label for each sampling point;

[0065] The number of clusters is determined by the elbow rule: calculate the sum of squared intra-cluster errors for different numbers of clusters, and select the number of clusters corresponding to the inflection point where the rate of decrease slows down significantly.

[0066] The K-means algorithm randomly initializes cluster centers and iteratively updates them until convergence. Finally, each point is assigned to the nearest cluster center, represented as:

[0067] ,

[0068] In the formula, Indicates the first The partition label of each sampling point, with a value of arrive An integer between [a certain value] and [a certain value] identifies the irrigation unit to which the point belongs; The number of clusters, i.e., the total number of irrigation zones, is determined by the elbow rule; The index representing the cluster center is equivalent to the irrigation partition index, and its value range is... ; Indicates the first The cluster center vector, with dimension 7, is obtained through iterative optimization using the K-means algorithm, representing the _th _i_ cluster center vector. The characteristics and spatial location center of each partition; This represents the L2 norm, also known as the Euclidean norm.

[0069] It should be noted that the vector composed of the partition labels of all sampling points , dimension This is used to identify the irrigation zone to which each sampling point belongs, through... It can obtain the set of sampling points contained in each partition.

[0070] In one embodiment, the irrigation zoning effect based on feature-spatial joint clustering is compared. Specifically, two conventional zoning methods, feature-only clustering and spatial-only clustering, are compared. From 100 selected sampling points, the K-means clustering algorithm is used to divide the irrigation area into six zones. The x-axis represents the x-coordinate (meters), and the y-axis represents the y-coordinate (meters). Each sampling point is marked with a different color according to its zone. Figure 2 As a feature-based clustering method, the visible partitions are spatially fragmented, with the same color points scattered in different areas. Adjacent plots may be assigned to different partitions, which can lead to difficulties in pipeline layout and chaotic water and fertilizer management in actual irrigation. Figure 3 Based on spatial coordinate clustering, the partitions are presented as continuous geometric blocks, but the soil moisture content, crop coefficient and other characteristics within each partition are quite different, making it impossible to achieve precise irrigation on demand; Figure 4 The joint clustering method of this invention maintains a continuous block structure in space and makes the features within each partition highly similar (the colored points in the figure are concentrated and the boundaries are relatively smooth), laying a scientific foundation for subsequent partition-based differentiated irrigation.

[0071] S4. Construction of a multi-objective irrigation optimization model based on zoning characteristics

[0072] Conventional irrigation optimization models neglect the coupling effect of pipeline pressure constraints on zonal flow and do not consider spatial variability of soil moisture. This invention constructs a multi-objective irrigation optimization model based on zonal characteristics, using irrigation duration and inlet target flow for each zonal region as decision variables. A pipeline hydraulic model is used to correlate zonal flow and pressure, defining three objective functions: irrigation uniformity, system energy consumption, and water resource utilization efficiency. This achieves multi-objective irrigation optimization modeling, expressed as:

[0073] 1) Define the association between decision variables and partition parameters

[0074] The decision variables for each partition are irrigation duration and target inlet flow rate. These decision variables are those that need to be determined during the optimization process. The soil moisture state within each partition is described by the average soil moisture content and the coefficient of variation, expressed as follows:

[0075] ,

[0076] ,

[0077] In the formula, Indicates the first The average soil moisture content of all sampling points within each zone, in units of This reflects the average soil moisture level in that region. Indicates the first The coefficient of variation of soil moisture content within each zone, dimensionless, characterizes the degree of spatial variation of soil moisture within the zone. Indicates the first The set of sampling points contained in each partition is obtained from the partition label, i.e. , Indicates the first The number of sampling points within each partition; Indicates the first The original soil moisture content at each sampling point, in units of .

[0078] At the same time, global soil parameters are defined, including field water holding capacity. (Unit is) ) and wilting coefficient (Unit is) ), obtained from soil texture determination.

[0079] 2) Objective function for irrigation uniformity

[0080] The uniformity of irrigation in each zone is defined as the expected value of the coefficient of variation of soil moisture after irrigation, and the overall uniformity of the system is defined as the weighted average of the areas of each zone, expressed as:

[0081] ,

[0082] In the formula, It represents the overall irrigation uniformity of the system, is dimensionless, and the smaller the value, the more uniform the spatial distribution of soil moisture after irrigation. It is the area-weighted average of the irrigation uniformity of each zone. Indicates the first The area of ​​each partition, in units of It is calculated from the partition boundary; Indicates the first The area of ​​each partition, in units of It is calculated from the partition boundary; Indicates difference from The index of the cluster centers is equivalent to the irrigation partition index;

[0083] Indicates the first Irrigation uniformity of each zone measures the deviation of the soil moisture content after irrigation from the target average moisture content within that zone. It is dimensionless and calculated as follows: ;

[0084] Indicates the first The target average soil moisture content for each zone, in units of The value is That is, 90% of field capacity, which is the expected soil moisture level after irrigation; Indicates the first The ingress target traffic for each partition, in units of , is a decision variable; Indicates the first Irrigation duration for each zone, in units of , is a decision variable; Indicates the first The irrigation water utilization coefficient for each zone is dimensionless and reflects the proportion of water loss during irrigation (such as evaporation and seepage). It can be calculated by simulating losses during pipeline water transport or by setting a default value based on experience. - Values ​​within the range; Indicates the root layer depth, in units of It depends on the crop type; for example, wheat is preferable. Corn is acceptable. For example, you can consult an agricultural manual or preset typical values ​​according to the crop variety.

[0085] It should be noted that, in terms of irrigation uniformity During the calculation process, The term is an estimate of the soil moisture content at that point after irrigation (assuming that the water is evenly distributed within the zone and considering the root layer depth). The sum of the squares after subtracting the target average moisture content, and then the square root divided by the target value, yields the relative standard deviation (coefficient of variation), which reflects the uniformity of water distribution after irrigation. The smaller the value, the more uniform the distribution.

[0086] 3) System energy consumption objective function

[0087] The energy consumption of a drip irrigation system is determined by the power required for the pump to overcome pipe network resistance and terrain elevation differences. The required pressure at the inlet of each zone is determined by the minimum operating pressure, terrain elevation differences, and head loss along the pipeline. Therefore, the total energy consumption of the system is calculated based on the total flow rate, pump head, and maximum irrigation duration, and is expressed as follows:

[0088] ,

[0089] ,

[0090] In the formula, This represents the total energy consumption of the system, in units of... This represents the electrical energy consumed throughout the entire irrigation process; The density of water is a physical constant, and here it is taken as [value missing]. ; This represents gravitational acceleration, a physical constant, and here it is taken as [value missing]. ; This represents the total system traffic, in units of... The calculation method is expressed as This characterizes the total flow demand when all zones are irrigated simultaneously, and is used to calculate the total power and energy consumption of the water pumps. Indicates the required pump head, in units of... Take the maximum value after all partitions are converted; the conversion relationship is as follows: The water column ensures that the water pump can provide sufficient head to meet the pressure requirements of the most unfavorable zone. This represents the efficiency of a water pump; it is dimensionless and determined by the pump model. A value of [missing value] can be used. As a typical value; This represents the maximum irrigation duration for all zones, in units of... This determines the pump's operating time;

[0091] Indicates the first The pressure required for each partition entry point, in units of This is used to ensure that the water emitters in the zone can function properly; This indicates the minimum working pressure of the irrigation device, in units of... The model of the water dispenser determines the type of water dispenser used. For example, take... ; Indicates the first The elevation difference between the highest point in each zone and the water source, in units of... It is obtained from terrain data, which can be obtained through GIS or on-site measurements; Indicates the first The head loss along the route for each zone, in units of The friction loss, representing the energy loss of water flowing through a pipe, is calculated using the Darcy-Weisbach formula, which is the standard method for calculating friction loss in fluid mechanics. ;

[0092] This is the friction factor, dimensionless, and depends on the pipe material and flow conditions; an empirical value can be used. (For smooth pipes), or calculate based on the Reynolds number; For the first The pipe length of each zone, in units of The location is determined by the pipeline network layout and can be obtained from design drawings or measurements. Pipe diameter, unit: Determined by the pipeline network design, for example, taking ; Flow rate, unit: That is, the flow rate divided by the cross-sectional area of ​​the pipe, expressed as .

[0093] It should be noted that in the total energy consumption of the computing system hour, The item is the power of the water pump (unit: ), divided by Convert to Multiply by the running time The total energy consumption is obtained because the water pump needs to overcome the resistance of the pipeline network to provide the head. The total flow rate determines the operating point of the water pump, the head is taken as the maximum value required to ensure that all zones can work, and the running time is taken as the maximum irrigation duration.

[0094] 4) Objective function for water resource utilization efficiency

[0095] The water resource utilization efficiency of a zone is defined as the ratio of the increase in crop evapotranspiration after irrigation to the amount of irrigation water. The overall water resource utilization efficiency of the system is the weighted average of the areas of each zone, expressed as:

[0096] ,

[0097] ,

[0098] In the formula, It represents the overall water resource utilization efficiency of the system, is dimensionless, and the larger the value, the higher the increase in crop evapotranspiration generated per unit of irrigation water. It is the area-weighted average of the water resource utilization efficiency of each zone, reflecting the economy of water use. Indicates the first Water resource utilization efficiency of each zone, dimensionless, quantifies the increase in crop evapotranspiration that can be brought about by a unit of net irrigation water volume, and characterizes the production efficiency of irrigation water in that zone. The larger the value, the more economical the water use, that is, the more crop evapotranspiration benefits are obtained with less water.

[0099] Indicates the first The average crop coefficient within each zone is dimensionless and determined by crop type and growth stage. It can be preset by referring to the FAO-56 manual or local agricultural data. Indicates the first Average reference evapotranspiration within each zone, in units of It is obtained from meteorological data, such as calculations using the Penman formula or data from weather stations.

[0100] It should be noted that in the process of calculating the water resource utilization efficiency of each zone, The term represents the potential evapotranspiration rate of the crop (in units of...). ), multiplied by the water stress coefficient The actual increase in evapotranspiration (assuming that evapotranspiration decreases proportionally during water deficit) is obtained and then multiplied by the irrigation time. (Unit: days) The total increase in evapotranspiration during the irrigation period (unit: days) ), multiplied by area Obtain the volume (Note: Therefore, multiply by Will Convert to Finally, the increased evaporation volume is obtained, and, The term represents the amount of irrigation water (net irrigation water after considering losses), and the ratio is the increase in evapotranspiration per unit of irrigation water.

[0101] It should also be noted that when calculating the water resource utilization efficiency of each zone, The conversion factor from millimeters to meters is 24, which is then divided to convert days to hours.

[0102] 5) Constraints

[0103] Optimization must satisfy constraints on flow rate, pressure, irrigation duration, and non-negativity to ensure safe system operation and effective decision variables, including:

[0104] a) Flow balancing: ;

[0105] b) Pressure constraint: ,

[0106] in, This indicates the maximum working pressure of the irrigation device, in units of... The model of the water dispenser determines the type of water dispenser used. For example, take... ;

[0107] c) Irrigation duration constraints: ,

[0108] in, This indicates the minimum permissible irrigation duration, in units of... The minimum operating time of the irrigation system or the crop's needs are determined, for example... ;

[0109] This indicates the maximum permissible irrigation duration, in units of... Considering soil infiltration capacity or avoiding deep seepage, for example The specific settings can be determined according to the actual situation;

[0110] d) Nonnegativity constraint: .

[0111] S5. Model Solving Based on Hybrid Strategy Multi-Objective Evolutionary Algorithm

[0112] Conventional multi-objective evolutionary algorithms suffer from problems such as insufficient population diversity and imbalanced search capabilities. This invention employs a hybrid strategy multi-objective evolutionary algorithm, which obtains the Pareto optimal solution set through chaotic mapping initialization, adaptive hybrid mutation, fast non-dominated sorting, and crowding distance selection. The specific steps are as follows:

[0113] 1) Population initialization and chaotic mapping

[0114] The decision variables (inlet target flow and irrigation duration) of each partition are encoded as individuals. A chaotic sequence is generated using logistic mapping and mapped onto the decision space to obtain the initial population, represented as:

[0115] ,

[0116] In the formula, Indicates the first The decision vector of each initial individual, with dimension . It contains the ingress target flow and irrigation duration of all partitions, and is the initial position of an individual in the decision space; For individual indexes, the value range is: ; This represents the population size; an example value is 100.

[0117] Indicates the first Among the individuals, the first The ingress target traffic for each partition is mapped to a chaotic variable. An interval, denoted as ; Indicates the first Among the individuals, the first The irrigation duration for each partition is mapped to a chaotic variable. An interval, denoted as ;

[0118] For the first The individual A chaotic variable of dimension is used to generate the initial population, ensuring that individuals are uniformly distributed in the decision space, thus increasing population diversity. A chaotic sequence is generated through a logistic mapping, exhibiting ergodicity and randomness. and definition for Random numbers within the interval, and chaotic mapping, ensure that the initial population is evenly distributed in the decision space, thereby increasing diversity; To control the parameters, a value of 4 is preferred to ensure chaotic characteristics; The dimension index of the chaotic variable, with a value range of 1. Because each individual has There are 1 decision variables, and each variable corresponds to a chaotic variable.

[0119] 2) Adaptive hybrid mutation operator

[0120] This approach integrates the ideas of differential evolution and particle swarm optimization, employing a hybrid strategy that fuses two mutation strategies. Different velocity-position updates are selected based on adaptive probabilities, thus balancing global exploration and local exploitation capabilities to generate an intermediate population, represented as:

[0121] ,

[0122] In the formula, Indicates the first The generation The mutation vector of each individual, with dimension . , representing a candidate combination of decision variables, will be crossed with the original individual to generate experimental individuals for the construction of the next generation population; This is the index for the number of iterations, and its value range is... ; This represents the maximum number of iterations; an example value is 500. Indicates the first The generation Each individual, i.e., a specific irrigation scheme decision vector, includes the inlet target flow and irrigation duration for all zones; , , For three distinct individuals randomly selected from the current population, the individual index is... Dissimilar and with different; This represents the scaling factor, which is dimensionless and is calculated as follows: When population diversity declines, The ratio of the terms decreases. near Reduce variable time and enhance local search; when diversity is high, near Increase the variable asynchronous length to facilitate global search; This represents the probability of choosing a mutation strategy, is dimensionless, and is calculated as follows: ; This represents the inertial weight, which is dimensionless and controls the degree of particle velocity inheritance. An example value is 0.8. Indicates the first The generation The mutation vector of each individual, initially set to zero; This represents the first learning factor, which controls the degree to which an individual moves toward its historical best; an example value is 2. This represents the second learning factor, which controls the degree to which an individual moves toward the global optimum; an example value is 2. Represents the first random number, which is Uniformly distributed random numbers within an interval; This represents the second random number. Uniformly distributed random numbers within an interval; Indicates the first The historical best position of each individual; This indicates the current global optimal position of the population. Indicates the first Generations of populations Indicates the initial population. Indicates the first The diversity measure of a generation of population is calculated by... The standard deviation of all individuals in the population across each decision variable dimension is calculated, and then the average of these standard deviations is taken. This average is used to measure the dispersion of the population in the decision space. A measure of the diversity of the initial population;

[0123] This represents the hyperbolic tangent function, used to map the input to... Interval.

[0124] Furthermore, the intermediate population was obtained after the mutation. It is a new set of individuals generated through mutation and crossover, used to interact with the parent population. Merge, perform non-dominated sorting and selection to produce the next generation.

[0125] It should be noted that the mutation strategy selection probability During the iteration process, the proportions of the two mutation strategies are dynamically balanced. In the early stages, the probabilities of the two strategies are roughly equal, balancing exploration and development. In the later stages, the probability of differential mutation increases because the population tends to converge at this point, and the local search capability of differential mutation (through...) Adaptive step size reduction helps with fine optimization, while particle swarm mutation uses historical information to guide the search; the two work together to improve algorithm performance.

[0126] 3) Fast non-dominated sorting and crowding distance

[0127] In the zoned irrigation control of drip irrigation networks, there are three conflicting objectives (uniformity, energy consumption, and water resource efficiency). By using non-dominated ordination, a set of trade-off solutions (Pareto front) can be found, and the crowding distance ensures that the solutions on the front are evenly distributed, avoiding clustering in a certain area, thus providing decision-makers with multiple options;

[0128] Specifically, a fast non-dominated sort is performed on the merged population, and the non-dominated rank and crowding distance of each individual are calculated to provide a basis for the selection operation, represented as:

[0129] ,

[0130] In the formula, Indicates the first The crowding distance of an individual is dimensionless and reflects the density around an individual in the same non-dominated layer. The larger the value, the sparser the solution in that region. Index of the objective function, Corresponding to the overall irrigation uniformity of the system Total system energy consumption and the overall water resource utilization efficiency of the system ; and Indicates the first On the first goal, with the second The objective function values ​​of two adjacent individuals; and Indicates the number of units in the current non-dominated layer. The maximum and minimum values ​​of each target.

[0131] In practical implementation, the non-dominant hierarchy This is obtained through a fast non-dominated sorting algorithm. Specifically, it compares the dominance relationships between individuals, groups those not dominated by any other individual into the first layer, removes them, and then groups the remaining non-dominated individuals into the second layer, and so on. Indicates the first The non-dominant hierarchy of an individual, the lower the hierarchy (e.g., ... The higher the level, the better. In the selection operation, individuals with lower levels are given priority. Within the same level, individuals with higher crowding are given priority.

[0132] It should be noted that the fast non-dominated sort is used to stratify individuals based on the three objective function values, grouping non-dominated individuals into the same stratum. The lower the stratum number (the smaller the rank), the better the individual (Pareto optimality). The crowding distance is used to measure the sparsity of individuals within the same stratum. The larger the distance, the sparser the solution in that region. When selecting, individuals with high crowding are preferred to be retained to maintain the diversity of solutions.

[0133] It should also be noted that when calculating the distance to congestion... During the process, and This is achieved by arranging individuals within the same non-dominated layer according to their position. After sorting the nth objective function values, take the nth value and... The objective function values ​​of two adjacent individuals. and It is the first in the current non-dominated layer The maximum and minimum values ​​of each target are obtained directly from the individuals in that layer.

[0134] It should also be noted that in the optimization of drip irrigation network zonal irrigation, the search space of decision variables is huge, and the objective functions (uniformity, energy consumption, water resource efficiency) are conflicting. Adaptive hybrid mutation can dynamically adjust the search step size and strategy according to the current state of the population: when the diversity is high in the early stage, large step size differential mutation helps to quickly explore new areas and avoid getting trapped in local optima; when the diversity decreases in the later stage, small step size particle swarm mutation uses the historical optimal and global optimal information of individuals to finely search for favorable areas and improve the quality of solutions. The adaptive mechanism enables the algorithm to efficiently approach the Pareto front, providing decision-makers with high-quality and diversified irrigation solutions.

[0135] It should also be noted that the distance to congestion The Pareto value measures the sparsity of the solutions around individuals within the same non-dominated layer. A larger value indicates a sparser solution in that area. In drip irrigation optimization, we aim to obtain a set of Pareto solutions that are evenly distributed in terms of uniformity, energy consumption, and water efficiency, allowing decision-makers to choose solutions based on different preferences. Individuals with large crowding distances represent fewer solutions in their respective areas. Prioritizing the retention of these individuals enriches the diversity of the solution set, avoids solutions concentrating near a certain objective extreme, and thus provides more diverse trade-offs, such as some solutions being more energy-efficient and others more uniform.

[0136] 4) Elite Preservation and Population Renewal

[0137] Individuals are selected in ascending order of non-dominance level and descending order of crowding distance within the same level to form the next generation population, denoted as […]. ;

[0138] After the iteration is complete, all non-dominated solutions are merged and duplicates are removed to obtain the Pareto optimal solution set, denoted as: :

[0139] in, Indicates the first The generation population is obtained through selection operations; Represents the parent population (the first generation) The merged set of the first generation population and the intermediate population, i.e. ; Indicates population size; This indicates the selection based on non-dominance level and crowding distance. The operation of each individual; This is the Pareto optimal solution set, which contains all non-dominated solutions. It is the final output multi-objective optimization solution set for decision-makers to choose from. Indicates from the first The non-dominated solution set extracted from the population. The characterization process involves merging all non-dominated solutions generated in the iterations, removing duplicates, and obtaining the final Pareto optimal solution set.

[0140] It should be noted that the elite preservation strategy involves preserving the parent population. and intermediate population merged into Then, in order of non-dominance level from low to high, and within the same level, from largest to smallest crowding distance, select the top... Individuals constitute the next generation population. This ensures that excellent solutions are not lost and accelerates convergence. In drip irrigation optimization, it helps to retain solutions that perform well in terms of uniformity, energy consumption, and water resource efficiency, while maintaining diversity and avoiding getting trapped in local optima.

[0141] S6. Generation and Execution of Optimal Irrigation Parameters Based on Multi-Attribute Decision Making

[0142] Conventional methods lack objective weights and feedback corrections when selecting the optimal solution from the Pareto solution set. This invention employs a method combining the distance between superior and inferior solutions with entropy weighting and decision-maker preferences, and introduces real-time feedback adjustments to correct irrigation parameters based on actual soil moisture monitoring, thus addressing uncertainties. The specific steps are as follows:

[0143] 1) Multi-attribute decision-making for Pareto solutions

[0144] For each solution in the Pareto optimal solution set, its three objective function values ​​are standardized, entropy weights are calculated to determine objective weights, and a comprehensive weight is obtained by combining these with the decision-maker's preferences. Then, the weighted Euclidean distance from each solution to the ideal solution is calculated, and the solution with the highest relative closeness is selected as the final decision, expressed as:

[0145]

[0146] In the formula, The decision solution represents the final irrigation scheme selected from the Pareto optimal solution set, which includes the optimal irrigation parameters. ;

[0147] Indicates the first Optimal ingress target traffic for each partition;

[0148] Indicates the first Optimal irrigation duration for each zone;

[0149] Representing the solution The weighted Euclidean distance to the positive ideal solution is calculated as follows: This is used to measure how close a solution is to the ideal solution; the smaller the distance, the better.

[0150] Representing the solution The weighted Euclidean distance to the negative ideal solution is calculated as follows: The negative ideal solution is a virtual solution where all objectives are at their worst. The larger this distance, the better the solution. The further away from the worst-case scenario, the better;

[0151] Indicates the first The comprehensive weight of each objective, combining objective entropy weight and subjective preference weight, is calculated using a geometric mean to balance the influence of both, avoiding any single weight being too small or too large. This ensures that the final weight reflects both the data's inherent discriminative power and the decision-maker's intent, expressed as follows: ;

[0152] Representing the solution The The standardized values ​​of the targets, ranging from ;

[0153] This represents the subjective preference weights that decision-makers assign to the three objectives (uniformity, energy consumption, and water efficiency) based on actual needs. For example, if energy conservation is given greater emphasis, the energy consumption objective can be assigned a higher weight. It is used to adjust the entropy weight to make the final selected scheme more in line with actual production goals. It is set based on experience, and an example value is given. ;

[0154] Indicates the first The entropy weight of each target is calculated from the information entropy.

[0155] In practical implementation, the ideal solution Defined as a virtual solution where all objectives are 1 after standardization, the negative ideal solution. Defined as virtual solutions where all objectives are 0 after standardization, these serve as reference benchmarks for calculating the closeness.

[0156] In practical implementation, the standardized processing method is as follows: for cost-type objectives ( and Standardized value For benefit-oriented goals ( Standardized value ,in, To solve The The objective function value, To solve The The standardized values ​​of the targets, ranging from , For the Pareto solution set, the first The maximum value of each target. For the Pareto solution set, the first The minimum value of each objective.

[0157] In practical implementation, The calculation method is as follows: First calculate the first... Information entropy of a target Then obtain the entropy weight. Combined with decision-maker preference weights To obtain the comprehensive weight and normalization ,in, This indicates the number of solutions in the Pareto optimal solution set.

[0158] 2) Generation and feedback adjustment of irrigation control commands

[0159] The irrigation parameters corresponding to the optimal solution are converted into control commands for each zone, and feedback corrections are made based on real-time soil moisture monitoring during actual irrigation to ensure that the target moisture content is achieved. This is expressed as:

[0160]

[0161] In the formula, Indicates the first The adjusted inbound target traffic for each partition, in units of... It is used to make corrections based on real-time monitoring during actual irrigation in order to compensate for insufficient irrigation;

[0162] Indicates the first The extended irrigation time required for each zone, in units of The calculation method is expressed as Used to revise the original plan, if If the actual moisture content is lower than the target, then irrigation should be extended. Then stop early, no need to extend;

[0163] This represents the correction factor, which is dimensionless and reflects the difference between the actual moisture content and the target moisture content. Its calculation method is different from that of the Auster system. ;

[0164] Indicates the planned irrigation duration At the end, the The average soil moisture content within each zone is monitored in real time to determine whether irrigation needs to be extended. This data is obtained through real-time monitoring using field sensors.

[0165] In practical implementation, if Then extend the irrigation time. The flow rate was adjusted to maintain a constant total water volume; the adjusted inlet target flow rate was... The pipeline pressure constraint must be met, that is, the corresponding pressure must be calculated. ,in, Indicates the adjusted inbound target traffic. If the pressure required for the corresponding partition entry exceeds... If the boundary value is taken, the adjusted instruction will be executed to achieve differentiated and precise irrigation for different zones.

[0166] It should be noted that if in If the target is reached ahead of schedule, the valve will be closed ahead of schedule.

[0167] It should also be noted that conventional methods lack objective weights and feedback corrections when selecting the optimal solution from the Pareto solution set. This invention adopts the superior-inferior solution distance method combined with the entropy weight method and decision-maker preferences, and introduces real-time feedback adjustments to ensure precise irrigation. The entropy weight method objectively determines the weight of each objective based on the distribution of the solution set itself, avoiding subjective arbitrariness. Combined with the decision-maker preference weights, it can reflect actual needs. The superior-inferior solution distance method selects the comprehensive optimal solution by calculating the closeness to the ideal solution. Real-time feedback adjusts irrigation parameters based on actual soil moisture monitoring to cope with uncertainties and improve irrigation accuracy.

[0168] In one embodiment, such as Figure 5 As shown, a Pareto front comparison of multi-objective optimization algorithms is conducted, specifically comparing the performance of the proposed hybrid strategy multi-objective evolutionary algorithm with two conventional multi-objective algorithms (second-generation non-dominated sorting genetic algorithm and multi-objective particle swarm optimization) in solving irrigation optimization problems. The experiment selected 30 Pareto optimal solutions, each corresponding to a set of irrigation schemes. The three objectives were irrigation uniformity (dimensionless, smaller values ​​indicate greater uniformity), total system energy consumption (kilowatt-hours, smaller values ​​indicate greater energy efficiency), and water resource utilization efficiency (dimensionless, larger values ​​indicate greater efficiency). Blue dots represent the algorithm of this invention, while red triangles and green squares represent the two conventional algorithms, respectively. As can be seen from the figure, the solution set of the algorithm of this invention is distributed closer to the ideal region in three-dimensional space: in the dimension of irrigation uniformity, blue dots are concentrated in the smaller value range (corresponding to greater uniformity); in the dimension of energy consumption, blue dots are concentrated in the lower value range (corresponding to greater energy efficiency); and in the dimension of water resource utilization efficiency, blue dots are concentrated in the higher value range (corresponding to higher efficiency). In contrast, the solution set of the conventional algorithms deviates from the ideal region overall, exhibiting either poor uniformity, excessively high energy consumption, or low efficiency. The solution set of this invention forms a better Pareto front for the three objectives, indicating that the algorithm can better balance the three conflicting objectives and provide decision-makers with a higher quality and more evenly distributed set of solutions.

[0169] S7. Zoned irrigation control of drip irrigation networks based on multi-objective optimization

[0170] Based on the aforementioned multi-source heterogeneous data acquisition, preprocessing, irrigation unit division, multi-objective optimization model construction, hybrid strategy evolutionary algorithm solution, and multi-attribute decision-making, a complete method for zoned irrigation control of drip irrigation networks is formed. First, soil moisture content, saturated hydraulic conductivity, terrain slope, crop coefficient, reference evapotranspiration, and spatial coordinate data from 100 sampling points collected in S1 are preprocessed by outlier removal and normalization in S2 to obtain a standardized feature matrix. Then, in S3, the normalized features and normalized spatial coordinates of each sampling point are concatenated into a 7-dimensional joint feature vector. The optimal number of partitions is determined using a K-means clustering algorithm combined with the elbow rule, thus dividing the irrigation area into several spatially continuous and feature-similar irrigation units. Each unit contains a set of sampling points and their corresponding partition labels. Based on the partitioning results, S4 constructs a multi-objective optimization model with irrigation duration and inlet target flow rate as decision variables. This model comprehensively considers three conflicting objectives: irrigation uniformity, system energy consumption, and water resource utilization efficiency. Network hydraulic constraints, flow balance constraints, and irrigation duration constraints are introduced to form a mathematical optimization problem.

[0171] S5 employs a hybrid strategy multi-objective evolutionary algorithm to solve this problem: it initializes the population through chaotic mapping to ensure diversity, uses an adaptive hybrid mutation operator (integrating differential evolution and particle swarm mutation) to dynamically balance global exploration and local exploitation, combines fast non-dominated sorting and crowding distance for elite selection, and obtains a Pareto optimal solution set after iterative evolution. This solution set contains multiple irrigation schemes with advantages in uniformity, energy consumption, and water efficiency.

[0172] S6 further employs a superior-inferiority distance method combined with entropy weighting and decision-maker preferences to select the overall optimal irrigation scheme from the Pareto solution set, generating the optimal inlet target flow rate and irrigation duration for each zone. During actual execution, the optimal parameters are converted into valve opening commands and irrigation duration settings for each zone, and water pumps are started to supply water according to the zone's flow rate. Simultaneously, soil moisture sensors deployed within each zone monitor changes in soil moisture content in real time during irrigation. If the measured average moisture content does not reach the target value by the end of the planned irrigation duration, a correction factor is calculated based on the deviation, dynamically extending the irrigation duration and adjusting the flow rate to maintain a constant total water volume. The adjusted flow rate is then verified to meet the pipeline pressure constraints, ensuring safe system operation. If the target is reached ahead of schedule, the valves are automatically closed.

[0173] Based on this, a closed-loop control method of "offline optimization + online feedback" is used to achieve zoned and differentiated precision irrigation of the drip irrigation network, effectively improving irrigation uniformity, reducing energy consumption and improving water resource utilization efficiency.

[0174] In one embodiment, box plots were compared between three irrigation control methods on three objectives. Through 20 independent repeated experiments, the performance of the three irrigation control methods—uniform irrigation, conventional zoned irrigation, and the method of the present invention—on three key performance indicators was compared. Figure 6 , Figure 7 , Figure 8 Three box plots are presented side-by-side, corresponding to irrigation uniformity, system energy consumption, and water resource utilization efficiency, respectively. The horizontal axis represents the three methods, and the vertical axis indicates the units. The irrigation uniformity box plot shows that the median and interquartile range of the method presented in this invention are significantly smaller than the other two methods, indicating that its spatial distribution of soil moisture after irrigation is the most uniform and stable. In the system energy consumption box plot, the energy consumption value of the method presented in this invention is generally lower than that of uniform irrigation and conventional zoning, with a significant median advantage and outstanding energy savings. In the water resource utilization efficiency box plot, the method presented in this invention has the highest median, and the box is located in the higher region, indicating that the increase in crop evapotranspiration per unit of irrigation water is the largest, resulting in more economical water use. The three box plots collectively verify that the method presented in this invention achieves superior performance on three conflicting objectives, and the results are statistically stable.

[0175] In one embodiment, such as Figure 9As shown, the impact of real-time feedback adjustment on irrigation accuracy was analyzed. The change in soil moisture content during irrigation was studied in a single zone. The target moisture content was set at 0.25 cubic meters per cubic meter. The horizontal axis represents time (hours), and the vertical axis represents soil moisture content (cubic meters per cubic meter). The blue curve represents conventional irrigation without feedback, where the moisture content is slightly lower than the target value at the end of four hours and then remains constant, failing to achieve the expected result. The red curve represents irrigation with feedback according to this invention. After detecting insufficient moisture content at four hours, the irrigation time is dynamically extended based on the deviation, and the flow rate is adjusted to ensure the final moisture content accurately reaches the target value (green horizontal dashed line). The experiment shows that this invention, through closed-loop control of "offline optimization + online feedback," can effectively cope with uncertainties in actual irrigation and improve irrigation accuracy.

[0176] Example 2

[0177] This embodiment provides a multi-objective optimization-based zoned irrigation control system for drip irrigation networks, executing the multi-objective optimization-based zoned irrigation control method for drip irrigation networks described in Embodiment 1, including:

[0178] Data acquisition module: used to collect multi-source heterogeneous farmland data;

[0179] Data preprocessing module: used to remove outliers and normalize multi-source heterogeneous farmland data to obtain normalized features;

[0180] Sampling point partitioning module: This module is used to construct a joint feature vector and use the K-means clustering method to combine normalized features with spatial coordinates to perform clustering, thereby obtaining the partitioning label for each sampling point;

[0181] Multi-objective irrigation optimization model construction module: used to construct a multi-objective irrigation optimization model based on zoning characteristics. The irrigation duration and inlet target flow rate of each zone are used as decision variables. The flow rate and pressure of each zone are associated through the pipeline hydraulic model. Three objective functions are defined: irrigation uniformity, system energy consumption and water resource utilization efficiency, so as to realize the modeling of multi-objective irrigation optimization.

[0182] The optimal solution calculation module is used to obtain the Pareto optimal solution set by employing a hybrid strategy multi-objective evolutionary algorithm through chaotic mapping initialization, adaptive hybrid mutation, fast non-dominated sorting, and crowding distance selection.

[0183] Irrigation parameter correction module: This module uses a combination of superior and inferior solution distance method, entropy weight method, and decision-maker preferences to introduce real-time feedback adjustments and correct irrigation parameters based on actual soil moisture monitoring.

[0184] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for zoned irrigation control of drip irrigation networks based on multi-objective optimization, characterized in that, Includes the following steps: S1. Distribute multiple sampling points evenly within the target irrigation area, record the spatial coordinates of each sampling point, and collect multi-source heterogeneous farmland data for each sampling point. S2. Perform outlier removal and normalization on multi-source heterogeneous farmland data to obtain normalized features; S3. By constructing a joint feature vector and using the K-means clustering method to combine the normalized features with spatial coordinates, the partition label of each sampling point is obtained. S4. Construct a multi-objective irrigation optimization model based on zoning characteristics, taking the irrigation duration and inlet target flow of each zone as decision variables, and linking the zone flow and pressure through the pipeline hydraulic model. Define three objective functions: irrigation uniformity, system energy consumption, and water resource utilization efficiency to achieve multi-objective irrigation optimization modeling. Specifically: The decision variables for each zone are irrigation duration and target inlet flow rate. Soil moisture status within a zone is described by average soil moisture content and coefficient of variation. Zone irrigation uniformity is defined as the expected value of the soil moisture coefficient of variation after irrigation, and the overall system uniformity is the weighted average of the areas of each zone. The energy consumption of the drip irrigation system is determined by the power required for the pump to overcome pipeline resistance and topographic elevation differences. The required pressure at the zone inlet is determined by the minimum operating pressure, topographic elevation differences, and head loss along the pipeline. The total energy consumption of the system is calculated based on the total flow rate, pump head, and maximum irrigation duration. Zone water resource utilization efficiency is defined as the ratio of increased crop evapotranspiration after irrigation to the amount of irrigation water, and the overall system water resource utilization efficiency is the weighted average of the areas of each zone. Constraints are set, including flow balance, pressure constraints, irrigation duration constraints, and non-negativity constraints. S5. A hybrid strategy multi-objective evolutionary algorithm is adopted, which obtains the Pareto optimal solution set through chaotic mapping initialization, adaptive hybrid mutation, fast non-dominated sorting, and crowding distance selection; the specific process is as follows: Chaotic mapping initialization: Encode the decision variables of each partition as individuals, generate chaotic sequences using logistic mapping, map them to the decision space, and obtain the initial population; Adaptive Hybrid Mutation: For the initial population, the ideas of differential evolution and particle swarm optimization are combined. Based on a hybrid strategy, two mutation strategies are fused, and different velocity-position updates are selected according to adaptive probabilities to obtain an intermediate population; represented as: ， In the formula, Indicates the first The generation The variation vector of each individual; , , These are three distinct individuals randomly selected from the current population. Indicates the scaling factor; Indicates the probability of choosing the mutation strategy; Indicates the first The generation Individual; Indicates the first The generation The variation vector of each individual; Indicates inertia weight; Indicates the first learning factor; Represents the first random number; Indicates the first The historical best position of each individual; Indicates the second learning factor; Indicates the second random number; This indicates the current global optimal position of the population; the intermediate population and the parent population are merged to obtain the merged population; Fast nondominated sorting and crowding distance selection: Perform fast nondominated sorting on the merged population, calculate the nondominated level and crowding distance of each individual; select the first few individuals to form the next generation population in order of nondominated level from low to high and crowding distance within the same level from large to small; after the iteration, merge all nondominated solutions and remove duplicates to obtain the Pareto optimal solution set. S6. The superior-inferior solution distance method, combined with the entropy weight method and decision-maker preferences, is adopted, and real-time feedback adjustments are introduced to correct irrigation parameters based on actual soil moisture monitoring. The specific process is as follows: For each solution in the Pareto optimal solution set, its three objective function values ​​are standardized, entropy weights are calculated to determine objective weights, and comprehensive weights are obtained by combining these with decision-maker preferences. The weighted Euclidean distance from each solution to the ideal solution is calculated, and the solution with the highest relative closeness is selected as the final decision solution. The final decision solution Includes optimal irrigation parameters , Indicates the first Optimal ingress target traffic for each partition. Indicates the first Optimal irrigation duration for each zone; The irrigation parameters corresponding to the final decision solution are converted into control commands for each zone, and feedback corrections are made based on real-time soil moisture monitoring during actual irrigation.

2. The drip irrigation network zoned irrigation control method based on multi-objective optimization according to claim 1, characterized in that, Key features in the multi-source heterogeneous farmland data of each sampling point in S1 include soil moisture content, soil saturated hydraulic conductivity, topographic slope, crop coefficient, and reference evapotranspiration.

3. The drip irrigation network zoned irrigation control method based on multi-objective optimization according to claim 2, characterized in that, S2 specifically refers to: For each key feature, calculate the mean and standard deviation of all sampling points. If a feature value exceeds the range of the mean plus or minus three times the standard deviation, it is considered an outlier and replaced with the median of that feature across all points. Then, linearly map each feature of the data after outlier removal to... To eliminate the influence of intervals, for each feature dimension, the minimum and maximum values ​​of the cleaned feature values ​​of all sampling points in that dimension are calculated. Then, the minimum-maximum normalization method is used to perform a linear transformation on the feature value of each sampling point to obtain the normalized feature value, and thus obtain the normalized feature vector of each sampling point; define Indicates the first The sampling point The normalized value of the dimensional feature, dimensionless, with a range of values ​​of . After minimum-maximum normalization, the th The feature vector of each sampling point is denoted as . .

4. The drip irrigation network zoned irrigation control method based on multi-objective optimization according to claim 1, characterized in that, S3 specifically refers to: Normalize the spatial coordinates of each sampling point to obtain normalized coordinates. Concatenate the normalized feature vector with the normalized coordinates to form a joint feature vector: Define the first... The joint feature vector of the sampling points is The dimension is 7. , Indicates the first The normalized value of the x-coordinate of each sampling point. Indicates the first The normalized value of the ordinate of each sampling point.

5. A multi-objective optimization-based zoned irrigation control system for drip irrigation networks, executing the multi-objective optimization-based zoned irrigation control method for drip irrigation networks as described in claim 1, characterized in that, include: Data acquisition module: used to collect multi-source heterogeneous farmland data; Data preprocessing module: used to remove outliers and normalize multi-source heterogeneous farmland data to obtain normalized features; Sampling point partitioning module: This module is used to construct a joint feature vector and use the K-means clustering method to combine normalized features with spatial coordinates to perform clustering, thereby obtaining the partitioning label for each sampling point; Multi-objective irrigation optimization model construction module: used to construct a multi-objective irrigation optimization model based on zoning characteristics. The irrigation duration and inlet target flow rate of each zone are used as decision variables. The flow rate and pressure of each zone are associated through the pipeline hydraulic model. Three objective functions are defined: irrigation uniformity, system energy consumption and water resource utilization efficiency, so as to realize the modeling of multi-objective irrigation optimization. The optimal solution calculation module is used to obtain the Pareto optimal solution set by employing a hybrid strategy multi-objective evolutionary algorithm through chaotic mapping initialization, adaptive hybrid mutation, fast non-dominated sorting, and crowding distance selection. Irrigation parameter correction module: This module uses a combination of superior and inferior solution distance method, entropy weight method, and decision-maker preferences to introduce real-time feedback adjustments and correct irrigation parameters based on actual soil moisture monitoring.

Images