Irrigation pipe network intelligent scheduling method and system based on hydraulic model

Abstract

The invention discloses an irrigation pipe network intelligent scheduling method and system based on a hydraulic model, and the method can simulate the hydraulic behaviors of a pipe network in different operation scenes through the construction of a hydraulic irrigation simulation model, thereby achieving the precise simulation and prediction of the hydraulic behaviors in the irrigation pipe network. On the basis, an irrigation pipe network intelligent scheduling optimization objective function is established by taking optimal water supply quality as an objective according to the requirements of crop types and growth cycles of a target area for water. The minimum absolute error between the actual irrigation amount and the theoretical water demand is considered, key conditions such as the water supply amount constraint, the head valve working pressure constraint and the pipeline pressure constraint are also fused, and the scientificity and rationality of irrigation scheduling are ensured. Therefore, the irrigation efficiency can be remarkably improved, water resources are saved, healthy growth of crops is promoted, and effective technical support is provided for solving the problems of water resource shortage, poor irrigation management and the like in modern agriculture.

Description

Technical Field

[0001] The present application relates to the field of agricultural irrigation technology, and in particular to an intelligent scheduling method and system for an irrigation network based on a hydraulic model. Background Art

[0002] In modern agriculture, the effective management and utilization of water resources is one of the key factors in improving crop yield and quality. With global climate change and population growth, agricultural production is facing increasingly severe challenges. Water shortage has become one of the main bottlenecks restricting the sustainable development of agriculture. Traditional irrigation methods often rely on experience and fixed irrigation schedules, which makes it difficult to accurately meet the water needs of different crops at different growth stages and large-scale irrigation at the same time, resulting in waste of water resources and uneven crop growth, and making it difficult to plan irrigation water in a unified manner. For example, frequent irrigation may lead to soil salt accumulation, while insufficient irrigation will affect crop growth and yield. Intelligent irrigation scheduling based on hydraulic models can solve the problems of existing technologies and provide an accurate and efficient irrigation water allocation plan to significantly reduce water resource consumption and improve the uniformity and health of crop growth. Summary of the invention

[0003] The embodiment of the present application provides an intelligent scheduling method and system for an irrigation pipe network based on a hydraulic model, which can achieve accurate water distribution and pressure control, thereby reducing the risk of pipe burst, improving irrigation efficiency, and reducing water resource waste.

[0004] In order to achieve the above object, the technical solution of the embodiment of the present invention is:

[0005] In the first aspect, an embodiment of the present invention provides an intelligent scheduling method for an irrigation network based on a hydraulic model, comprising: constructing a hydraulic irrigation model topology map of the target area according to the irrigation water source and irrigation network data of the target area; performing hydraulic irrigation simulation calculations according to the hydraulic irrigation model topology map, completing the call and initialization configuration of the network topology, and providing a data call interface for the intelligent scheduling algorithm to realize the simulation operation of the hydraulic irrigation model; establishing an irrigation network intelligent scheduling optimization objective function based on the crop type in the target area with the goal of optimizing the water supply quality; the optimization objective function is used to minimize the absolute error between the actual irrigation volume and the theoretical water demand; establishing irrigation network intelligent scheduling optimization constraint conditions by comprehensively considering the irrigation law of crops, irrigation water quotas, and hydraulic coefficients of the irrigation network; the constraint conditions include water supply constraints, head valve working pressure constraints, and pipeline health constraints; solving the optimal irrigation network scheduling plan using a preset genetic algorithm based on the optimization objective function and the optimization constraint conditions.

[0006] In some possible implementations, a water conservancy and irrigation model topology map of the target area is constructed based on the irrigation water source and irrigation pipe network data of the target area, including: drawing the water conservancy and irrigation model topology map of the target area through preset water conservancy system simulation software based on the graphic materials and irrigation data of the target area; the water conservancy and irrigation model topology map can simulate the actual irrigation conditions of the target area.

[0007] In some possible implementations, the optimization objective function is expressed as:

[0008]

[0009] Where T represents different irrigation stages, i represents the node number, and D iT represents the theoretical water demand of node i in stage T, Q iT is the total irrigation amount of node i in stage T, T schedual It is the total irrigation stage, which is embodied as seven stages of planting crops in the present invention, i node Represents all irrigation nodes in the current irrigation area.

[0010] In some possible implementations, the water supply constraint includes a total water supply constraint for a stage and an irrigation water quota constraint;

[0011] The total water supply constraint in the stage is expressed as:

[0012]

[0013] The irrigation water quota constraint is expressed as;

[0014]

[0015] The working water pressure constraint of the first valve is expressed as:

[0016] H i (B)≥H idem ;

[0017] The pipeline health constraint is expressed as:

[0018]

[0019] Among them, maxD iT and minD iT are the maximum water consumption and minimum water demand of node i in stage T respectively; Q dil It represents the annual water supply quota of the region, which is reflected in the model as the total flow of the first section of the pipeline connected to the reservoir node during the entire irrigation cycle; H i (B) represents the actual working water pressure of each node under the irrigation strategy, H idem is the minimum working pressure of the node; H jb(B) is the pressure of the first node of each pipeline, H jf (B) is the pressure of each pipeline tail node, K is the upper limit coefficient of pipeline pressure, H jul Design pressure for each pipeline.

[0020] In some possible implementations, according to the optimization objective function and optimization constraints, a preset genetic algorithm is used to solve and obtain the optimal irrigation network scheduling scheme, including:

[0021] The fitness function is used to evaluate each generation of individuals, and the solution that meets the preset requirements or reaches the upper limit of the number of iterations is regarded as the optimal solution; the fitness function is expressed as:

[0022]

[0023] In a second aspect, an embodiment of the present invention provides an intelligent scheduling system for an irrigation network based on a hydraulic model, comprising: a model construction module, which is used to construct a hydraulic irrigation model topology map of a target area according to the irrigation water source and irrigation network data of the target area; a model simulation operation module, which is used to perform hydraulic irrigation simulation calculations according to the hydraulic irrigation model topology map, complete the call and initialization configuration of the network topology, and provide a data call interface for the intelligent scheduling algorithm to realize the simulation operation of the hydraulic irrigation model; an optimization objective function construction module, which is used to establish an irrigation network intelligent scheduling optimization objective function based on the crop type in the target area with the goal of optimizing water supply quality; the optimization objective function is used to minimize the absolute error between the actual irrigation volume and the theoretical water demand; an optimization constraint condition construction module, which is used to establish an irrigation network intelligent scheduling optimization constraint condition by comprehensively considering the irrigation law of crops, the irrigation water quota, and the hydraulic coefficient of the irrigation network; the constraint condition includes a water supply constraint, a head valve working pressure constraint, and a pipeline health constraint; a solution module, which is used to solve the optimal irrigation network scheduling scheme using a preset genetic algorithm based on the optimization objective function and the optimization constraint condition.

[0024] One or more technical solutions provided in the embodiments of the present invention have at least the following technical effects or advantages:

[0025] In the embodiment of the present invention, by constructing a hydraulic irrigation simulation model, the hydraulic behavior of the pipe network under different operating scenarios can be simulated, thereby realizing accurate simulation and prediction of the hydraulic behavior in the irrigation pipe network. On this basis, according to the type of crops in the target area and their demand for water in the growth cycle, with the goal of optimizing the water supply quality, an intelligent scheduling optimization objective function of the irrigation pipe network is established. Not only the minimum absolute error between the actual irrigation volume and the theoretical water demand is considered, but also key conditions such as water supply constraints, head valve working pressure constraints, and pipeline pressure constraints are incorporated to ensure the scientificity and rationality of irrigation scheduling. Therefore, it can significantly improve irrigation efficiency, save water resources, promote the healthy growth of crops, and provide effective technical support for solving problems such as water shortage and poor irrigation management in modern agriculture. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the embodiments of the present invention, the accompanying drawings required for use in the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.

[0027] Figure 1 A schematic flow chart of an embodiment of an intelligent scheduling method for an irrigation network based on a hydraulic model provided for the implementation of the present invention;

[0028] Figure 2 A water conservancy irrigation model topology diagram of an actual irrigation pipe network in an embodiment of the present invention;

[0029] Figure 3 A rotation irrigation area division diagram of the western area of ​​a certain actual irrigation pipe network in an embodiment of the present invention;

[0030] Figure 4 A schematic diagram of a single-objective genetic algorithm optimization process in an embodiment of the present invention;

[0031] Figure 5 It is a comparison chart of irrigation error rate in 7 irrigation stages between the traditional rotation irrigation system and the optimized scheduling of the present invention;

[0032] Figure 6 It is a structural schematic diagram of an irrigation pipe network intelligent scheduling system based on a hydraulic model in an embodiment of the present invention. DETAILED DESCRIPTION

[0033] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0034] In the relevant description of this embodiment, the terms "including, containing, having" and the like are open terms and are generally understood to include but not be limited to; the term "at least one" is generally understood to mean one or more, where "plurality" refers to two or more; the term "at least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items, for example, "at least one of a, b or c", or "at least one of a, b and c", can all represent: a, b, c, ab (i.e., a and b), ac, bc, or abc, where a, b, c can be single or multiple, respectively; the symbol "A / B" is used to describe the selection relationship of associated objects, generally indicating an "or" relationship before and after.

[0035] In the following description of the present embodiment, the terms used in the embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit the present application. The singular forms "a" and "the" used in the embodiments of the present application and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings.

[0036] Those skilled in the art should understand that in the following description of the embodiments of the present application, the order of serial numbers does not mean the order of execution, some or all of the steps can be executed in parallel or sequentially, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0037] Those skilled in the art will appreciate that the numerical ranges in the embodiments of the present application are to be construed as also specifically disclosing each intermediate value between the upper and lower limits of the scope. Each smaller range between the intermediate value in any stated value or stated range and any other stated value or intermediate value in the range is also included in the present invention. The upper and lower limits of these smaller ranges may be independently included or excluded in the scope.

[0038] Unless otherwise specified, the technical / scientific terms used herein have the same meanings as those generally understood by those skilled in the art to which this application belongs. Although this application only describes preferred methods and materials, any methods and materials similar or equivalent to these may also be used in the implementation or testing of this application. All documents mentioned in this specification are incorporated by reference to disclose and describe methods and / or materials related to the documents. In the event of a conflict with any incorporated document, the content of this specification shall prevail.

[0039] In order to illustrate the technical solution of the present invention, specific embodiments are provided below for illustration.

[0040] In modern agriculture, the effective management and utilization of water resources is one of the key factors in improving crop yield and quality. With global climate change and population growth, agricultural production is facing increasingly severe challenges. Water shortage has become one of the main bottlenecks restricting the sustainable development of agriculture. Traditional irrigation methods often rely on experience and fixed irrigation schedules, which makes it difficult to accurately meet the water needs of different crops at different growth stages and large-scale irrigation at the same time, resulting in waste of water resources and uneven crop growth, and making it difficult to plan irrigation water in a unified manner. For example, frequent irrigation may lead to soil salt accumulation, while insufficient irrigation will affect crop growth and yield. Intelligent irrigation scheduling based on hydraulic models can solve the problems of existing technologies and provide an accurate and efficient irrigation water allocation solution to significantly reduce water resource consumption and improve the uniformity and health of crop growth.

[0041] Based on this, the embodiments of the present invention provide an intelligent scheduling method and system for an irrigation network based on a hydraulic model, which can achieve accurate water distribution and pressure control, thereby reducing the risk of pipe burst, improving irrigation efficiency, and reducing water resource waste.

[0042] Figure 1 A schematic diagram of an embodiment of an intelligent scheduling method for an irrigation network based on a hydraulic model provided for the implementation of the present invention is shown in FIG. Figure 1 As shown, the above method may include:

[0043] S101, constructing a water conservancy irrigation model topology map of the target area according to the irrigation water source and irrigation pipe network data of the target area;

[0044] Among them, the irrigation water source includes but is not limited to the location, water volume, water quality, water temperature, water flow rate and other information of surface water (such as rivers, lakes, reservoirs, etc.), and related information of groundwater (such as the depth, water output, water quality, etc. of wells). The irrigation pipe network data includes but is not limited to the pipe length, pipe radius, valve nodes, pipe elevation and connection relationship between pipes of the irrigation pipe.

[0045] When constructing the topology of the water conservancy irrigation model, the above-mentioned parameter information will be comprehensively considered, and the irrigation water source will be used as the starting point. Based on the pipeline information in the irrigation pipe network data, the connection relationship from the water source to each irrigation area will be accurately depicted, including the layout of the main pipe, branch pipe, valve, sprinkler, etc. With this information, a detailed and accurate topology map can be established. This topology map can not only show the physical structure of the pipe network, but also include the relationship between the water source and the pipe network, providing basic data support and a visual structural framework for subsequent irrigation scheduling optimization operations.

[0046] In some embodiments, the above step S101 can draw a water conservancy and irrigation model topology map of the target area based on the graphic information and irrigation data of the target area through a preset water conservancy system simulation software; the water conservancy and irrigation model topology map can simulate the actual irrigation conditions of the target area.

[0047] Specifically, a professional geographic information system (GIS) or hydraulic simulation software (such as EPANET, etc.) can be used to construct a water conservancy irrigation model topology map of the target area based on these data. Take the construction of a water conservancy irrigation model topology map through EPANET as an example: the first step is to enter the drawing interface, add an irrigation water source (such as a reservoir) according to the actual irrigation area, and set the location of the reservoir on the drawing interface; the second step is to add nodes, and add pipeline connection nodes and valve nodes corresponding to the actual irrigation area on the drawing interface through the node button; the third step is to add pipe segments, each pipe segment connects two nodes, and curved pipe segments can also be added as needed; the fourth step is parameter input, click on the node or pipeline, and enter the attribute parameters related to it, such as node name, type (such as water source, demand node), head or pipe length, diameter, material, and friction coefficient. The fifth step is topology generation and inspection, saving the topology model as a .inp type file to ensure that the topology can simulate the actual irrigation area for subsequent calls.

[0048] For example, see Figure 2 As shown, Figure 2 It is a water conservancy irrigation model topology diagram of the actual irrigation pipe network in the embodiment of the present invention. After obtaining the data of the irrigation water source, irrigation pipe drawings, and irrigation valve control area of ​​the target area, through the above step S101, it is possible to draw a water conservancy irrigation model topology diagram. Figure 2 The topology diagram of the water conservancy irrigation model is shown.

[0049] S102, according to the water conservancy irrigation model topology diagram, perform hydraulic irrigation simulation calculation, complete the call and initialization configuration of the pipe network topology, and provide a data call interface for the intelligent scheduling algorithm to realize the simulation operation of the hydraulic irrigation model;

[0050] Specifically, after obtaining the water conservancy irrigation model topology diagram constructed above, hydraulic irrigation simulation calculation is further carried out. The core of this step is to use hydraulic simulation software or algorithm to simulate the hydraulic behavior of the irrigation pipe network under different working conditions according to the actual layout and operation parameters of the pipe network.

[0051] First, import the pipe network topology into the hydraulic simulation software to complete the call and initial configuration of the pipe network. For example, set the material, diameter, flow rate, pressure and other parameters of the pipe, and define the operation logic of key nodes such as valves and pump stations. These configurations will ensure that the simulation results can truly reflect the actual operation status of the pipe network.

[0052] Next, the simulation software and the algorithm are seamlessly connected using the data call interface required by the intelligent scheduling algorithm. This interface will allow the algorithm to access the pipe network data in the simulation software in real time, including key information such as flow, pressure, and water quality. This data will provide the necessary input for the intelligent scheduling algorithm, enabling it to automatically calculate the optimal irrigation scheduling plan based on the current pipe network status and operation goals.

[0053] After completing the docking of the data call interface, start the simulation operation of the hydraulic irrigation model. During this process, the simulation software will simulate and calculate the hydraulic behavior of the pipe network in real time according to the preset working conditions and parameters. At the same time, the intelligent scheduling algorithm will continuously receive and process the data output by the simulation software, and automatically adjust the irrigation scheduling plan according to the algorithm logic to achieve the optimization of the pipe network operation.

[0054] For example, the hydraulic modeling based on Python WNTR tool library to achieve simulation is used as an example: WNTR has the following functions: generating pipe network hydraulic and water quality models, modifying or operating pipe network structures, simulating pipe leakage, visualizing results, etc. The modeling steps include initialization settings, pipe network topology calls, and simulation runs.

[0055] The initialization settings include time options and hydraulic simulation presets. The time options can be modified through wntr.options.time, including simulation time, simulation step, water demand mode step, simulation start time, and total time and step of simulation result report; hydraulic simulation presets can be modified through wntr.options.hydra ukic, including flow units, adjustment calculation formula, default water demand mode and water demand operator, etc.

[0056] The creation and calling of the pipe network topology in Python are as follows: 1. The calling and calculation of the topological pipe network are based on the WNTR library. Make sure that the WNTR library is installed and imported; 2. Call the pipe network model according to the storage address of the topological pipe network and copy it to the new variable wn; 3. Check the node and pipe segment information to ensure that all information corresponds to the actual data. If you need to modify the data, you can modify it by checking the properties of the node. The node properties include: node water demand (base_demand), pressure (pressure), head (head), pipe segment length (length), friction (roughness), diameter (diameter), etc. After completing the data confirmation, you can perform the simulation.

[0057] The simulation is run by calling run_sim. The simulation results are returned in dictionary format. The simulation results of each node and pipeline are stored in run_sim.node and run_sim.link. The hydraulic simulation results of the node include the actual water demand, head, and pressure. The hydraulic simulation results of the pipeline include flow rate per second, head loss, velocity, status, and friction factor.

[0058] S103, establishing an irrigation network intelligent scheduling optimization objective function based on the type of crops in the target area and taking the optimal water supply quality as the goal; the optimization objective function is used to minimize the absolute error between the actual irrigation amount and the theoretical water demand;

[0059] For example, take the irrigation of crops in a certain place as an example. Assume that the land is flat, the soil moisture content is low, the rainfall is little, and the main irrigation water source comes from the mountain reservoir. Since gravity flow is used for water supply, the main thing is to schedule the opening and closing of the valve. And it needs to be scheduled according to the water demand characteristics of crops in different growth cycles.

[0060] Assuming that the main crop in the region is apple, the annual water requirement of apple is 434-479 mm (millimeter). In areas with annual precipitation less than 450 mm, timely and appropriate irrigation is required according to the water demand logic to meet the water demand of apple. The water requirement of apple increases year by year with the increase of tree age, branches, leaves and fruits. From budding to fruit ripening and picking, the average water consumption intensity per square meter of planting area is about 2.01-2.21 mm / d (millimeter / day), among which the water consumption in each phenological period varies greatly. The specific irrigation requirements are as follows:

[0061] 1) Bud stage (early to mid-April): water consumption intensity is 1.21-1.47 mm / d.

[0062] 2) Flowering period (late April to early May): water consumption intensity is 1.44~1.81mm / d.

[0063] 3) New shoots grow vigorously and for a long time (early May to early June): The water consumption intensity is the largest in the whole phenological period, which is 2.58-2.80 mm / d.

[0064] 4) New shoots stop growing for a long time (mid-June to early July): water consumption intensity is significantly reduced to 1.50-1.62 mm / d.

[0065] 5) Secondary growth period of new shoots (mid-July to early September): This period is also the period of rapid fruit expansion, with a water consumption intensity of 2.42-2.64 mm / d. During this period, the temporal and spatial distribution of precipitation is uneven and transpiration is strong, with a total water consumption of 152.0-165.7 mm / d.

[0066] 6) Fruit ripening period (mid-September to mid-October): water consumption intensity is 2.07-2.31 mm / d.

[0067] 7) Leaf fall period (late October to early November): water consumption intensity is significantly reduced to 2.01-2.21 mm / d.

[0068] Based on the different scheduling durations of each stage and the basic water requirements per unit planting area, the apples are divided into the above 7 stages from budding to fruit ripening and picking. The simulation step is set to 1 day, that is, the opening and closing of the head water supply valve (node ​​in the topology diagram) is scheduled in units of days. Therefore, the decision variable B = [b1, b2, b3, b4, b5, b6, b7] is a three-dimensional matrix, b1~b7 are all n T ×i node A two-dimensional matrix of type bool (elements have values ​​of 0 or 1), representing the irrigation schemes from the 1st to the 7th stage. T is the number of scheduling days in irrigation stage T, i node is the number of head valves in the irrigation area. Based on the above analysis, the objective function of the optimization problem is set to maximize the satisfaction of irrigation water demand, that is, the absolute error between the actual irrigation amount and the theoretical water demand is minimized. The objective function expression can be expressed as:

[0069]

[0070] Where T represents different irrigation stages, i represents the node number, and D iT represents the theoretical water demand of node i in the Tth stage, T schedual It is the total irrigation stage, which is embodied as seven stages of planting crops in the present invention, i node Represents all irrigation nodes in the current irrigation area.

[0071] Q iTis the total watering amount of node i in stage T, expressed as:

[0072]

[0073] Among them, q iT is the water supply of node i in stage T within a scheduling step, b iTn Indicates the on / off status of node i in the nth scheduling period of phase T, and the value can be 0 or 1.

[0074] S104, by comprehensively considering the irrigation law of crops, the irrigation water quota, and the hydraulic coefficient of the irrigation pipe network, establish the intelligent scheduling optimization constraint conditions of the irrigation pipe network; the constraint conditions include water supply constraint, head valve working pressure constraint, and pipe health constraint;

[0075] Specifically, taking the planting of apples in the above-mentioned place as an example, after completing the construction of the irrigation scheduling optimization objective function to ensure irrigation quality, the concept of irrigation water quota is introduced for the planting area of ​​apple trees: the irrigation water quota refers to the amount of irrigation water for a certain area of ​​land during the preparation period for apple cultivation and the entire growth period of the crop. The calculation of the irrigation water quota usually involves factors such as crop evapotranspiration, soil evaporation and rainfall, and can be calculated by subtracting rainfall from the sum of crop evapotranspiration and soil evaporation. In the prior art, the general value of the irrigation water quota is determined by calculating the net water quota and the irrigation water utilization coefficient of the existing large and medium-sized irrigation districts, the headwaters of small irrigation districts, and the wellheads. The calculation method is expressed as follows:

[0076] m 通用 =m 净 / η 斗 ;

[0077] Among them, m 通用 It is the general value of irrigation water quota, in m 3 / mu; m 净 Net water consumption quota, in m 3 / mu; η 斗 is the irrigation water utilization coefficient, which is determined comprehensively according to the irrigation water utilization coefficient of the actual water use scenario. When specifying the advanced value of the irrigation water quota, the irrigation water utilization coefficient of the actual irrigation technology can be substituted into the above formula for calculation.

[0078] Among them, the irrigation water utilization coefficients of common water-saving irrigation technologies are: η 渠道防渗 =0.7,η 管道 =0.8,η 喷灌 =0.8,η 微灌 =0.85.

[0079] When determining specific irrigation water quotas, it is necessary to introduce the concept of hydrological year. Hydrological year is a concept corresponding to hydrological conditions, used to describe years under specific hydrological conditions. The guarantee rate represents the degree of drought in a hydrological year. It is generally believed that a hydrological year with a guarantee rate of 50% is a normal water year, and a guarantee rate of 75% is a drought year.

[0080] From the above, it can be determined that the irrigation water quota constraint of the optimization objective function can be expressed as:

[0081]

[0082] Among them, Q dil Indicates the annual water supply quota of the area. Figure 2 It is reflected as the total flow of the first section of the pipeline outside the reservoir node during the entire irrigation cycle.

[0083] In some embodiments, Figure 2 The irrigation area shown is divided into the southern area, the northern area and the western area. Taking the western area as an example, the traditional rotation irrigation strategy design is as follows Figure 3 As shown in the figure, according to manual experience, irrigation valves are opened in a planned manner according to the area. The main irrigation method of the irrigation area is drip irrigation. The irrigation area is divided into 4 rotation irrigation areas according to the branch lines. The total area is about 3895.6 mu. The average soil bulk density of 1m soil layer before rainfall is 1.3g / m 3 The main crop in this area is apple, and the maximum water consumption is designed to be 3mm / d. Therefore, the hourly water consumption during drip irrigation is 2.62mm / m 2 In addition, the designed water requirements of fruit trees in the seven stages from budding to leaf fall are 1.5mm / d, 2mm / d, 3mm / d, 2mm / d, 3mm / d, 2.5mm / d, 2.5mm / d, and the irrigation water quota is 634.78m 3 / mu, which basically meets the guaranteed irrigation water supply rate in normal water years. The relevant data of the rotation irrigation system in September are shown in Table 1, and the scheduling steps and water demand in each stage are shown in Table 2.

[0084] Table 1:

[0085]

[0086] Table 2:

[0087]

[0088] Based on this, the total water supply constraint of the objective function can be determined as follows:

[0089]

[0090] Among them, maxD iT and minD iTare the maximum water consumption and minimum water demand of node i in stage T respectively.

[0091] Understandably, in the actual rotation irrigation and water supply process, there are cases where farmers privately connect production water pipes and use excessive water. Privately connecting water supply pipes not only causes insufficient water supply and a drop in reservoir water levels, but also causes the pipes to be emptied and negative pressure to occur, endangering water supply safety. Therefore, the intelligent scheduling of the irrigation area makes a fine configuration of the irrigation volume of each irrigation head, and can formulate a water supply scheduling plan for each irrigation head according to the fruit tree irrigation cycle and water demand.

[0092] In some embodiments, the first valve working water pressure constraint is expressed as:

[0093] H i (B)≥H idem ;

[0094] Among them, the constraints H i (B) represents the actual working water pressure of each node under the irrigation strategy, H idem is the minimum working pressure of the node.

[0095] In some embodiments, the health of pipelines should also be considered when formulating water supply scheduling plans for irrigation areas. The pressure H of each pipeline during the scheduling process j (B) must be less than the design pressure H jul K times, where H j (B) can be expressed as its first node pressure H jf (B) and tail node pressure H jb The mean of (B), the pipeline health constraint expression can be expressed as:

[0096]

[0097] S105, according to the optimization objective function and the optimization constraints, a preset genetic algorithm is used to solve and obtain the optimal irrigation network scheduling plan.

[0098] Specifically, a genetic algorithm is used to solve the irrigation scheduling optimization problem established in the above steps S103 and S104. The basic idea of ​​the genetic algorithm is to encode the solution of the problem into a set of genes or chromosomes, and then use genetic operations (including selection, crossover, and mutation) to evolve these individual solutions. Each individual solution is assigned a fitness value to evaluate its superiority in the solution space. During the evolution process, the solution with a higher fitness may be used to generate the next generation of solutions.

[0099] Figure 4 This is a schematic diagram of the single-objective genetic algorithm optimization process in an embodiment of the present invention, see Figure 4As shown, the primary task of the genetic algorithm to solve the single-objective optimization problem is to define the fitness function and determine the genetic operator. In the process of algorithm iteration, the fitness function is used to evaluate each generation of individuals. The fitness value reflects the excellence of the individuals in the population. Individuals with higher fitness are better solutions. As the genetic algorithm proceeds, the individual fitness value will continue to increase, and the quality of the solution will improve accordingly, until a solution that meets the requirements is obtained or the number of iterations reaches the upper limit, and the algorithm iteration is terminated. The optimization goal in the example adopted by the present invention is to minimize the absolute error between the actual water supply and the theoretical water storage capacity. Therefore, the absolute value of the objective function can be taken as the fitness function. The minimum fitness value means the minimum absolute error rate. Therefore, the expression of the fitness function can be expressed as:

[0100]

[0101] The definitions and values ​​of the variables in the above formula are as described above. For example, the irrigation area consists of 153 head valves, and the scheduling cycle is divided into 7 stages, where the number of scheduling steps in each stage is n. T They are 20 days, 30 days, 30 days, 30 days, 60 days, 40 days, and 20 days respectively, and the scheduling step is 1 day. Therefore, the decision variable B (given by b iTn The array can be set to a format of 7×n T ×153 three-dimensional array.

[0102] Since the decision variable is a three-dimensional matrix, and the number of rows and columns of each element is different, it is necessary to crossover different elements separately when performing the crossover operation. The operation steps are as follows: Step 1. Calculate the number of individuals n participating in the crossover according to the crossover operator, and select n individuals with the best fitness values ​​as parent individuals; Step 2. Traverse these n parent individuals, and for each parent individual, randomly select an individual from all individuals as the parent individual to cross with it; Step 3. Traverse each first-level index of the parent individual; Step 4. Randomly take a section in each corresponding second-level index of the parent individual and assign it to the corresponding position of the parent individual.

[0103] Similar to the crossover operation, the compilation operation also needs to be discussed separately for different orders, randomly selecting individuals for mutation, and for each individual participating in the mutation, randomly selecting a segment in each of its secondary indexes to perform the mutation operation. Since the decision variable is encoded as a binary code, the compilation operation is to randomly flip the mutation code segment bit by bit.

[0104] The invention provides an irrigation pipe network intelligent scheduling method based on a hydraulic model, which is programmed based on Python, and the algorithm parameters can be set as follows: crossover operator (crossover probability is 80%), mutation operator (mutation probability is 10%), initial population size is 30, and the maximum number of iterations is 500 generations.

[0105] Specific steps are as follows Figure 4 As shown in the figure, (1) determine the encoding method, fitness function, operator and algorithm parameters of the individuals in the population; (2) generate a four-dimensional array with the element format of h×7×nT×153 within the feasible domain, where h represents the population size and 7×nT×153 represents the opening and closing combination of 153 head valves in 7 scheduling stages as the initial population. (3) update the pipe network parameters according to the stage, substitute the individuals into the hydraulic model to run the simulation, and obtain the flow and pressure data of each individual. (4) calculate the fitness value of each individual in the population according to formula (11). (5) determine whether the convergence condition is met. If there is an individual whose fitness value reaches the expectation or the number of iterations reaches the maximum, jump to (7), otherwise execute the next step; (6) perform selection, crossover and mutation operations to generate a new population. Go to (3); (7) the algorithm outputs the current optimal solution, that is, the optimal irrigation head scheduling plan, which is encapsulated as a .txt format document.

[0106] In some embodiments, after obtaining the optimal irrigation network scheduling solution, the results can be further analyzed and evaluated. For example, based on the real data of a local irrigation water supply network, programming experiments are performed through the Python platform, and the parameter settings of the optimization algorithm can be shown in Table 3.

[0107] Table 3:

[0108]

[0109] As shown in Table 3, the pipeline pressure upper limit coefficient K refers to the ratio of the maximum internal pressure allowed in the pipeline during the scheduling process to the maximum pressure of the pipeline design. The actual water demand of the node is related to the theoretical water demand DiT of the node. The node may be opened or closed during scheduling, and its water supply is 0 when it is closed. Therefore, in order to meet the requirements of the full-cycle irrigation volume, the water supply of the node should be higher than its theoretical water demand when it is opened. After multiple simulation experiments, the node water demand is set to 1.85 times the theoretical water demand.

[0110] Table 4 shows the scheduling process and irrigation error rate of the 5 head valves of the west 1 branch of the irrigation area in the embodiment of the present invention within 20 scheduling steps in irrigation stage 1. As can be seen from Table 4, the average error rate between the actual irrigation amount and the theoretical water demand is 7.05%.

[0111] Table 4:

[0112]

[0113] Figure 5 This is a comparison chart of the irrigation error rate between the traditional rotation irrigation system and the optimized scheduling of the present invention in 7 irrigation stages, see Figure 5As shown in the figure, the average irrigation error rate of traditional rotation irrigation scheduling is 19.6%. The error is mainly caused by the irrigation amount exceeding the theoretical water demand. The higher error rate in stage 4 and stage 5 is due to the fact that the rotation irrigation system takes into account the large evaporation in summer and ensures the soil moisture ratio by excessive water supply. The average irrigation error rate of the scheduling strategy of the method of the present invention is 6.49%. Through refined scheduling, soil moisture can be replenished in time to ensure the quality of crop irrigation.

[0114] In the embodiment of the present invention, by constructing a hydraulic irrigation simulation model, the hydraulic behavior of the pipe network under different operating scenarios can be simulated, thereby realizing accurate simulation and prediction of the hydraulic behavior in the irrigation pipe network. On this basis, according to the type of crops in the target area and their demand for water in the growth cycle, with the goal of optimizing the water supply quality, an intelligent scheduling optimization objective function of the irrigation pipe network is established. Not only the minimum absolute error between the actual irrigation volume and the theoretical water demand is considered, but also key conditions such as water supply constraints, head valve working pressure constraints, and pipeline pressure constraints are incorporated to ensure the scientificity and rationality of irrigation scheduling. Therefore, it can significantly improve irrigation efficiency, save water resources, promote the healthy growth of crops, and provide effective technical support for solving problems such as water shortage and poor irrigation management in modern agriculture.

[0115] Based on the same inventive concept, the embodiment of the present application also provides an intelligent scheduling system for irrigation pipe networks based on a hydraulic model. Figure 6 FIG. 1 is a schematic diagram of the structure of an intelligent scheduling system for an irrigation network based on a hydraulic model in an embodiment of the present invention. Figure 6 As shown, the irrigation network intelligent scheduling system 600 based on the hydraulic model may include:

[0116] The model building module 601 is used to build a water conservancy irrigation model topology map of the target area according to the irrigation water source and irrigation pipe network data of the target area;

[0117] The model simulation operation module 602 is used to perform hydraulic irrigation simulation calculation according to the hydraulic irrigation model topology diagram, complete the call and initialization configuration of the pipe network topology, and provide a data call interface for the intelligent scheduling algorithm to realize the simulation operation of the hydraulic irrigation model;

[0118] The optimization objective function construction module 603 is used to establish an optimization objective function for intelligent scheduling of irrigation pipe networks based on the type of crops in the target area and with the goal of optimizing water supply quality; the optimization objective function is used to minimize the absolute error between the actual irrigation amount and the theoretical water demand;

[0119] The optimization constraint condition building module 604 is used to establish the optimization constraint conditions of the intelligent scheduling of the irrigation network by comprehensively considering the irrigation law of crops, the irrigation water quota, and the hydraulic coefficient of the irrigation network; the constraint conditions include water supply constraint, head valve working pressure constraint, and pipeline health constraint;

[0120] The solution module 605 is used to solve the optimal irrigation network scheduling solution by using a preset genetic algorithm according to the optimization objective function and the optimization constraints.

[0121] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other. Each embodiment focuses on the differences from other embodiments.

[0122] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit the present application. Although the present application has been described in detail with reference to the aforementioned embodiments, a person of ordinary skill in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some or all of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the present application.

Claims

1. An intelligent scheduling method for irrigation pipe network based on hydraulic model, characterized in that: include: Constructing a water conservancy irrigation model topology map of the target area based on the irrigation water source and irrigation pipe network data of the target area; According to the water conservancy irrigation model topology diagram, hydraulic irrigation simulation calculation is performed to complete the call and initialization configuration of the pipe network topology, and a data call interface is provided for the intelligent scheduling algorithm to realize the simulation operation of the hydraulic irrigation model; According to the crop types in the target area, an irrigation network intelligent scheduling optimization objective function is established with the goal of optimizing water supply quality; the optimization objective function is used to minimize the absolute error between the actual irrigation amount and the theoretical water demand; By comprehensively considering the irrigation rules of crops, irrigation water quotas, and hydraulic coefficients of the irrigation pipe network, the optimization constraints of intelligent scheduling of the irrigation pipe network are established; the constraints include water supply constraints, head valve working pressure constraints, and pipe health constraints; According to the optimization objective function and the optimization constraints, a preset genetic algorithm is used to solve the problem and obtain the optimal irrigation network scheduling solution.

2. The method according to claim 1, characterized in that The step of constructing a water conservancy irrigation model topology map of the target area based on the irrigation water source and irrigation pipe network data of the target area includes: According to the graphic information and irrigation data of the target area, a water conservancy and irrigation model topology map of the target area is drawn through a preset water conservancy system simulation software; the water conservancy and irrigation model topology map can simulate the actual irrigation situation of the target area.

3. The method according to claim 2, characterized in that The optimization objective function is expressed as: Where T represents different irrigation stages, i represents the node number, and D iT represents the theoretical water demand of node i in stage T, Q iT is the total irrigation amount of node i in stage T, T schedual It is the total irrigation stage, which is embodied as seven stages of planting crops in the present invention, i node Represents all irrigation nodes in the current irrigation area.

4. The method according to claim 3, characterized in that The water supply constraints include total water supply constraints for the stage and irrigation water quota constraints; The total water supply constraint in this stage is expressed as: Among them, maxD iT and minD iT are the maximum water consumption and minimum water demand of node i in stage T, respectively, iTn is the open and closed state of node i in the nth scheduling period of phase T; The irrigation water quota constraint is expressed as: Among them, Q dil It indicates the annual water supply quota of the area; The working water pressure constraint of the first valve is expressed as: H i (B)≥H idem ; Among them, the constraints H i (B) represents the actual working water pressure of each node under the irrigation strategy, H idem is the minimum working pressure of the node; The pipeline health constraint is expressed as: Among them, H i (B) represents the actual working water pressure of each node under the irrigation strategy, H idem is the minimum working pressure of the node; H jb (B) is the pressure of the first node of each pipeline, H jf (B) is the pressure of each pipeline tail node, K is the upper limit coefficient of pipeline pressure, H jul Design pressure for each pipeline.

5. The method according to claim 4, characterized in that According to the optimization objective function and the optimization constraint conditions, a preset genetic algorithm is used to solve and obtain the optimal irrigation network scheduling scheme, including: The fitness function is used to evaluate each generation of individuals, and the solution that meets the preset requirements or the individual that reaches the upper limit of the number of iterations is taken as the optimal solution; wherein the fitness function is expressed as:

6. An intelligent scheduling system for irrigation pipe network based on hydraulic model, characterized in that: include: A model building module, used to build a water conservancy irrigation model topology map of the target area according to the irrigation water source and irrigation pipe network data of the target area; The model simulation operation module is used to perform hydraulic irrigation simulation calculation according to the hydraulic irrigation model topology diagram, complete the call and initialization configuration of the pipe network topology, and provide a data call interface for the intelligent scheduling algorithm to realize the simulation operation of the hydraulic irrigation model; An optimization objective function construction module is used to establish an irrigation network intelligent scheduling optimization objective function based on the type of crops in the target area and with the goal of optimizing water supply quality; the optimization objective function is used to minimize the absolute error between the actual irrigation amount and the theoretical water demand; The optimization constraint condition building module is used to establish the optimization constraint conditions for intelligent scheduling of the irrigation network by comprehensively considering the irrigation law of crops, the irrigation water quota, and the hydraulic coefficient of the irrigation network; the constraint conditions include water supply constraint, head valve working pressure constraint, and pipeline health constraint; The solution module is used to solve the optimization objective function and the optimization constraint conditions using a preset genetic algorithm to obtain an optimal irrigation network scheduling solution.

Images