Irrigation digital twin system for combination of agriculture and clean energy

Abstract

The invention discloses an irrigation digital twinning system for combination of agriculture and clean energy, and belongs to the technical field of agricultural irrigation, the irrigation digital twinning system comprises a physical body, a twinning body and a digital twinning platform, and data mirroring, mapping reconstruction, information interaction and analogue simulation of a virtual body and the physical body are realized through data driving of the digital twinning platform; a simulation model and a twinborn body are constructed by taking a digital twinborn platform as a framework, taking the model as a substrate and taking data as driving. Agricultural, irrigation and clean energy power generation are combined by applying a digital twinborn technology, twinborn modeling is performed on a crop model, a power generation model and an irrigation model, and a digital twinborn model is established through a data management module, an optimization model module, a machine learning module and the like of a digital twinborn platform. And a system and a platform which have a full life cycle and integrate monitoring, optimization adjustment, analogue simulation, control and operation and maintenance are formed.

Description

Technical Field

[0001] The present invention belongs to the field of photovoltaic irrigation technology, and specifically relates to an irrigation digital twin system that combines agriculture with clean energy. Background Art

[0002] Agricultural development faces challenges such as resource shortages, insufficient technological expertise, and low efficiency. To ensure a balanced supply of agricultural products, modern agriculture must be developed based on the actual needs of agricultural development, embracing informatization and modernization. With the development of the Internet of Things (IoT) and modern new energy models, a new era has arrived for agriculture. The IoT, based on various sensors, collects vast amounts of data in real time, enabling perception of the world through internet and communication networks, and utilizing automated control and other advanced technologies to control related devices within the system. The development of modern agriculture is facing increasing challenges related to uneven water resource distribution and the imbalance between supply and demand. In practical agricultural production, effective and rational irrigation systems should be implemented. Based on the actual water requirements of crops, advanced technologies should be applied to implement precision irrigation through analysis of extensive data to improve irrigation efficiency and maximize water utilization.

[0003] Clean energy is green energy that emits no pollutants and can be used directly for production and daily life. It includes nuclear energy, wind energy, solar energy, geothermal energy, and many other energy sources. With the growing demand for energy and increasing environmental protection worldwide, the promotion and application of clean energy has become an inevitable trend. For example, solar power generation uses photovoltaic equipment to convert solar energy into electricity. This process does not emit any harmful substances and does not pollute the environment. Wind energy is also a renewable, pollution-free energy source with vast reserves. Wind energy is the kinetic energy generated by the movement of large amounts of air over the Earth's surface. It is significantly affected by topographical factors and is currently primarily utilized through wind turbines.

[0004] Digital twin technology leverages data from physical models, sensor updates, and operational history to integrate multidisciplinary, multi-physics, multi-scale, and multi-probability simulation processes. This technology maps physical equipment in a virtual space, reflecting the entire lifecycle of the corresponding physical equipment. Digital twin agriculture is a new model for modern agriculture that leverages scientific theories and technologies such as complex adaptive systems theory, digital twins, and blockchain to innovate smart agriculture.

[0005] Patent No. CN118246713A specifically provides a calculation formula for a crop growth cycle calculation model. This invention uses irrigation districts as calculation units. By collecting and organizing the planting structure of irrigation districts, utilizing existing hydrological, meteorological, and water resource monitoring elements, it matches and calculates the water demand process of crops in irrigation districts with the spatiotemporal process of precipitation, and constructs a multi-factor calculation method. The results of this multi-factor calculation provide a data basis for objectively determining the water consumption of cultivated land in irrigation districts. However, this patent fails to organically combine clean energy, irrigation, and agriculture to form an intelligent monitoring and control system, thereby failing to rationally and efficiently utilize resources. Summary of the Invention

[0006] This invention addresses the inability of existing intelligent monitoring and control systems to efficiently utilize resources. By proposing a digital twin irrigation system for agriculture and clean energy, this system integrates clean energy, irrigation, and agricultural systems into a three-in-one intelligent monitoring and control system. By monitoring crop water demand and adjusting the irrigation system's output and the clean energy generation system's supply, this system effectively achieves water-saving irrigation and electricity distribution, effectively utilizing resources.

[0007] To solve the above technical problems, the present invention provides an irrigation digital twin system that combines agriculture with clean energy, including:

[0008] physical, virtual, and digital twin platforms;

[0009] The physical bodies include clean energy systems for power generation, irrigation systems, and agricultural systems;

[0010] The twins include a clean energy system twin, an irrigation system twin, and an agricultural system twin;

[0011] The digital twin platform includes an information system unit, a data management unit, a state database unit, an optimization model unit, a machine learning unit, and a solution evaluation unit;

[0012] The digital twin platform is used to perform twin modeling of the clean energy system, irrigation system, and agricultural system to form a monitoring and control system. The output of the irrigation system and the supply mode of the clean energy power generation system are adjusted according to the water demand of crops. At the same time, twin models of sub-regions are established according to different irrigation areas, and the crop model and irrigation model of each sub-region are matched with each other.

[0013] Preferably, the clean energy system twin is embodied by a clean energy system power generation model, including a solar power generation model and a wind power generation model;

[0014] The twin of the irrigation system is characterized by pump characteristics and pipeline characteristics; wherein the pump characteristics include a head characteristic curve and a power characteristic curve, and the pipeline characteristics include a pipeline characteristic curve;

[0015] The agricultural system twin is embodied by calculating the water supply of the irrigation system.

[0016] Preferably, the solar power generation model is specifically shown as follows:

[0017]

[0018] Among them, P v is the solar power generation power, P VN is the solar rated power, G is the actual radiation intensity, G N is the rated radiation intensity, η is the temperature coefficient of the photovoltaic panel, T is the actual temperature of the photovoltaic panel, T N is the rated temperature of the photovoltaic panel, γ is the shading coefficient;

[0019] The wind power generation model is specifically shown in the following formula:

[0020]

[0021] Among them, P W is the wind power generation power, V W is the fan speed at a certain moment, P WN is the wind energy rated power, A1~A3 are the characteristic coefficients of the wind energy generator, V min is the minimum speed of wind power generation, V N is the rated speed of wind power generation, V max is the maximum speed of wind power generation;

[0022] The clean energy system power generation model is specifically shown in the following formula:

[0023] P sys =P V +P W ;

[0024] Among them, P sys Power for clean energy generation system.

[0025] Preferably, the lift characteristic curve is specifically shown as follows:

[0026] H=a1Q 2 +a2Qk+a3k 2 ;

[0027] Where H is the pump head, a1 to a3 are the fitting coefficients of the head characteristic curve, Q is the pump flow rate, and k is the pump speed ratio;

[0028] The power characteristic curve is specifically shown in the following formula:

[0029] P=b1Q 3 +b2Q 2 k 2 +b3Qk 3 +b4k 4 ;

[0030] Among them, b1~b4 are the fitting coefficients of the head characteristic curve;

[0031] The pipeline characteristic curve is specifically shown in the following formula:

[0032] H sys =c1Q 2 +c2Q+c3;

[0033] Among them, c1~c3 are the fitting coefficients of the pipeline characteristic curve, H sys is the pipeline resistance;

[0034] The calculation of the water supply of the irrigation system is specifically shown in the following formula:

[0035] Q req =Q p +Q i +Q s -Q e -Q t -Q d ;

[0036] Among them, Q p is the precipitation, Q i is the water supply, Q s is the soil moisture content, Q e is the amount of water evaporated from the soil layer, Q t is the amount of water infiltrated into the soil layer, Q d is the soil drainage volume; Qreq is the water requirement for crop growth.

[0037] Preferably, the information system unit is a human-computer interaction and management platform; the data management unit manages and processes data from the database; the state database unit stores the operating data of the physical body and the virtual body; the optimization model unit is used to optimize the water demand conditions according to the water demand of crops and perform multi-objective optimization with minimum water consumption deviation and minimum power consumption as optimization goals, and obtain the adjustment plan through iterative solution of the optimization algorithm; the machine learning unit is used to learn historical plans and optimize the adjustment plan provided by the optimization model unit; the plan evaluation unit is used to screen the plans and evaluate the simulation results.

[0038] Preferably, the optimization model unit comprises the following steps:

[0039] S1. Obtain the water demand of crops in the agricultural system through sensors and transmit relevant data to the digital twin platform;

[0040] S2. Calculate the theoretical water supply for each sub-region based on the agricultural system twin;

[0041] S3. Based on the irrigation system twin, the actual water supply of each sub-area is calculated considering the irrigation constraints, and then the actual total water supply of the irrigation system twin is calculated. At the same time, the power consumption of the sub-area pump is calculated, and then the total power consumption of the irrigation system twin is calculated;

[0042] S4. Determine the operating mode of the pump in the current sub-region by controlling the status of the pump in the sub-region according to the actual water supply;

[0043] S5. Obtain environmental parameters through sensors and calculate power generation based on the clean energy system twin;

[0044] S6. Determine the power supply mode based on the power generation and the total power consumption; if the power generation is greater than or equal to the total power consumption, store or connect the excess power to the grid; if the power generation is less than the total power consumption, supplement the required power through the grid.

[0045] Preferably, the irrigation constraints include that the actual head of each pump in the sub-area must not be lower than the theoretical head, and the actual water supply in the sub-area must not be lower than the theoretical water supply in the sub-area.

[0046] Preferably, the calculation of the actual water supply is specifically expressed as follows:

[0047]

[0048] Among them, Q i_g is the actual water supply of each sub-area, z is the number of pumps in the sub-area, Q i_gz is the water supply of a single pump, and n is the total number of pumps;

[0049] The power consumption of the pump in the calculation sub-area is specifically expressed as follows:

[0050]

[0051] Among them, P i_g is the power consumption of the sub-area pump;

[0052] The total actual water supply is specifically expressed as follows:

[0053]

[0054] The calculation of the power consumption of each sub-area is specifically expressed as follows:

[0055]

[0056] Preferably, the minimum water consumption deviation is specifically expressed as follows:

[0057] min F1=|Q sum -Q i-sum |;

[0058] The minimum power consumption is specifically expressed as follows:

[0059]

[0060] Preferably, the scheme evaluation unit includes: evaluating the optimization scheme and the historical scheme and making a decision on the evaluated scheme. If the conditions are met, the control scheme is output; if not, the parameters are adjusted and the optimization calculation is performed again until the judgment conditions are met.

[0061] Beneficial effects of the present invention:

[0062] 1. This solution uses twin modeling of clean energy systems, irrigation systems, and agricultural systems. Using the data-driven digital twin platform, it achieves data mirroring, mapping reconstruction, information exchange, and simulation between virtual and physical entities. By monitoring crop water requirements and rationally adjusting the irrigation system's water supply and power generation system's supply model, it effectively achieves water-saving irrigation and power distribution, ensuring a better water environment for crops. This creates a system and platform that integrates monitoring, optimization, simulation, control, and operation and maintenance throughout the entire lifecycle. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 This is an overall block diagram of an irrigation digital twin system that combines agriculture and clean energy according to the present invention;

[0064] Figure 2 It is the optimization model simulation flow chart of the present invention;

[0065] Figure 3 This is a flowchart of the calculation process for optimizing the digital twin platform of the present invention. DETAILED DESCRIPTION

[0066] Example 1: Figure 1-Figure 3 As shown in the figure, an irrigation digital twin system for combining agriculture and clean energy includes:

[0067] Physical body, virtual body and digital twin platform; the physical body includes clean energy system, irrigation system and agricultural system for power generation; the twin includes clean energy system twin, irrigation system twin and agricultural system twin; the digital twin platform includes information system unit, data management unit, state database unit, optimization model unit, machine learning unit and scheme evaluation unit; the clean energy system, irrigation system and agricultural system are twin modeled through the digital twin platform to form a monitoring and control system, and the output of the irrigation system and the supply mode of the clean energy power generation system are adjusted according to the water demand of crops. At the same time, twin models of sub-regions are established according to different irrigation areas, and the crop model and irrigation model of each sub-region match each other.

[0068] The twin models here refer to the crop model and irrigation model mentioned in the latter sentence. The entire system is composed of multiple sub-region systems, each with its own twin model.

[0069] Physically, clean energy systems include solar and wind power generation systems. Solar power systems include photovoltaic panels, brackets, combiner boxes, controllers, inverters, batteries, and other devices; wind power systems include wind turbines, towers, controllers, inverters, batteries, and other devices. Both provide power for irrigation systems. Irrigation systems include pumps, motors, inverters, pipes, valves, sprinklers, brackets, and other supporting equipment, providing power and water for agricultural systems. Agricultural systems include crops, monitoring systems, fertilization devices, sensors, and other devices.

[0070] This paper uses digital twin technology to create digital twins of clean energy systems, irrigation systems, and agricultural systems. Using a digital twin platform as a framework, models as a foundation, and data as a driver, a simulation model is constructed, resulting in an irrigation digital twin system that integrates agriculture and clean energy. By monitoring the water needs of crops and rationally adjusting the water supply of the irrigation system and the supply mode of the power generation system, this system effectively achieves water-saving irrigation and power distribution, ensuring a better water environment for crops. This system and platform integrate monitoring, optimization, simulation, control, and operation and maintenance throughout the entire life cycle.

[0071] Specifically, the clean energy system twin is embodied through the clean energy system power generation model, including the solar power generation model and the wind power generation model;

[0072] The clean energy system power generation model is shown in the following formula:

[0073] P sys =P V +P W ;

[0074] Among them, P sysPower for clean energy generation system.

[0075] The solar power generation model is shown below:

[0076]

[0077] Among them, P v is the solar power generation power, P VN is the solar rated power, G is the actual radiation intensity, G N is the rated radiation intensity, η is the temperature coefficient of the photovoltaic panel, T is the actual temperature of the photovoltaic panel, T N is the rated temperature of the photovoltaic panel, γ is the shading coefficient;

[0078] The wind power generation model is shown in the following formula:

[0079]

[0080] Among them, P W is the wind power generation power, V W is the fan speed at a certain moment, P WN is the wind energy rated power, A1~A3 are the characteristic coefficients of the wind energy generator, V min is the minimum speed of wind power generation, V N is the rated speed of wind power generation, V max is the maximum speed of wind power generation;

[0081] The irrigation system twin is characterized by pump characteristics and pipeline characteristics; wherein the pump characteristics include the head characteristic curve and the power characteristic curve, and the pipeline characteristics include the pipeline characteristic curve.

[0082] Specifically, the lift characteristic curve is shown as follows:

[0083] H=a1Q 2 +a2Qk+a3k 2 ;

[0084] Where H is the pump head, a1 to a3 are the fitting coefficients of the head characteristic curve, Q is the pump flow rate, and k is the pump speed ratio;

[0085] The power characteristic curve is shown in the following formula:

[0086] P=b1Q 3 +b2Q 2 k 2 +b3Qk 3 +b4k 4 ;

[0087] Among them, b1~b4 are the fitting coefficients of the head characteristic curve;

[0088] The pipeline characteristic curve is shown in the following formula:

[0089] H sys =c1Q 2 +c2Q+c3;

[0090] Among them, c1~c3 are the fitting coefficients of the pipeline characteristic curve, H sys is the pipeline resistance;

[0091] The agricultural system twin is reflected by calculating the water supply of the irrigation system.

[0092] The water supply of the irrigation system is calculated as follows:

[0093] Q req =Q p +Q i +Q s -Q e -Q t -Q d ;

[0094] Among them, Q p is the precipitation, Q i is the water supply, Q s is the soil moisture content, Q e is the amount of water evaporated from the soil layer, Q t is the amount of water infiltrated into the soil layer, Q d is the soil drainage volume; Qreq is the water requirement for crop growth.

[0095] Specifically, the information system unit is a human-computer interaction and management platform; the data management unit manages and processes data from the database; the state database unit stores the operating data of the physical and virtual bodies; the optimization model unit is used to optimize the water demand conditions based on the water demand of crops and perform multi-objective optimization with minimum water consumption deviation and minimum power consumption as the optimization goals, and to obtain the adjustment plan through iterative solution of the optimization algorithm; the machine learning unit is used to learn historical plans and optimize the adjustment plan provided by the optimization model unit; the plan evaluation unit is used to screen the plans and evaluate the simulation results.

[0096] The water requirement of crops here is calculated by the following formula, Q req To calculate the water requirement for crop growth, we need to calculate Q i , and the required irrigation water volume Q is calculated i Here is a unified formula for the irrigation water quantity Q for each sub-area: i_j All are calculated using this formula. In the table below, i represents irrigation, and j is used to distinguish each area. i_jThis is a theoretical value. In practice, the water supply provided by the pump is not necessarily equal to this value. We use the actual water supply of the sub-area Q i_g To indicate that there is a constraint here (the actual value Q i_g > or = theoretical value Q i_j ).

[0097] Specifically, taking the swarm algorithm as an example, the adjustment solution is obtained through iterative optimization algorithm:

[0098] Step 1. Determine parameters and search space: After determining the optimization parameters, define the search space for each parameter. Here, lift is used as the optimization parameter.

[0099] Step 2: Initialize the population: Randomly generate a set of solutions X={x1,x2…x n}, x is the control parameter of each pump, and each pump is controlled by three parameters (start and stop o, speed ratio k, valve opening v), that is, each x is encoded by three numbers x1 = {o1, k1, v1}.

[0100] Step 3: Calculate the population fitness: that is, perform multi-objective optimization based on the minimum water consumption deviation and minimum power consumption function;

[0101] Step 4: Update the population to provide a new solution for the next calculation;

[0102] Step 5: Determine whether the algorithm termination condition is met: Determine whether the maximum number of iterations is reached. If not, continue iterating to find the optimal solution until the condition is met.

[0103] Step 6: Output the optimal value, obtain the Pareto solution set, and obtain the corresponding control plan.

[0104] The minimum water consumption deviation is specifically expressed as follows:

[0105] min F1=|Q sum -Q i-sum |;

[0106] The minimum power consumption is specifically expressed as follows:

[0107]

[0108] The optimization solution comes from two parts. One part comes from the solution given by the optimization model, which is the step in claim 9; the other part comes from learning previous solutions through machine learning, so as to find the nonlinear relationship between input variables and output values and perform predictive optimization more quickly. Their purpose is to find the control mode (start and stop, speed ratio and valve opening) of each pump to minimize the water consumption deviation and power consumption of the system. For engineering optimization, it is usually necessary to evaluate the solution. For example, there are multiple extreme values in multi-objective optimization, and the best solution is determined based on the Pareto front or related criteria. Due to the randomness of the optimization itself, more calculations are required to ensure the reliability of the results. When the solution does not meet the requirements, the relevant parameters of the machine learning model can be adjusted to improve its prediction accuracy, or the relevant parameters of the optimization model algorithm can be adjusted and then recalculated.

[0109] The optimization model unit includes the following steps:

[0110] S1. Obtain the water demand of crops in the agricultural system through sensors and transmit relevant data to the digital twin platform;

[0111] S2. Calculate the theoretical water supply for each sub-region based on the agricultural system twin;

[0112] S3. Based on the irrigation system twin, the actual water supply of each sub-area is calculated considering the irrigation constraints, and then the actual total water supply of the irrigation system twin is calculated. At the same time, the power consumption of the sub-area pump is calculated, and then the total power consumption of the irrigation system twin is calculated;

[0113] S4. Determine the operation mode of the current sub-region pump by controlling the status of the pump in the sub-region according to the actual water supply;

[0114] S5. Obtain environmental parameters through sensors and calculate power generation based on the clean energy system twin;

[0115] S6. Determine the power supply mode based on the power generation and total power consumption; if the power generation is greater than or equal to the total power consumption, store or connect the excess power to the grid; if the power generation is less than the total power consumption, supplement the required power through the grid.

[0116] Irrigation constraints include that the actual head of each pump in the sub-area must not be lower than the theoretical head, and the actual water supply in the sub-area must not be lower than the theoretical water supply in the sub-area.

[0117] The actual water supply is calculated as follows:

[0118]

[0119] Among them, Q i_g is the actual water supply of each sub-area, z is the number of pumps in the sub-area, Qi_gz is the water supply of a single pump, and n is the total number of pumps;

[0120] The power consumption of the sub-area pump is calculated as follows:

[0121]

[0122] Among them, P i_g is the power consumption of the sub-area pump;

[0123] The total actual water supply is specifically expressed as follows:

[0124]

[0125] The power consumption of each sub-area is calculated as follows:

[0126]

[0127] Among them, the solution evaluation unit includes: evaluating the optimization solution and the historical solution and making decisions on the evaluated solution. If the conditions are met, the control solution is output; if not, the parameters are adjusted and the optimization calculation is performed again until the judgment conditions are met.

[0128] The solution set obtained here is the Pareto optimal solution set obtained from multi-objective optimization. Evaluation and decision-making are performed based on the Pareto frontier optimal solution determination method. If the solution does not meet expectations, some structural parameters of the optimization algorithm (such as the population size and number of iterations) can be readjusted and the solution can be re-calculated until the conditions are met.

[0129] The technical point of this invention is to coordinate the balance among photovoltaic power generation, crop demand, and agricultural irrigation; taking crop demand as the prerequisite, photovoltaic power generation as the energy supply, and adjusting the relevant operations of the pump as the means, on the basis of regional satisfaction, considering the energy consumption and irrigation of the entire system, and striving to rely on digital twins and optimization methods to minimize the energy consumption of the entire system and achieve water-saving irrigation.

[0130] This solution uses twin modeling of clean energy, irrigation, and agricultural systems, and uses the data-driven digital twin platform to achieve data mirroring, mapping reconstruction, information exchange, and simulation between virtual and physical entities. By monitoring crop water requirements and rationally adjusting the irrigation system's water supply and power generation system's supply model, it effectively achieves water-saving irrigation and power distribution, ensuring a better water environment for crops. This creates a system and platform that integrates monitoring, optimization, simulation, control, and operation and maintenance throughout the entire lifecycle.

Claims

1. An irrigation digital twin system that combines agriculture and clean energy, characterized by: Including physical body, virtual body and digital twin platform; The physical bodies include clean energy systems for power generation, irrigation systems, and agricultural systems; The twins include a clean energy system twin, an irrigation system twin, and an agricultural system twin; The digital twin platform includes an information system unit, a data management unit, a state database unit, an optimization model unit, a machine learning unit, and a solution evaluation unit; The digital twin platform is used to perform twin modeling of the clean energy system, irrigation system, and agricultural system to form a monitoring and control system. The output of the irrigation system and the supply mode of the clean energy power generation system are adjusted according to the water demand of crops. At the same time, twin models of sub-regions are established according to different irrigation areas, and the crop model and irrigation model of each sub-region are matched with each other.

2. The irrigation digital twin system for combining agriculture and clean energy according to claim 1 is characterized in that: The clean energy system twin is embodied by a clean energy system power generation model, including a solar power generation model and a wind power generation model; The irrigation system twin is characterized by pump characteristics and pipeline characteristics; wherein the pump characteristics include a head characteristic curve and a power characteristic curve, and the pipeline characteristics include a pipeline characteristic curve; The agricultural system twin is embodied by calculating the water supply of the irrigation system.

3. The irrigation digital twin system for combining agriculture and clean energy according to claim 2, characterized in that: The solar power generation model is specifically shown as follows: Among them, P v is the solar power generation power, P VN is the solar rated power, G is the actual radiation intensity, G N is the rated radiation intensity, η is the temperature coefficient of the photovoltaic panel, T is the actual temperature of the photovoltaic panel, T N is the rated temperature of the photovoltaic panel, γ is the shading coefficient; The wind power generation model is specifically shown in the following formula: Among them, P W is the wind power generation power, V W is the fan speed at a certain moment, P WN is the wind energy rated power, A1~A3 are the characteristic coefficients of the wind energy generator, V min is the minimum speed of wind power generation, V N is the rated speed of wind power generation, V max is the maximum speed of wind power generation; The clean energy system power generation model is specifically shown in the following formula: P sys =P V +P W ; Among them, P sys Power for clean energy generation system.

4. The irrigation digital twin system for combining agriculture and clean energy according to claim 2, characterized in that: The lift characteristic curve is specifically shown in the following formula: <h2 style=";text-align:left;direction:ltr">H=a1Q<h2 style=";text-align:left;direction:ltr"> 2 <h2 style=";text-align:left;direction:ltr"> +a2Qk+a3k<h2 style=";text-align:left;direction:ltr"> 2 <h2 style=";text-align:left;direction:ltr"> ; Where H is the pump head, a1 to a3 are the fitting coefficients of the head characteristic curve, Q is the pump flow rate, and k is the pump speed ratio; The power characteristic curve is specifically shown in the following formula: P=b1Q 3 +b2Q 2 k 2 +b3Qk 3 +b4k 4 ; Among them, b1~b4 are the fitting coefficients of the head characteristic curve; The pipeline characteristic curve is specifically shown in the following formula: H sys =c1Q 2 +c2Q+c3; Among them, c1~c3 are the fitting coefficients of the pipeline characteristic curve, H sys is the pipeline resistance; The calculation of the water supply of the irrigation system is specifically shown in the following formula: Q req =Q p +Q i +Q s -Q e -Q t -Q d ; Among them, Q p is the precipitation, Q i is the water supply, Q s is the soil moisture content, Q e is the amount of water evaporated from the soil layer, Q t is the amount of water infiltrated into the soil layer, Q d is the soil drainage volume; Qreq is the water requirement for crop growth.

5. The irrigation digital twin system for combining agriculture and clean energy according to claim 1, characterized in that: The information system unit is a human-computer interaction and management platform; the data management unit manages and processes data from the database; the state database unit stores the operating data of the physical body and the virtual body; the optimization model unit is used to optimize the water demand conditions according to the water demand of crops and perform multi-objective optimization with minimum water consumption deviation and minimum power consumption as optimization goals, and to obtain the adjustment plan through iterative solution of the optimization algorithm; the machine learning unit is used to learn historical plans and optimize the adjustment plan provided by the optimization model unit; the plan evaluation unit is used to screen the plans and evaluate the simulation results.

6. The irrigation digital twin system for combining agriculture and clean energy according to claim 5, characterized in that: The optimization model unit comprises the following steps: S1. Obtain the water demand of crops in the agricultural system through sensors and transmit relevant data to the digital twin platform; S2. Calculate the theoretical water supply for each sub-region based on the agricultural system twin; S3. Based on the irrigation system twin, the actual water supply of each sub-area is calculated considering the irrigation constraints, and then the actual total water supply of the irrigation system twin is calculated. At the same time, the power consumption of the sub-area pump is calculated, and then the total power consumption of the irrigation system twin is calculated; S4. Determine the operating mode of the pump in the current sub-region by controlling the status of the pump in the sub-region according to the actual water supply; S5. Obtain environmental parameters through sensors and calculate power generation based on the clean energy system twin; S6. Determine the power supply mode based on the power generation and the total power consumption; if the power generation is greater than or equal to the total power consumption, store or connect the excess power to the grid; if the power generation is less than the total power consumption, supplement the required power through the grid.

7. The irrigation digital twin system for combining agriculture and clean energy according to claim 6, characterized in that: The irrigation constraints include that the actual head of each pump in the sub-area must not be lower than the theoretical head, and the actual water supply in the sub-area must not be lower than the theoretical water supply in the sub-area.

8. The irrigation digital twin system for combining agriculture and clean energy according to claim 6, characterized in that: The calculation of the actual water supply is specifically expressed as follows: Among them, Q i_g is the actual water supply of each sub-area, z is the number of pumps in the sub-area, Q i_gz is the water supply of a single pump, and n is the total number of pumps; The power consumption of the pump in the calculation sub-area is specifically expressed as follows: Among them, P i_g is the power consumption of the sub-area pump; The total actual water supply is specifically expressed as follows: The calculation of the power consumption of each sub-area is specifically expressed as follows:

9. The irrigation digital twin system for combining agriculture and clean energy according to claim 5, characterized in that: The minimum water consumption deviation is specifically expressed as follows: minF1=|Q sum -Q i -s um |; The minimum power consumption is specifically expressed as follows:

10. The irrigation digital twin system for combining agriculture and clean energy according to claim 5, characterized in that: The scheme evaluation unit includes: evaluating the optimized scheme and the historical scheme and making a decision on the evaluated scheme. If the conditions are met, the control scheme is output; if not, the parameters are adjusted and the optimization calculation is performed again until the judgment conditions are met.

Images