Digital twin sprinkling irrigation optimization system and method for tea-light complementation

Abstract

The invention discloses a digital twin sprinkling irrigation optimization system and method for tea and light complementation, and belongs to the technical field of sprinkling irrigation optimization. A digital twinborn mirror image platform in the system is used for constructing a digital twinborn model and a photovoltaic system digital twinborn model, and the digital twinborn model comprises a three-dimensional model of a tea garden and a physical model of the tea garden; the photovoltaic system sub-model in the system is used for simulating the generating capacity and the working efficiency of the photovoltaic system in the tea garden under different weather conditions; a data acquisition module in the system acquires tea garden data based on a sensor deployed in a tea garden; a strategy generation module in the system predicts a tea growth state and irrigation requirements, predicts a power generation trend of a photovoltaic system and determines an irrigation strategy based on tea garden data, a digital twinborn model and a digital twinborn model of the photovoltaic system; a sprinkling irrigation regulation and control module in the system executes an irrigation task based on the irrigation strategy; the interaction module in the system is used for interacting with a user. According to the invention, water saving, emission reduction and intelligent management are realized.

Description

Technical Field

[0001] The present application relates to the technical field of sprinkler irrigation optimization, and particularly relates to a digital twin sprinkler irrigation optimization system and method for tea-light complementary. Background Art

[0002] Tea-light complementary is a new model that combines photovoltaic power generation with tea planting. In terms of water use, the main irrigation method in the tea-light complementary model is still traditional manual irrigation, which has low irrigation accuracy and water resource utilization efficiency, is difficult to achieve on-demand irrigation, results in water resource waste, and has a low degree of intelligence. It mainly relies on manual operation, causing a large labor intensity and increasing labor costs. Summary of the Invention

[0003] The present application provides a digital twin sprinkler irrigation optimization system and method for tea-light complementary, aiming to solve the technical problems of poor irrigation accuracy and low water resource utilization efficiency in tea gardens.

[0004] The first aspect of the present application proposes a digital twin sprinkler irrigation optimization system for tea-light complementary, and the system includes:

[0005] A digital twin mirror platform, a data acquisition module, a strategy generation module, a sprinkler irrigation control module, and an interaction module;

[0006] The digital twin mirror platform is used to construct a digital twin model and a digital twin model of the photovoltaic system. The digital twin model includes a three-dimensional solid model of the tea garden and a physical model of the tea garden; the three-dimensional solid model of the tea garden is constructed based on the tea garden GIS data and the UAV aerial image, simulating the terrain, soil, and vegetation of the tea garden; the physical model of the tea garden integrates multiple sub-models to simulate the change process of the physical environment of the tea garden, and the sub-models include a soil moisture migration sub-model and a crop growth sub-model; the photovoltaic system sub-model is used to simulate the power generation and working efficiency of the photovoltaic system in the tea garden under different weather conditions;

[0007] The data acquisition module acquires tea garden data based on sensors deployed in the tea garden. The tea garden data includes soil data, moisture data, and real-time status data of the photovoltaic system;

[0008] The strategy generation module predicts the tea growth state and irrigation demand, predicts the power generation trend of the photovoltaic system, and determines the irrigation strategy based on the tea garden data, the digital twin model, and the digital twin model of the photovoltaic system;

[0009] The sprinkler irrigation control module executes the irrigation task based on the irrigation strategy;

[0010] The interaction module is used to interact with users.

[0011] According to the system of the first aspect of the present application, the digital twin mirror platform includes a data collection and processing module, a digital twin model construction module, and a digital twin model integration and application module;

[0012] The data collection and processing module obtains relevant data of the tea garden and the photovoltaic system. The relevant data includes the topographic features, soil types, vegetation distribution, crop growth cycles, irrigation records, meteorological condition data of the tea garden, as well as the layout, performance parameters, and historical power generation data of the photovoltaic modules. The meteorological condition data includes rainfall, temperature, and humidity. The relevant data is processed to obtain processed relevant data;

[0013] The digital twin model construction module constructs a three-dimensional model of the tea garden, a physical model of the tea garden, and a photovoltaic module sub-model based on the processed relevant data. Among them, the three-dimensional model of the tea garden is constructed based on the tea garden GIS data and UAV aerial images, simulating the terrain, soil, and vegetation of the tea garden. The physical model of the tea garden integrates multiple sub-models to simulate the change process of the physical environment of the tea garden. The sub-models include a soil moisture migration sub-model and a crop growth sub-model. Each photovoltaic module sub-model is constructed based on the electrical characteristics and physical structure of the photovoltaic module;

[0014] The digital twin model integration and application module is used to integrate the three-dimensional model of the tea garden and the physical model of the tea garden to form a digital twin model; integrate the digital twin model and the digital twin model of the photovoltaic system to form an overall digital twin model; based on the layout and connection method of the photovoltaic system, combine each photovoltaic module sub-model to form a digital twin model of the photovoltaic system. The digital twin model of the photovoltaic system is used to simulate the power generation and working efficiency of the photovoltaic system in the tea garden under different weather conditions; based on the electrical data and meteorological condition data of the photovoltaic modules instantaneously collected by the data collection and processing module, the overall digital twin model is updated and optimized.

[0015] According to the system of the first aspect of the present application, the digital twin model construction module also constructs a growth physical model of tea leaves, and the growth physical model is:

[0016]

[0017] Among them, W(t) is the value of the biomass of tea leaves at time t, η is the synthetic metabolism constant of tea leaves, κ is the catabolism constant of tea leaves, t is in days, and the biomass of tea leaves includes the dry weight, fresh leaf weight, or the number of leaves of tea leaves.

[0018] According to the system of the first aspect of the present application, the data acquisition module includes a data collection sub-module and a data integration sub-module;

[0019] The data acquisition sub-module obtains the tea garden data sensed by each sensor in the tea garden based on wireless communication technology, and sends the tea garden data to the interaction module and the data integration sub-module;

[0020] The data integration sub-module preprocesses the tea garden data, integrates the preprocessed tea garden data, and sends the integrated tea garden data to the policy generation module;

[0021] The policy generation module inputs the integrated tea garden data into the digital twin model to obtain the tea growth trend and the photovoltaic power generation trend; performs machine learning on the integrated tea garden data to predict the tea irrigation demand, and determines the irrigation strategy based on the tea growth trend, the photovoltaic power generation trend, the tea growth state, and the irrigation demand.

[0022] According to the system of the first aspect of the present application, the method for determining the irrigation strategy includes:

[0023] Construct a target function for the energy consumption of the photovoltaic tea garden, and the target function for the energy consumption of the photovoltaic tea garden is:

[0024] E total = w × [C tea × P tea (x1, x2, x3, x4) - C irr (x1, x2, x3, x4)] + (1 + w) × [C pv × P pv (y1, y2, y3) - C pv-maint (y1, y2, y3)]

[0025] In the formula: E total is the energy consumption of the photovoltaic tea garden; w is the weight factor, 0 ≤ w ≤ 1; x1, x2, x3, x4 are the irrigation electricity consumption, irrigation water consumption, irrigation frequency, and irrigation method respectively; y1, y2, y3 are the installation angle, orientation, and cleaning frequency of the photovoltaic panels respectively; P tea is the tea yield; P pv is the power generation of the photovoltaic power station composed of photovoltaic modules; C tea is the tea market price; C pv is the photovoltaic grid-connected electricity price; C irr is the irrigation cost, including water resource cost and electricity cost; C pv-maint is the operation and maintenance cost of the photovoltaic power station;

[0026] Generate a number of candidate irrigation strategies based on the tea growth trend, the photovoltaic power generation trend, and the tea irrigation demand; construct a particle swarm, and use the particle swarm algorithm to determine the irrigation strategy.

[0027] The second aspect of the present application proposes a digital twin irrigation optimization method for tea-light complementary. The method is based on the digital twin irrigation optimization system for tea-light complementary as described above, and the method includes:

[0028] Step S1: Obtain the tea garden data of the sensors deployed in the tea garden;

[0029] Step S2: The digital twin irrigation optimization system for tea-light complementary generates an irrigation plan based on the tea garden data, and formulates an irrigation task based on the irrigation plan; the intelligent valve irrigates based on the irrigation task, and adjusts the irrigation water volume and water flow speed during the irrigation process based on the irrigation task.

[0030] The third aspect of the present application proposes a computer-readable storage medium, in which multiple instructions are stored; the multiple instructions are used to be loaded and executed by a processor to perform the method as described in the second aspect of the present application.

[0031] The fourth aspect of the present application proposes an electronic device, characterized in that the electronic device includes:

[0032] A processor for executing multiple instructions;

[0033] A memory for storing multiple instructions;

[0034] Among them, the multiple instructions are used to be stored by the memory and loaded and executed by the processor to perform the method as described in the second aspect of the present application.

[0035] The beneficial technical effects brought by the present application include:

[0036] (1) The present application combines digital twin technology with photovoltaic tea gardens, can monitor soil humidity, meteorological conditions and tea tree growth status in real time, thereby accurately calculating the water demand of tea trees, optimizing the irrigation mode, and realizing on-demand irrigation. It avoids water resource waste in the traditional irrigation mode and significantly improves the water resource utilization efficiency.

[0037] (2) The present application optimizes the irrigation strategy through digital twin technology, realizing water conservation, emission reduction and intelligent management in the field of agricultural irrigation.

[0038] (3) The present application uses digital twin technology to realize real-time monitoring and intelligent optimal allocation of water and light in the tea garden, thereby maximizing the resource utilization efficiency. Through precise irrigation management, water resource waste can be significantly reduced, production costs can be reduced, the utilization efficiency of water resources and light can be significantly improved, waste can be reduced. At the same time, the tea growth environment is improved through precise irrigation and light management, and the negative impact on the environment is reduced by reducing the over-reliance on water resources. Description of the Drawings

[0039] Figure 1 Schematic diagram of the structure of a digital twin sprinkler irrigation optimization system for tea-light complementary in this application;

[0040] Figure 2 Schematic diagram of the construction method of the digital twin mirror platform in this application;

[0041] Figure 3 Schematic diagram of the construction method of the data collection and processing module in this application;

[0042] Figure 4 Schematic diagram of the execution method of the strategy generation module in this application;

[0043] Figure 5 Schematic diagram of the execution method of the sprinkler irrigation control module in this application;

[0044] Figure 6 Schematic diagram of the function of the interaction module in this application. Detailed implementation mode

[0045] The following combines the drawings and embodiments to describe this application in detail.

[0046] As Figure 1 shown, this application proposes a digital twin sprinkler irrigation optimization system for tea-light complementary, including:

[0047] A digital twin mirror platform, a data acquisition module, a strategy generation module, a sprinkler irrigation control module, and an interaction module;

[0048] The digital twin mirror platform is used to construct a digital twin model and a digital twin model of the photovoltaic system. The digital twin model includes a three-dimensional model of the tea garden and a physical model of the tea garden; the three-dimensional model of the tea garden is constructed based on the GIS data of the tea garden and the UAV aerial photography images, simulating the terrain, soil, and vegetation of the tea garden; the physical model of the tea garden integrates multiple sub-models to simulate the change process of the physical environment of the tea garden. The sub-models include a soil moisture movement sub-model and a crop growth sub-model; the photovoltaic system sub-model is used to simulate the power generation and working efficiency of the photovoltaic system in the tea garden under different weather conditions;

[0049] The data acquisition module acquires tea garden data based on sensors deployed in the tea garden. The tea garden data includes soil data, moisture data, and real-time status data of the photovoltaic system;

[0050] The strategy generation module predicts the growth status and irrigation requirements of tea leaves and the power generation trend of the photovoltaic system based on the tea garden data, the digital twin model, and the digital twin model of the photovoltaic system, and determines the irrigation strategy;

[0051] The sprinkler irrigation control module executes the irrigation task based on the irrigation strategy;

[0052] The interaction module is used to interact with users.

[0053] Further, as Figure 2 shown, the digital twin mirror platform includes a data collection and processing module, a digital twin model construction module, and a digital twin model integration and application module.

[0054] As Figure 3 shown, the data collection and processing module acquires relevant data of the tea garden and the photovoltaic system. The relevant data includes the topographic features, soil types, vegetation distribution, crop growth cycles, irrigation records, meteorological condition data of the tea garden, as well as the layout, performance parameters, and historical power generation data of the photovoltaic modules. The meteorological condition data includes rainfall, temperature, humidity, and wind speed. The relevant data is processed to obtain processed relevant data. In this application, for example, after preprocessing the relevant data and then performing security and privacy protection processing, it can also be uploaded to a data center or a cloud platform.

[0055] The digital twin model construction module constructs a three-dimensional solid model of the tea garden, a physical model of the tea garden, and a photovoltaic module sub-model based on the processed relevant data. Among them, the three-dimensional solid model of the tea garden is constructed based on the tea garden GIS data and drone aerial images, simulating the terrain, soil, and vegetation of the tea garden. The physical model of the tea garden integrates multiple sub-models to simulate the change process of the physical environment of the tea garden. The sub-models include a soil moisture migration sub-model and a crop growth sub-model. Each photovoltaic module sub-model is constructed based on the electrical characteristics and physical structure of the photovoltaic module.

[0056] The digital twin model integration and application module is used to integrate the three-dimensional solid model of the tea garden and the physical model of the tea garden to form a digital twin model; integrate the digital twin model and the digital twin model of the photovoltaic system to form an overall digital twin model; based on the layout and connection method of the photovoltaic system, combine each photovoltaic module sub-model to form a digital twin model of the photovoltaic system. The digital twin model of the photovoltaic system is used to simulate the power generation amount and working efficiency of the photovoltaic system in the tea garden under different weather conditions; based on the electrical data and meteorological condition data of the photovoltaic modules instantaneously collected by the data collection and processing module, update and optimize the overall digital twin model.

[0057] In this application, the photovoltaic module sub-model can describe the power generation performance of the photovoltaic module under different light conditions and can simulate the power generation amount and efficiency of the photovoltaic system under different weather conditions. The overall digital twin model can comprehensively consider the interaction relationship between the tea garden environment and the photovoltaic system, provide comprehensive data support and decision-making basis for optimizing the irrigation strategy and improving the performance of the photovoltaic system, and dynamically adjust the irrigation plan and the operation strategy of the photovoltaic system by real-time monitoring and analyzing the model data to achieve the efficient utilization of water resources in the tea garden and the stable operation of the photovoltaic system. The electrical data of the photovoltaic module is one of the performance parameters of the photovoltaic module.

[0058] Furthermore, the digital twin model construction module also constructs a growth physical model of tea leaves, and the growth physical model is:

[0059]

[0060] where W(t) is the value of the biomass of tea leaves at time t, η is the anabolism constant of tea leaves, κ is the catabolism constant of tea leaves, and t is in days. The biomass of the tea leaves includes the dry weight, fresh leaf weight, or the number of leaves of the tea leaves.

[0061] A variety of sensors are deployed in the tea garden. The soil humidity sensor is deployed in the irrigation area of the tea garden to collect soil humidity data in real time; the meteorological monitoring device is deployed in the center of the tea garden to collect the rainfall, temperature, humidity, light intensity, and wind speed of the tea garden; cameras are deployed at the boundary of the tea garden to obtain images of the tea leaves; the photovoltaic module sensor is deployed on the photovoltaic module to monitor the temperature and light conditions of the photovoltaic module; a data acquisition device is deployed in the photovoltaic system to obtain the power generation, voltage, and current of the photovoltaic system.

[0062] The data acquisition module includes a data collection sub-module and a data integration sub-module.

[0063] The data collection sub-module obtains the tea garden data sensed by the various sensors in the tea garden based on wireless communication technology, and sends the tea garden data to the interaction module and the data integration sub-module.

[0064] The data integration sub-module preprocesses the tea garden data, integrates the preprocessed tea garden data, and sends the integrated tea garden data to the policy generation module.

[0065] In this application, the data acquisition sub-module monitors the data sources of the tea garden environment and the photovoltaic system. The soil moisture sensor collects soil moisture data in real time to ensure the accuracy of irrigation. These sensors usually have high precision (such as an error of ±3%), and can accurately reflect the soil moisture status. Meteorological data is crucial for evaluating the lighting conditions of the tea garden and predicting irrigation requirements. By combining image recognition technology with cameras, the growth status and leaf surface humidity of the tea leaves are monitored to indirectly reflect the water demand of the crops. The data collected by the photovoltaic module sensors is used to evaluate the power generation efficiency and health status of the modules. Through the built-in data acquisition function of the inverter or an external data acquisition device, key parameters such as the power generation, voltage, and current of the photovoltaic system are obtained in real time. The data acquisition technology uses Internet of Things technology and wireless communication technologies such as LoRa, NB-IoT, and Zigbee to transmit data to the data center in real time. The above technologies have the characteristics of low power consumption and wide coverage, and are suitable for deployment in the vast areas of the tea garden. A remote monitoring system platform is built to view the operation data of the tea garden environment and the photovoltaic system in real time through a web page or a mobile APP, realizing remote monitoring and management.

[0066] The data integration sub-module preprocesses the data. By data cleaning, duplicate, abnormal, and missing data records are removed to ensure the accuracy and integrity of the data. For example, for the data of the soil moisture sensor, abnormal values outside the normal range need to be excluded. Using data integration, the data from different sensors are integrated according to the time stamp to form a unified data format, which includes integrating the tea garden environment data and the photovoltaic system data into the same database. According to the analysis requirements, operations such as unit conversion and format adjustment are performed on the data. For example, the light intensity data is converted from lux to watts per square meter to compare with the power generation efficiency of the photovoltaic modules; a dedicated data center is built or a cloud computing platform is used to provide data storage, processing, and analysis services. The data center should have characteristics such as high availability, scalability, and security, and real-time data stream processing tools such as Kafka and Flume are used to instantaneously process and analyze the collected data. This includes operations such as data filtering, aggregation, and conversion, providing basic data for the subsequent construction of the digital twin model and decision support; encrypting the storage and transmission of sensitive data to prevent data leakage and illegal access, and using the AES encryption algorithm to encrypt sensitive fields in the database. Implement strict access control policies to limit the access rights of different users to the data, formulate and implement privacy protection policies to ensure compliance with relevant laws, regulations, and privacy protection principles during the data acquisition and integration process. Clearly inform users of information such as the purpose of data collection, usage methods, and protection measures.

[0067] The strategy generation module inputs the integrated tea garden data into the overall digital twin model to obtain the tea growth trend and photovoltaic power generation trend; performs machine learning on the integrated tea garden data to predict the tea irrigation demand, and determines the irrigation strategy based on the tea growth trend, photovoltaic power generation trend, tea growth status, and irrigation demand.

[0068] Further, the ways to determine the irrigation strategy include:

[0069] Construct a target function for the energy consumption of the photovoltaic tea garden. The target function for the energy consumption of the photovoltaic tea garden is:

[0070] E total = w × [C tea × P tea (x1, x2, x3, x4) - C irr (x1, x2, x3, x4)] + (1 + w) × [C pv × P pv (y1, y2, y3) - C pv-maint (y1, y2, y3)]

[0071] In the formula: E total is the energy consumption of the photovoltaic tea garden; w is the weight factor, 0 ≤ w ≤ 1; x1, x2, x3, x4 are the irrigation power consumption, irrigation water consumption, irrigation frequency, and irrigation method respectively; y1, y2, y3 are the installation angle, orientation, and cleaning frequency of the photovoltaic panels respectively; P tea is the tea yield; P pv is the power generation of the photovoltaic power station composed of photovoltaic modules; C tea is the tea market price; C pv is the photovoltaic grid-connected electricity price; C irr is the irrigation cost, including water resource cost and electricity cost; C pv-maint is the operation and maintenance cost of the photovoltaic power station;

[0072] Generate several candidate irrigation strategies based on the tea growth trend, photovoltaic power generation trend, and tea irrigation demand; construct a particle swarm and use the particle swarm algorithm to determine the irrigation strategy.

[0073] As Figure 4 shown, in this application, the strategy generation module uses artificial intelligence technologies such as machine learning and data mining to deeply analyze the data. Based on soil humidity and light intensity, train a classification or regression model to predict the growth status or irrigation demand of tea; by analyzing the historical power generation data of the photovoltaic system, identify the key factors affecting power generation efficiency and predict the future power generation trend. Based on the analysis results for decision-making, the strategy generation module will evaluate the factors affecting the irrigation strategy according to the analysis results, generate multiple candidate irrigation strategies. Then select the irrigation strategy from the candidate irrigation strategies.

[0074] The sprinkler irrigation control module includes a control sub-module and an actuator sub-module.

[0075] The control sub-module generates an irrigation plan based on the irrigation strategy or user instructions, formulates irrigation tasks based on the irrigation plan, and interacts with the interaction module; the actuator sub-module includes intelligent valves, sprinklers, water pumps, and pipelines. The intelligent valves open at the time specified by the irrigation strategy or when the soil moisture is lower than a preset threshold to start irrigation.

[0076] In this application, for example, when it is detected that the soil moisture is lower than the set threshold, the intelligent valve automatically opens to start irrigation. High-efficiency sprinklers (such as micro-sprinklers or drip irrigation heads) are used to directly deliver water to the roots of plants, reducing water evaporation and loss. The flow rate of the water pump is adjusted to ensure sufficient water supply during irrigation and avoid soil erosion or uneven sprinkling caused by excessive water pressure. According to the needs of plants, frequent small-scale irrigation (such as multiple times a day) is set to avoid plant damage caused by soil drought. If the soil moisture of the plants remains within an appropriate range, based on the soil moisture data, the intelligent valve can be automatically switched on and off as needed to keep the soil humidity within the normal range. Uniformly sprinkling sprinklers are used to ensure uniform irrigation and avoid local over-drying or over-wetting. Select appropriate sprinkler angles and spraying radii, and set a fixed irrigation frequency (such as irrigating 2-3 times a week) according to the plant growth cycle and weather conditions to avoid over-irrigation. As Figure 5 As shown, in this application, the sprinkler irrigation control module starts irrigation by the actuator sub-module according to the irrigation strategy.

[0077] The interaction module is used to obtain the tea garden data obtained by the data acquisition module, obtain the irrigation tasks formulated by the sprinkler irrigation control module, and perform data analysis and issue user instructions.

[0078] The interaction module has four functions: real-time monitoring, remote control, irrigation plan formulation, and data analysis and reporting. Users can intuitively understand key parameters such as soil humidity, temperature, meteorological conditions, and crop growth status of the farmland through real-time data charts and images on the interaction module; users can remotely control the on / off of irrigation equipment, water volume adjustment, etc. through control buttons or sliders on the interaction module, supporting multiple irrigation modes such as timed irrigation, cyclic irrigation, and remote irrigation, and users can flexibly select according to actual needs; users can formulate detailed irrigation plans according to the crop growth cycle and environmental conditions through the irrigation plan formulation tool on the interaction module, and the platform supports the saving and sharing functions of irrigation plans. Users can save their irrigation plans for future use or share them with other users; the interaction module supports the analysis and statistics of historical data to generate irrigation effect reports and crop growth reports, etc. Users can customize the content and format of the reports through the report generation tool on the platform to better understand the irrigation effect and crop growth status.

[0079] This application provides a digital twin sprinkler irrigation optimization method for tea-light complementary. Based on the digital twin sprinkler irrigation optimization system for tea-light complementary as described above, the method includes:

[0080] Step S1: Obtain the tea garden data of the sensors deployed in the tea garden;

[0081] Step S2: The digital twin sprinkler irrigation optimization system for tea-light complementary generates an irrigation plan based on the tea garden data and formulates an irrigation task based on the irrigation plan; the intelligent valve irrigates based on the irrigation task and adjusts the irrigation water volume and water flow speed during the irrigation process based on the irrigation task.

[0082] This application provides a specific embodiment of a digital twin sprinkler irrigation optimization method for tea-light complementary.

[0083] The digital twin mirror platform consists of a data collection and processing module, a model construction module, and a model integration and application module. Among them, the data collection and processing module comprehensively collects relevant data of the tea garden and the photovoltaic system by using various technical means such as UAV aerial photography, satellite remote sensing, GIS system, and Internet of Things sensors. These data include, but are not limited to, the topography, soil type, vegetation distribution, crop growth cycle, irrigation records, meteorological conditions (such as rainfall, temperature, humidity, wind speed, etc.) of the tea garden, as well as the layout, performance parameters, historical power generation data of the photovoltaic modules, etc.; The model construction is divided into the digital twin model of the tea garden and the digital twin model of the photovoltaic system. Both models use ArcGIS Pro for geometric modeling to obtain topographic maps, soil maps, vegetation cover maps, sunshine data, etc. of the tea garden, as well as the technical parameters and installation requirements of the photovoltaic system. Using the data management tools of ArcGIS Pro, various types of geospatial data collected are sorted out to ensure consistent data formats and unified coordinate systems. If the data comes from different coordinate systems or formats, data conversion and projection are required to ensure that all data is within the same geospatial framework. Using the 3D modeling function of ArcGIS Pro, a 3D terrain model of the tea garden is constructed based on the topographic map and vegetation cover map, and the layout and installation angle of the photovoltaic panels are designed according to the technical parameters and installation requirements of the photovoltaic system. Using the mapping and visualization functions of ArcGIS Pro, 3D visualization models, light simulation diagrams, shadow analysis diagrams, etc. of the tea garden and the photovoltaic system are generated. As the tea garden and the photovoltaic system change and new data is obtained, the geospatial data and related parameters in ArcGIS Pro are updated regularly. Under the modeling conditions of the foregoing geometric model, the growth of tea leaves is simulated in real time to mirror the plant digital model. The simulation is carried out through WOFOST. Historical meteorological data collected by the weather station, including daily average temperature, precipitation, sunshine hours, relative humidity, etc., and soil parameters are set by the soil depth, soil texture, water holding capacity, organic matter content, etc. collected by the soil sensor. The crop information of the tea is set. A suitable tea tree growth model is selected in the WOFOST model, and relevant growth parameters are set. The different growth stages of the tea tree are defined, such as germination, seedling, mature tree, and peak production period, and the growth parameters of each stage are set. The WOFOST model is started for simulation operation to generate dynamic data of the tea tree growth. Usually, the output includes growth rate, yield prediction, dry matter weight, leaf area index, etc. The simulation results of the model are compared with the field observation data to evaluate the accuracy and reliability of the model; The photovoltaic power generation simulation is carried out using PVsyst. Create a new project in the PVSyst software, input the project name, location, and relevant basic information, import the measured weather station data, select "fixed photovoltaic system", and input the technical parameters of the photovoltaic modules, including rated power, open circuit voltage, short circuit current, efficiency, etc.It is also necessary to set the rated power and efficiency parameters of the inverter, define the tilt angle and azimuth angle of the photovoltaic module to adapt to the local sunlight conditions, design the layout of the photovoltaic array, including the arrangement, spacing and quantity of components, ensure compliance with the site conditions and design requirements, start the simulation, and the software will calculate the power generation, performance ratio (PR), system efficiency, etc. of the photovoltaic system according to the input meteorological data and system parameters. Integrate the aforementioned digital twin model of the tea garden and the digital twin model of the photovoltaic system through a program written in Python. The program calls the real-time measured data for numerical simulation to form a complete system-level digital twin model. This model will be able to comprehensively consider the interaction relationship between the tea garden environment and the photovoltaic system, provide comprehensive data support and decision-making basis for optimizing the irrigation strategy and improving the performance of the photovoltaic system. Dynamically adjust the irrigation plan and the operation strategy of the photovoltaic system by real-time monitoring and analyzing the model data to achieve the efficient utilization of water resources in the tea garden and the stable operation of the photovoltaic system.

[0084] The data acquisition module consists of a data collection sub-module and a data integration sub-module. The data collection sub-module monitors the data sources of the tea garden environment and the photovoltaic system. Deploy soil moisture sensors in key areas of the tea garden, such as near the irrigation area, to collect soil moisture data in real time to ensure the accuracy of irrigation. These sensors usually have high precision (such as an error of ±3%), and can accurately reflect the soil moisture condition. Install a weather station in the center or representative area of the tea garden to collect meteorological data such as rainfall, temperature, humidity, light intensity, wind speed, etc. The data is crucial for evaluating the light conditions of the tea garden and predicting irrigation requirements. Monitor the growth status and leaf surface humidity of the tea leaves through image recognition technology combined with cameras to indirectly reflect the water demand of the crops. Install photovoltaic module sensors on the photovoltaic modules to monitor the temperature, light reception, etc. of the modules. The data is used to evaluate the power generation efficiency and health status of the modules. Obtain key parameters such as the power generation, voltage, and current of the photovoltaic system in real time through the built-in data collection function of the inverter or an external data collector. The data collection technology uses Internet of Things technology and utilizes wireless communication technologies such as LoRa, NB-IoT, Zigbee, etc. to transmit the sensor data to the data center in real time. The above technologies have the characteristics of low power consumption and wide coverage, and are suitable for deployment in the vast areas of the tea garden. Build a remote monitoring system platform to view the operation data of the tea garden environment and the photovoltaic system in real time through a web page or a mobile APP to achieve remote monitoring and management.

[0085] The data integration sub-module preprocesses the data, removes duplicate, abnormal, and missing data records through data cleaning to ensure the accuracy and integrity of the data. For example, for soil moisture sensor data, abnormal values outside the normal range need to be removed. Data integration is used to integrate data from different sensors according to the timestamp to form a unified data format. It is determined that all date data should use the "YYYY-MM-DD" format, all numerical data should use floating-point numbers with two decimal places, and all text data should use UTF-8 encoding. The pandas library is used for data conversion and cleaning. Date strings are converted into date-type data, numerical strings are converted into floating-point-type data, and the converted data is saved as a new CSV file, ensuring that all data conforms to the unified data format specification. A MySQL database is created to provide data storage, processing, and analysis services. Real-time data stream processing tools such as Kafka and Flume are used to immediately process and analyze the collected data. This includes operations such as data filtering, aggregation, and transformation, providing basic data for subsequent digital twin model construction and decision support; encrypting the storage and transmission of sensitive data to prevent data leakage and unauthorized access, and using the AES encryption algorithm to encrypt sensitive fields in the database. Implement strict access control policies to limit different users' access rights to the data, formulate and implement privacy protection policies, ensure compliance with relevant laws, regulations, and privacy protection principles during data collection and integration, and clearly inform users of information such as the purpose of data collection, usage methods, and protection measures.

[0086] The policy generation module uses artificial intelligence technologies such as machine learning and data mining to deeply analyze the data to reveal hidden patterns and laws behind the data.

[0087] The sprinkler irrigation control module consists of a control terminal sub-module and an actuator sub-module. The control terminal sub-module automatically formulates irrigation plans based on the data provided by the intelligent analysis and strategy generation platform, including irrigation time, water volume, method, etc. The actuator sub-module includes intelligent valves, sprinklers, water pumps, pipelines, etc., and has functions such as remote control and automatic adjustment. It can accurately control the water volume and irrigation range according to the irrigation plan. The sprinkler irrigation strategy is differently processed according to the water shortage situation of the plants. Soil moisture sensors are used to monitor the soil moisture in real time and timely feedback the water shortage state. When the detected soil moisture is lower than the set threshold, the intelligent valve automatically opens to start irrigation. High-efficiency sprinklers (such as micro-sprinklers or drip irrigation heads) are used to directly deliver water to the roots of the plants, reducing water evaporation and loss. The water pump flow is adjusted to ensure sufficient water volume during irrigation and avoid soil erosion or uneven sprinkling caused by excessive water pressure. According to the plant requirements, frequent small-scale irrigation (such as multiple times a day) is set to avoid plant damage caused by soil drought. If the soil moisture of the plants remains within the appropriate range, according to the soil moisture data, the intelligent valve can be automatically switched on or off as needed to keep the soil humidity within the normal range. Uniform sprinkling sprinklers are used to ensure uniform irrigation and avoid local over-drying or over-wetting. Appropriate sprinkler angles and spraying radii are selected, and fixed irrigation frequencies (such as irrigation 2-3 times a week) are set according to the plant growth cycle and weather conditions to avoid over-irrigation.

[0088] As Figure 6 shown, the interaction module has functions of real-time monitoring, remote control, irrigation plan formulation, data analysis and reporting. Users can intuitively understand key parameters such as soil humidity, temperature, meteorological conditions and crop growth status of the farmland through real-time data charts and images. Users can remotely control the on / off and water volume adjustment of irrigation equipment through control buttons or sliders, supporting multiple irrigation modes such as timed irrigation, cyclic irrigation, and remote irrigation. Users can flexibly select according to actual needs. Users can formulate detailed irrigation plans according to the crop growth cycle and environmental conditions through the irrigation plan formulation tool, supporting the saving and sharing functions of irrigation plans. Users can save their irrigation plans for future use or share them with other users. The platform supports the analysis and statistics of historical data to generate irrigation effect reports and crop growth reports, etc. Users can customize the content and format of the reports through the report generation tool to better understand the irrigation effect and crop growth status.

[0089] The above specific embodiments only describe the design principles of the present application. The shapes and names of the components in this description can be different and are not limited. Therefore, those skilled in the art of the present application can modify or equivalently replace the technical solutions recorded in the foregoing embodiments. And these modifications and replacements do not depart from the creative purpose and technical solutions of the present application and should all belong to the protection scope of the present application.

Claims

1. A digital twin sprinkler irrigation optimization system for tea-solar complementary, characterized in that, The system includes: A digital twin mirror platform, a data acquisition module, a strategy generation module, an irrigation regulation module, and an interaction module; The digital twin mirror platform is used to construct a digital twin model and a digital twin model of the photovoltaic system. The digital twin model includes a three-dimensional solid model of the tea garden and a physical model of the tea garden. The three-dimensional solid model of the tea garden is constructed based on the tea garden GIS data and the UAV aerial images, simulating the terrain, soil, and vegetation of the tea garden. The physical model of the tea garden integrates multiple sub-models to simulate the change process of the physical environment of the tea garden. The sub-models include a soil moisture migration sub-model and a crop growth sub-model. The photovoltaic system sub-model is used to simulate the power generation and working efficiency of the photovoltaic system in the tea garden under different weather conditions; The data acquisition module acquires tea garden data based on the sensors deployed in the tea garden. The tea garden data includes soil data, moisture data, and real-time status data of the photovoltaic system; The strategy generation module predicts the growth status and irrigation requirements of the tea leaves and the power generation trend of the photovoltaic system based on the tea garden data, the digital twin model, and the digital twin model of the photovoltaic system, and determines the irrigation strategy; The irrigation regulation module executes the irrigation task based on the irrigation strategy; The interaction module is used to interact with the user.

2. The system according to claim 1, wherein The digital twin mirror platform includes a data collection and processing module, a digital twin model construction module, and a digital twin model integration and application module; The data collection and processing module acquires the relevant data of the tea garden and the photovoltaic system. The relevant data includes the terrain and landform, soil type, vegetation distribution, crop growth cycle, irrigation records, and meteorological condition data of the tea garden, as well as the layout, performance parameters, and historical power generation data of the photovoltaic modules. The meteorological condition data includes rainfall, temperature, humidity, and wind speed. The relevant data is processed to obtain the processed relevant data; The digital twin model construction module constructs a three-dimensional solid model of the tea garden, a physical model of the tea garden, and a photovoltaic module sub-model based on the processed relevant data. Among them, the three-dimensional solid model of the tea garden is constructed based on the tea garden GIS data and the UAV aerial images, simulating the terrain, soil, and vegetation of the tea garden. The physical model of the tea garden integrates multiple sub-models to simulate the change process of the physical environment of the tea garden. The sub-models include a soil moisture migration sub-model and a crop growth sub-model. Each photovoltaic module sub-model is constructed based on the electrical characteristics and physical structure of the photovoltaic module; The digital twin model integration and application module is used to integrate the three-dimensional solid model of the tea garden and the physical model of the tea garden to form a digital twin model; integrate the digital twin model and the digital twin model of the photovoltaic system to form an overall digital twin model; combine each photovoltaic module sub-model based on the layout and connection method of the photovoltaic system to form a digital twin model of the photovoltaic system. The digital twin model of the photovoltaic system is used to simulate the power generation and working efficiency of the photovoltaic system in the tea garden under different weather conditions; update and optimize the overall digital twin model based on the electrical data and meteorological condition data of the photovoltaic modules instantaneously collected by the data collection and processing module.

3. The system according to any one of claims 1-2, characterized in that, The digital twin model construction module also constructs a growth physical model of the tea leaves. The growth physical model is: Among them, W(t) is the value of the biomass of tea leaves at time t, η is the anabolism constant of tea leaves, κ is the catabolism constant of tea leaves, and t is in days. The biomass of the tea leaves includes the dry weight of the tea leaves, the fresh leaf weight, or the number of leaves.

4. The system according to claim 1, characterized in that, The data acquisition module includes a data collection sub-module and a data integration sub-module; The data collection sub-module obtains the tea garden data sensed by each sensor in the tea garden based on wireless communication technology, and sends the tea garden data to the interaction module and the data integration sub-module; The data integration sub-module preprocesses the tea garden data, integrates the preprocessed tea garden data, and sends the integrated tea garden data to the policy generation module; The policy generation module inputs the integrated tea garden data into the digital twin model to obtain the tea growth trend and the photovoltaic power generation trend; performs machine learning on the integrated tea garden data to predict the tea irrigation demand, and determines the irrigation strategy based on the tea growth trend, the photovoltaic power generation trend, the tea growth state, and the irrigation demand.

5. The system according to claim 4, wherein The ways to determine the irrigation strategy include: Construct a target function for the energy consumption of the photovoltaic tea garden. The target function for the energy consumption of the photovoltaic tea garden is: E total = w × [C tea × P tea (x1, x2, x3, x4) - C irr (x1, x2, x3, x4)] + (1 + w) × [C pv × P pv (y1, y2, y3) - C pv-maint (y1, y2, y3)] Where: E total is the energy consumption of the photovoltaic tea garden; w is the weight factor, 0 ≤ w ≤ 1; x1, x2, x3, and x4 are the irrigation electricity consumption, irrigation water consumption, irrigation frequency, and irrigation method respectively; y1, y2, and y3 are the installation angle, orientation, and cleaning frequency of the photovoltaic panels; P tea is the tea yield; P pv is the electricity generation of the photovoltaic power station composed of photovoltaic modules; C tea is the tea market price; C pv is the photovoltaic on-grid electricity price; C irr is the irrigation cost, including water resource cost and electricity cost; C pv-maint is the operation and maintenance cost of the photovoltaic power station; Generate a number of candidate irrigation strategies based on the tea growth trend, the photovoltaic power generation trend, and the tea irrigation demand; construct a particle swarm, and use the particle swarm algorithm to determine the irrigation strategy.

6. A digital twin irrigation optimization method for tea and solar complementary, based on the digital twin irrigation optimization system for tea and solar complementary as described in any one of claims 1-5, characterized in that, The method includes: Step S1: Obtain the tea garden data of the sensors deployed in the tea garden; Step S2: The digital twin sprinkler irrigation optimization system for tea-light complementary generates an irrigation plan based on the tea garden data, and formulates an irrigation task based on the irrigation plan; the intelligent valve irrigates based on the irrigation task, and adjusts the irrigation water volume and water flow rate during the irrigation process.

7. A computer-readable storage medium, in which multiple instructions are stored; the multiple instructions are used to be loaded and executed by a processor to perform the method as claimed in claim 6.

8. An electronic device, characterized in that, The electronic device includes: A processor for executing multiple instructions; A memory for storing multiple instructions; Among them, the multiple instructions are used to be stored by the memory and loaded and executed by the processor to perform the method as claimed in claim 6.

Images