Intelligent cultivation tank system and plant cultivation method

Abstract

The invention relates to the technical field of soilless culture, in particular to an intelligent cultivation tank system and a plant cultivation method. The system comprises a sensor configured to collect environmental data of a cultivation tank; the artificial intelligence module is configured to identify and analyze the environment data, obtain different types of sub-environment data, and generate a first nutrient solution adjusting instruction based on the different types of sub-environment data; the digital twinning module is configured to perform matrix conversion on the sub-environment data and map the sub-environment data to a digital twinning scene; the digital twinning module is configured to analyze spatio-temporal data of the plant in real time in a digital twinning scene and trigger a second nutrient solution adjusting instruction when the growth stage of the plant changes; the nutrient solution circulating device is configured to adjust the concentration of the nutrient solution in the cultivation tank based on the first nutrient solution adjusting instruction and / or the second nutrient solution adjusting instruction. According to the system, the intelligence of the soilless culture system is improved, and precise control over the plant growth environment is achieved.

Description

Technical Field

[0001] The present application relates to the technical field of soilless cultivation, and further to an intelligent cultivation trough system and a plant cultivation method. Background Art

[0002] At present, soilless cultivation has been widely used as a method of plant growth that does not rely on soil. Traditional soilless cultivation systems mainly rely on manual or semi-automatic environmental control methods to achieve control of the plant growth environment. These control measures include but are not limited to manual adjustment of key parameters such as nutrient solution supply. Although these methods can meet the basic needs of plant growth to a certain extent, these soilless cultivation systems still have limitations in terms of intelligence and cannot achieve precise control of the plant growth environment. Summary of the invention

[0003] In order to solve the above technical problems, the present application provides an intelligent cultivation trough system and a plant cultivation method, which improves the intelligence of the soilless cultivation system, realizes precise control of the plant growth environment, and improves the plant yield and quality.

[0004] In a first aspect, the present application provides an intelligent cultivation trough system, comprising: a sensor configured to collect environmental data of the cultivation trough in real time, and configured to collect a target image of a plant; an artificial intelligence module configured to identify and analyze the environmental data, obtain different types of sub-environment data, and generate a first nutrient solution adjustment instruction based on the different types of sub-environment data; a digital twin module configured to perform matrix conversion on the different types of sub-environment data and map them to a pre-built digital twin scene; the digital twin module is also configured to analyze the spatiotemporal data of the plant in real time in the digital twin scene, and trigger a second nutrient solution adjustment instruction when the growth stage of the plant changes; a nutrient solution circulation device configured to adjust the nutrient solution concentration in the cultivation trough based on the first nutrient solution adjustment instruction and / or the second nutrient solution adjustment instruction; a growth monitoring module configured to analyze the growth data of the plant based on hyperspectral imaging technology and machine learning algorithms; and a pest and disease monitoring module configured to determine the health status of the plant based on an artificial intelligence image recognition algorithm and the target image.

[0005] The above intelligent cultivation system collects the environmental data of the cultivation trough in real time by configuring sensors, combining the recognition and analysis of environmental data by the artificial intelligence module and the matrix conversion and mapping of the digital twin module. The application of this integrated technology enables the nutrient solution circulation device to dynamically adjust the nutrient solution concentration according to the first nutrient solution adjustment instruction and the second nutrient solution adjustment instruction, thereby improving the intelligence of the soilless cultivation system, realizing the precise control of the plant growth environment, and improving the plant yield and quality.

[0006] In one implementation, the artificial intelligence module is configured to identify and analyze the environmental data based on a preset growth model and an artificial intelligence visual recognition model to obtain multiple target environmental data; the artificial intelligence module is configured to classify the multiple target environmental data according to the sensor number to obtain different types of sub-environmental data.

[0007] In one implementation, the digital twin module is also configured to simulate the spread trend of pests and diseases based on the health status of the plants, and test a variety of pest and disease control strategies.

[0008] In one implementation, it also includes: the digital twin module is configured to perform growth trend prediction and environmental change analysis on the plant based on the growth data.

[0009] The above intelligent cultivation system can accurately determine the health status of plants by collecting target images of plants through sensors and combining the pest and disease monitoring module with artificial intelligence image recognition algorithms. The digital twin module simulates the spread trend of pests and diseases based on the health status of plants and tests a variety of pest and disease control strategies, thereby providing early warnings and optimizing control measures to reduce crop losses. The growth monitoring module analyzes plant growth data based on hyperspectral imaging technology and machine learning algorithms. The digital twin module further predicts growth trends and analyzes environmental changes based on these data to achieve precise control of plant growth environments and improve crop yields and quality. The integrated application of these technologies not only improves the accuracy of pest and disease monitoring and the timeliness of early warning, but also enhances the real-time monitoring and prediction capabilities of plant growth status, providing intelligent and precise management methods for soilless cultivation, and effectively improving the efficiency of agricultural production and the yield and quality of crops.

[0010] In one implementation, the environmental data includes ambient temperature, greenhouse humidity and light intensity; the artificial intelligence module is configured to generate environmental adjustment instructions based on the ambient temperature, greenhouse humidity and light intensity, and also includes: an environmental adjustment device, configured to adjust the ambient temperature, greenhouse humidity and light intensity respectively based on the environmental adjustment instructions.

[0011] In one implementation, the environmental data also includes substrate temperature, and further includes: a substrate regulating device configured to regulate the liquid flow rate in the temperature regulating pipeline based on the substrate temperature regulating instruction generated by the artificial intelligence module.

[0012] The above intelligent cultivation system collects key environmental data such as ambient temperature, substrate temperature, greenhouse humidity and light intensity in real time through sensors, and the artificial intelligence module can generate accurate environmental adjustment instructions based on these data. The environmental adjustment device finely adjusts the ambient temperature, greenhouse humidity and light intensity according to the environmental adjustment instructions, while the substrate adjustment device adjusts the liquid flow rate in the temperature adjustment pipeline according to the substrate temperature adjustment instructions generated by the artificial intelligence module to control the temperature of the cultivation substrate. This control measure realizes comprehensive intelligent control of the soilless cultivation environment, improves the response speed and control accuracy of the intelligent cultivation trough system, optimizes the plant growth conditions, thereby promoting the healthy growth of crops, improving yield and quality, while reducing energy consumption and manual management costs, and improving the efficiency and sustainability of the intelligent cultivation trough system. In addition, the self-learning and evolutionary capabilities of the artificial intelligence module ensure that the system performance will continue to be optimized over time to meet the diverse agricultural needs under different regional and seasonal conditions.

[0013] In one implementation, the artificial intelligence module is also configured to monitor the working status of the intelligent cultivation trough system in real time and automatically perform fault maintenance operations; the digital twin module is also configured to monitor the working status of the intelligent cultivation trough system in real time and perform fault prediction operations on the intelligent cultivation trough system.

[0014] In one implementation, the temperature regulating pipe is made of heat-resistant polyethylene.

[0015] In a second aspect, the present application also provides a plant cultivation method, which is applied to any of the above-mentioned intelligent cultivation trough systems, including: real-time collection of environmental data of the cultivation trough; identifying and analyzing the environmental data to obtain different types of sub-environment data, and generating a first nutrient solution adjustment instruction based on the different types of sub-environment data; matrix conversion of the different types of sub-environment data, and mapping them to a pre-built digital twin scene; real-time analysis of the spatiotemporal data of the plant in the digital twin scene, and triggering a second nutrient solution adjustment instruction when the growth stage of the plant changes; adjusting the nutrient solution concentration in the cultivation trough based on the first nutrient solution adjustment instruction and / or the second nutrient solution adjustment instruction.

[0016] In one implementation, it also includes: identifying and analyzing the environmental data based on a preset growth model and an artificial intelligence visual recognition model to obtain multiple target environmental data; classifying the multiple target environmental data according to the sensor number to obtain different types of sub-environmental data.

[0017] Compared with the prior art, the present invention has at least one of the following beneficial effects: 1. By configuring sensors to collect environmental data of the cultivation trough in real time, combined with the recognition and analysis of environmental data by the artificial intelligence module and the matrix conversion and mapping of the digital twin module. The application of this integrated technology enables the nutrient solution circulation device to dynamically adjust the nutrient solution concentration according to the first nutrient solution adjustment instruction and the second nutrient solution adjustment instruction, thereby improving the intelligence of the soilless cultivation system, achieving precise control of the plant growth environment, and improving plant yield and quality.

[0018] 2. By collecting the target image of the plant through the sensor and combining it with the artificial intelligence image recognition algorithm of the pest and disease monitoring module, the health status of the plant can be accurately determined. The digital twin module simulates the spread trend of pests and diseases based on the health status of the plant, and tests a variety of pest and disease control strategies, so as to provide early warning and optimize control measures to reduce crop losses. The growth monitoring module analyzes the growth data of the plant based on hyperspectral imaging technology and machine learning algorithms. The digital twin module further predicts the growth trend and analyzes environmental changes based on these data to achieve precise control of the plant growth environment and improve crop yield and quality. The integrated application of these technologies not only improves the accuracy of pest and disease monitoring and the timeliness of early warning, but also enhances the real-time monitoring and prediction capabilities of plant growth status, providing intelligent and precise management methods for soilless cultivation, and effectively improving the efficiency of agricultural production and the yield and quality of crops.

[0019] 3. Through sensors, key environmental data such as ambient temperature, substrate temperature, greenhouse humidity and light intensity are collected in real time, and the artificial intelligence module can generate accurate environmental adjustment instructions based on these data. The environmental adjustment device finely adjusts the ambient temperature, greenhouse humidity and light intensity according to the environmental adjustment instructions, while the substrate adjustment device adjusts the liquid flow rate in the temperature adjustment pipeline according to the substrate temperature adjustment instructions generated by the artificial intelligence module to control the temperature of the cultivation substrate. This control measure realizes comprehensive intelligent control of the soilless cultivation environment, improves the response speed and control accuracy of the intelligent cultivation trough system, optimizes the plant growth conditions, thereby promoting the healthy growth of crops, improving yield and quality, while reducing energy consumption and manual management costs, and improving the efficiency and sustainability of the intelligent cultivation trough system. In addition, the self-learning and evolutionary capabilities of the artificial intelligence module ensure that the system performance will continue to be optimized over time to meet the diverse agricultural needs under different regional and seasonal conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The preferred implementation modes will be described below in a clear and understandable manner with reference to the accompanying drawings to further illustrate the above-mentioned characteristics, technical features, advantages and implementation methods of the present invention.

[0021] Figure 1 A framework diagram of an intelligent cultivation trough system provided in an embodiment of the present application is shown; Figure 2 A flow chart of a plant cultivation method provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0022] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the specific implementation methods of the present invention will be described below with reference to the accompanying drawings. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings and other implementation methods can be obtained based on these drawings without creative work.

[0023] In order to simplify the drawings, only the parts related to the invention are schematically shown in each figure, and they do not represent the actual structure of the product. In addition, in order to simplify the drawings and facilitate understanding, in some figures, only one of the parts with the same structure or function is schematically drawn or marked. In this article, "one" not only means "only one", but also means "more than one".

[0024] It should be further understood that the term “and / or” used in the specification and appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0025] In this document, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0026] In addition, in the description of the present application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0027] It should be noted that the above embodiments can be freely combined as needed. The above are only preferred embodiments of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be regarded as the protection scope of the present invention.

[0028] A digital twin is a virtual model that aims to accurately reflect a physical object or system. It models and simulates physical entities in the real world through sensors, data analysis, and simulation technology to achieve real-time monitoring, prediction, and optimization of the real world. Digital twins usually consist of three parts: physical entities, digital models, and data connections. Physical entities are entities in the real world, such as machines, equipment, factories, etc.; digital models are the core of digital twins, which are virtual models corresponding to physical entities; data connections are technologies that connect physical entities and digital models, including sensors, data acquisition, data storage, and data analysis. For example, in soilless cultivation, digital twins can achieve accurate simulation and monitoring of crop growth environments and processes by creating digital copies of crops.

[0029] Artificial intelligence (AI) enables computer systems to perform tasks that usually require human intelligence, such as visual recognition, language understanding, decision-making, and learning. In soilless cultivation, artificial intelligence can provide intelligent decision support by conducting in-depth analysis of crop growth data through machine learning algorithms and data analysis techniques. The embodiments of the present application combine artificial intelligence technology, digital twin technology, and soilless cultivation, and set up a corresponding intelligent cultivation trough system, which can achieve at least one of the following beneficial effects: improving the intelligence of the soilless cultivation system and achieving precise control of the plant growth environment; or overcoming the problems of extensive control and high energy consumption in traditional soilless cultivation systems, thereby reducing production costs.

[0030] The following is a detailed description with reference to the accompanying drawings: Reference Figure 1 , which shows a framework diagram of an intelligent cultivation trough system provided in an embodiment of the present application. Figure 1As shown, the intelligent cultivation trough system 100 includes: a sensor 110, an artificial intelligence module 120, a digital twin module 130, a nutrient solution circulation device 140, a pest and disease monitoring module 150 and a growth detection module 160. Among them, the sensor 110 is configured to collect environmental data in the cultivation trough in real time, and is configured to collect target images of plants; the artificial intelligence module 120 is configured to identify and analyze the environmental data, obtain different types of sub-environment data, and generate a first nutrient solution adjustment instruction based on different types of sub-environment data; the digital twin module 130 is configured to perform matrix conversion on different types of sub-environment data and map them to a pre-built digital twin scene; the digital twin module 130 is also configured to analyze the spatiotemporal data of the plants in real time in the digital twin scene, and generate a second nutrient solution adjustment instruction when the growth stage of the plants changes; the nutrient solution circulation device 140 is configured to adjust the nutrient solution concentration in the cultivation trough based on the first nutrient solution adjustment instruction and / or the second nutrient solution adjustment instruction; the pest and disease monitoring module 150 is configured to determine the health status of the plants based on the artificial intelligence image recognition algorithm and the target image; the growth monitoring module 160 is configured to analyze the growth data of the plants based on hyperspectral imaging technology and machine learning algorithms.

[0031] The cultivation trough includes a cultivation trough body, an insulation layer, an isolation part, and an insulation cover. Among them, the cultivation trough body is used to carry the cultivation substrate; the insulation layer is located at the bottom of the inner side of the cultivation trough body to prevent the soil temperature from being too high; the isolation part is provided with a fluid through hole to ensure the circulation of the nutrient solution; the insulation cover covers the top of the cultivation trough to keep the internal temperature of the cultivation trough constant. The sensor 110 includes but is not limited to a temperature sensor, a humidity sensor, a light sensor, a soil moisture sensor, and a nutrient solution component sensor, which are used to collect various environmental data in the cultivation trough in real time. The nutrient solution circulation device 140 includes a liquid reservoir, a circulation pump, and a distribution pipeline, which is responsible for supplying nutrient solution to the cultivation substrate.

[0032] The hardware equipment such as the cultivation trough body, the insulation layer, the isolation part, the insulation cover, the nutrient solution circulation device 140 and the sensor 110 are installed, and these hardware equipment are calibrated at the same time. Ensure their correct installation space position, orientation and pitch angle, and connection with the central processor. Select a suitable cultivation substrate according to the plant type and ensure that it meets the requirements of soilless cultivation. Fill the cultivation substrate into the accommodation space of the cultivation trough body to ensure that the cultivation substrate is evenly distributed and leave enough space for the growth of the plant root system. The external parameters of the sensor are calibrated, and the environmental data of the cultivation trough is collected in real time through the sensor 110 (the environmental data may include the environmental data inside the cultivation trough and the environmental data outside the cultivation trough), and the environmental data is classified and sent to the artificial intelligence module 120. The artificial intelligence module 120 can identify and analyze the environmental data to obtain different types of sub-environmental data (the sub-environmental data can be the ambient temperature outside the cultivation trough, the cultivation substrate temperature, the greenhouse humidity, the light intensity, the nutrient solution concentration, and the pH value of the nutrient solution. The sub-environmental data is essentially obtained by splitting the environmental data according to the sensor number). Then, the machine learning model is used to analyze these different types of sub-environment data, predict the growth trends of the plants and environmental changes, automatically adjust the formula and supply of the nutrient solution, and generate the first nutrient solution adjustment instruction.

[0033] The digital twin module 130 performs matrix conversion on different types of sub-environment data through the internal digital twin safety intelligent prevention and control platform unit, converting two-dimensional data into data in three-dimensional space. The data in three-dimensional space should be set in the pre-built digital twin scene, and the impact of different environmental conditions on plant growth is simulated in the data twin scene. At the same time, a nutrient solution management mechanism is constructed in the digital twin scene to analyze the spatiotemporal data of the plant in real time. When the growth stage of the plant changes, the second nutrient solution adjustment instruction is automatically triggered.

[0034] The nutrient solution circulation device 140 can adjust the nutrient solution concentration in the cultivation trough based on the first nutrient solution adjustment instruction and / or the second nutrient solution adjustment instruction. Among them, the second nutrient solution adjustment instruction triggered by the digital twin module 130 can serve as an auxiliary decision for the first nutrient solution adjustment instruction generated by the artificial intelligence module. The specific working process of the nutrient solution circulation device 140 is: start the circulation pump to allow the nutrient solution to flow into the first space through the liquid inlet pipe, evenly distributed in the cultivation matrix, and provide nutrients for the crops. Excess nutrient solution flows into the second space through the fluid through hole, returns to the liquid storage part through the liquid outlet pipe, and is stored or filtered and then recycled again, which can improve the utilization rate of the nutrient solution.

[0035] The embodiment of the present application configures sensors to collect environmental data of the cultivation trough in real time, combines the recognition and analysis of environmental data by the artificial intelligence module, and the matrix conversion and mapping of the digital twin module. The application of this integrated technology enables the nutrient solution circulation device to dynamically adjust the nutrient solution concentration according to the first nutrient solution adjustment instruction and the second nutrient solution adjustment instruction, thereby improving the intelligence of the soilless cultivation system, realizing precise control of the plant growth environment, and improving the plant yield and quality.

[0036] In one embodiment of the present application, the artificial intelligence module is configured to identify and analyze environmental data based on a preset growth model and an artificial intelligence visual recognition model to obtain multiple target environmental data; the artificial intelligence module is configured to classify multiple target environmental data according to the sensor number to obtain different types of sub-environmental data.

[0037] After obtaining the environmental data of the cultivation trough, the artificial intelligence module imports the preset growth model, and identifies and analyzes the received environmental data through the internal artificial intelligence target recognition module and the pre-trained artificial intelligence visual recognition model, and obtains multiple target environmental data (target environmental data is data containing environmental target types and their parameter values), and then sorts and classifies the target environmental data according to the sensor number through the data analysis output module to obtain different types of sub-environmental data, and sends these sub-environmental data to the digital twin module in real time. The digital twin module performs operations such as matrix conversion and mapping of different types of sub-data to digital twin scenes, and then triggers the second nutrient solution adjustment instruction when the growth stage of the plant changes.

[0038] In one embodiment of the present application, refer to the attached Figure 1 The digital twin module 130 is also configured to simulate the spread trend of pests and diseases based on the health status of the plants and test various pest and disease control strategies. The digital twin module 130 is configured to predict the growth trend of the plants and analyze environmental changes based on the growth data.

[0039] The sensor 110 can be a high-definition camera. By setting the photographing frequency for the sensor 110, the sensor 110 can scan the plant at the preset photographing frequency to obtain the target image of the plant. The pest and disease monitoring module identifies pests and diseases on the target image based on the artificial intelligence image recognition algorithm. When the recognition threshold is greater than the preset threshold, it is determined that the plant has signs of pests and diseases (that is, the health status of the plant is determined). Based on the health status of the plant, the digital twin module 130 simulates the occurrence and spread of pests and diseases in the digital twin model and tests a variety of pest and disease control strategies.

[0040] The growth monitoring module 160 analyzes the growth data of the plants (growth data includes growth rate and health status) through hyperspectral imaging technology and machine learning algorithms, and sends the growth data in real time to the digital twin safety intelligent prevention and control platform unit in the digital twin module 130 to predict the growth trend of the plants and analyze environmental changes.

[0041] The embodiment of the present application uses sensors to collect target images of plants, and combines the pest and disease monitoring module with artificial intelligence image recognition algorithms to accurately determine the health status of plants. The digital twin module simulates the spread trend of pests and diseases based on the health status of the plants, and tests a variety of pest and disease control strategies, so as to provide early warning and optimize control measures to reduce crop losses. The growth monitoring module analyzes the growth data of plants based on hyperspectral imaging technology and machine learning algorithms. The digital twin module further predicts growth trends and analyzes environmental changes based on these data to achieve precise control of the plant growth environment and improve crop yield and quality. The integrated application of these technologies not only improves the accuracy of pest and disease monitoring and the timeliness of early warning, but also enhances the real-time monitoring and prediction capabilities of plant growth status, provides intelligent and precise management methods for soilless cultivation, and effectively improves the efficiency of agricultural production and the yield and quality of crops.

[0042] In one embodiment of the present application, refer to the attached Figure 1 The environmental data includes the ambient temperature (or the ambient temperature outside the cultivation tank), the substrate temperature (or the cultivation substrate temperature), the greenhouse humidity and the light intensity; the artificial intelligence module 120 is configured to generate an environmental adjustment instruction based on the ambient temperature, the greenhouse humidity and the light intensity, and also includes: an environmental adjustment device 170, which is configured to adjust the ambient temperature, the greenhouse humidity and the light intensity respectively based on the environmental adjustment instruction. The substrate adjustment device 180 is configured to adjust the liquid flow rate in the temperature adjustment pipeline based on the substrate temperature adjustment instruction generated by the artificial intelligence module 120.

[0043] The artificial intelligence module 120 uses an artificial intelligence algorithm to analyze and predict the ambient temperature data, and automatically adjusts the working state of the environmental adjustment device (or temperature adjustment device) 170 to cope with changes in the external environment. Through the integrated humidity sensor and the environmental adjustment device 170, the artificial intelligence module 120 automatically adjusts the humidity in the greenhouse to adapt to crop growth. The artificial intelligence module 120 can also automatically adjust the light intensity and light duration of the cultivation trough according to the photosynthesis requirements and light intensity of the plants. The environmental adjustment instructions generated by the artificial intelligence module 120 may include an ambient temperature adjustment instruction, a greenhouse humidity adjustment instruction, and a light intensity adjustment instruction. Among them, the ambient temperature adjustment instruction is used to instruct the temperature regulator in the environmental adjustment device 170 to adjust the ambient temperature; the greenhouse humidity adjustment instruction is used to instruct the humidity controller in the environmental adjustment device 170 to adjust the greenhouse humidity; and the light intensity adjustment instruction is used to instruct the lighting device in the environmental adjustment device 170 to adjust the light intensity and light duration.

[0044] The substrate regulating device (or substrate temperature regulating device) 180 automatically adjusts the liquid flow rate (or temperature regulating medium flow rate) in the temperature regulating pipe based on the substrate temperature regulating instruction generated by the artificial intelligence module 120 and the real-time substrate temperature data to maintain the optimal growth temperature of the cultivation substrate. Through the above-mentioned regulating measures, the growth environment of the plant can be optimized.

[0045] The embodiment of the present application collects key environmental data such as ambient temperature, substrate temperature, greenhouse humidity and light intensity in real time through sensors, and the artificial intelligence module can generate accurate environmental adjustment instructions based on these data. The environmental adjustment device finely adjusts the ambient temperature, greenhouse humidity and light intensity according to the environmental adjustment instructions, and the substrate adjustment device adjusts the liquid flow rate in the temperature adjustment pipeline according to the substrate temperature adjustment instructions generated by the artificial intelligence module to control the temperature of the cultivation substrate. This control measure realizes comprehensive intelligent control of the soilless cultivation environment, improves the response speed and control accuracy of the intelligent cultivation trough system, optimizes the plant growth conditions, thereby promoting the healthy growth of crops, improving yield and quality, while reducing energy consumption and manual management costs, and improving the efficiency and sustainability of the intelligent cultivation trough system. In addition, the self-learning and evolutionary capabilities of the artificial intelligence module ensure that the system performance will continue to be optimized over time to meet the diverse agricultural needs under different regional and seasonal conditions.

[0046] In one embodiment of the present application, the artificial intelligence module is also configured to monitor the working status of the intelligent cultivation trough system in real time and automatically perform fault maintenance operations; the digital twin module is also configured to monitor the working status of the intelligent cultivation trough system in real time and perform fault prediction operations on the intelligent cultivation trough system.

[0047] The AI ​​module can monitor the working status of the smart cultivation trough system. Once an abnormality is found, it will automatically diagnose the fault and prompt maintenance operations. After the plants mature, the AI ​​module can also perform harvesting operations and remove the harvested plants from the cultivation trough. After harvesting, the cultivation trough and related equipment are cleaned and disinfected to prepare for the planting of plants in the next season. The AI ​​module can also regularly check the working status of each component of the smart cultivation trough system, including the working status of key components such as circulation pumps, temperature control equipment and sensors, to ensure the stable operation of the smart cultivation trough system.

[0048] The digital twin module can activate the predictive maintenance system in the digital twin model, check the working status of each component of the smart cultivation trough system, including circulation pumps, temperature control equipment and sensors, predict the failure points and maintenance needs of the smart cultivation trough system, and thus avoid unexpected shutdown of the smart cultivation trough system.

[0049] In one embodiment of the present application, it also includes: running a data analysis and decision support platform, allowing users to browse the overview page of the smart cultivation trough system, deeply analyzing the collected data through an artificial intelligence module, providing plant growth trend predictions and cultivation suggestions, and helping users make scientific decisions; an automation control module, used to confirm that the smart cultivation trough system is in standby mode, setting an automation control strategy, and ensuring that the smart cultivation trough system automatically operates according to preset conditions.

[0050] In one embodiment of the present application, the cultivation trough body is made of lightweight and high-strength material; the insulation layer is preferably made of material with excellent thermal resistance properties, such as polyurethane foam plastic or spray thermal resistance material; the isolation part is made of corrosion-resistant material to ensure long-term stability; the insulation cover is made of flexible material and should have good thermal insulation performance; the temperature regulating pipe in the substrate temperature control system is made of heat-resistant polyethylene (PERT) material with high thermal conductivity; the circulation pump has moderate power to ensure uniform flow; the sensor needs to have high sensitivity and accuracy; the core components of the artificial intelligence module use high-performance servers, and the software platform has strong compatibility and is easy to upgrade.

[0051] Reference Figure 2 , which shows a flow chart of a plant cultivation method provided in an embodiment of the present application, applied to the intelligent cultivation trough system in any of the above embodiments, including: S200, real-time collection of environmental data of the cultivation trough; S210, identifying and analyzing the environmental data, acquiring different types of sub-environmental data, and generating a first nutrient solution adjustment instruction based on the different types of sub-environmental data; S220, performing matrix conversion on different types of sub-environment data and mapping them to a pre-built digital twin scene; S230, analyzing the spatiotemporal data of the plant in real time in the digital twin scene, and triggering a second nutrient solution adjustment instruction when the growth stage of the plant changes; S240: Adjust the concentration of the nutrient solution in the cultivation tank based on the first nutrient solution adjustment instruction and / or the second nutrient solution adjustment instruction.

[0052] The details of the embodiments of the present application have been described in the aforementioned embodiments and will not be repeated here.

[0053] In one embodiment of the present application, it also includes: identifying and analyzing environmental data based on a preset growth model and an artificial intelligence visual recognition model to obtain multiple target environmental data; classifying the multiple target environmental data according to the sensor number to obtain different types of sub-environmental data.

[0054] In one embodiment of the present application, it also includes: S1. Install and calibrate all hardware equipment, including sensors for temperature, humidity, light, and nutrient solution composition, to ensure their correct installation spatial position, orientation, and pitch angle, as well as connection with the central processor. Measure and calibrate the external parameters of the sensors, collect sensor data in real time, and send the data to the artificial intelligence target recognition unit and the digital twin security intelligent prevention and control platform unit after classification; S2. Configure the artificial intelligence environment adjustment system, import the preset growth model, and use the artificial intelligence target recognition module to use the trained artificial intelligence visual recognition model to perform environmental parameter recognition and analysis on the received sensor data, obtain data containing environmental target types and their parameter values, and then use the data analysis and output module to sort and classify the environmental target data according to the sensor number, and send it to the digital twin security intelligent prevention and control platform unit in real time; S3. On the digital twin safety intelligent prevention and control platform unit, the monitoring data, plant growth stage and nutritional demand data from the sensor are received, the two-dimensional data is converted into three-dimensional spatial data through matrix conversion, and mapped to the constructed digital twin scene to simulate the impact of different environmental conditions on plant growth; S4. Build a nutrient solution management mechanism in the twin scene, analyze the spatiotemporal data of plant targets in real time, and automatically trigger the nutrient solution formula adjustment command and early warning broadcast when the plant growth enters the corresponding stage. At the same time, human intervention can be carried out to send emergency nutrient supplement commands by voice command or manual control button, and send the nutrient solution adjustment command data to the on-site execution unit through the network to complete remote intelligent control; S5. Turn on the pest and disease monitoring system, set the photo taking frequency and recognition threshold, monitor the health of the plants through artificial intelligence image recognition technology, detect signs of pests and diseases at an early stage, and simulate the occurrence and spread of pests and diseases in the digital twin model to test different prevention and control strategies; S6. Start the growth monitoring system, analyze the growth rate and health status of the plants through hyperspectral imaging and machine learning algorithms, and send the growth data to the digital twin safety intelligent prevention and control platform unit in real time to predict growth trends and analyze environmental changes; S7. Activate the predictive maintenance system in the digital twin model to check the working status of each system component, including circulation pumps, temperature control equipment and sensors, predict system failures and maintenance needs, and reduce unexpected downtime; S8. Run the data analysis and decision support platform, browse the system overview page, use the AI ​​system to deeply analyze the collected data, provide growth trend predictions and cultivation suggestions, and help decision makers make scientific decisions; S9. Turn on the automation control system, confirm that each subsystem is in standby mode, set the automation control strategy, and ensure that the system automatically runs according to the preset conditions; S10. Officially start the intelligent cultivation trough system, observe the initial operation, ensure that all systems work in a coordinated and consistent manner, and make necessary adjustments and optimizations based on system feedback and performance data.

[0055] It should be noted that the above embodiments can be freely combined as needed. The above are only preferred embodiments of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be regarded as the protection scope of the present invention.

Claims

1. An intelligent cultivation trough system, characterized in that: include: A sensor configured to collect environmental data of the cultivation trough in real time and configured to collect target images of the plants; an artificial intelligence module, configured to identify and analyze the environmental data, obtain different types of sub-environmental data, and generate a first nutrient solution adjustment instruction based on the different types of sub-environmental data; A digital twin module is configured to perform matrix conversion on different types of sub-environment data and map them into a pre-built digital twin scene; The digital twin module is further configured to analyze the spatiotemporal data of the plant in real time in the digital twin scene, and trigger a second nutrient solution adjustment instruction when the growth stage of the plant changes; a nutrient solution circulation device configured to adjust the concentration of the nutrient solution in the cultivation tank based on the first nutrient solution adjustment instruction and / or the second nutrient solution adjustment instruction; A growth monitoring module configured to analyze the growth data of the plant based on hyperspectral imaging technology and machine learning algorithms; The pest and disease monitoring module is configured to determine the health status of the plant based on an artificial intelligence image recognition algorithm and the target image.

2. The intelligent cultivation trough system according to claim 1, characterized in that: The artificial intelligence module is configured to identify and analyze the environmental data based on a preset growth model and an artificial intelligence visual recognition model to obtain a plurality of target environmental data; The artificial intelligence module is configured to classify the plurality of target environment data according to the numbers of the sensors to obtain different types of sub-environment data.

3. The intelligent cultivation trough system according to claim 1, characterized in that: Also includes: The digital twin module is also configured to simulate the spread trend of pests and diseases based on the health status of the plants and test a variety of pest and disease control strategies.

4. The intelligent cultivation trough system according to claim 3, characterized in that: Also includes: The digital twin module is configured to predict the growth trend and analyze environmental changes of the plant based on the growth data.

5. The intelligent cultivation trough system according to claim 1, characterized in that: The environmental data include ambient temperature, greenhouse humidity and light intensity; The artificial intelligence module is configured to generate an environment adjustment instruction based on the ambient temperature, the greenhouse humidity and the light intensity, and further includes: The environment adjustment device is configured to adjust the environment temperature, the greenhouse humidity and the light intensity respectively based on the environment adjustment instruction.

6. The intelligent cultivation trough system according to claim 1, characterized in that: The artificial intelligence module is also configured to monitor the working status of the intelligent cultivation trough system in real time and automatically perform fault maintenance operations; The digital twin module is also configured to monitor the working status of the intelligent cultivation trough system in real time and perform fault prediction operations on the intelligent cultivation trough system.

7. The intelligent cultivation trough system according to claim 5, characterized in that: The environmental data also includes substrate temperature, and also includes: The substrate regulating device is configured to regulate the flow rate of the liquid in the temperature regulating pipeline based on the substrate temperature regulating instruction generated by the artificial intelligence module.

8. A plant cultivation method, characterized in that: The intelligent cultivation trough system applied to any one of claims 1 to 7 comprises: Collect the environmental data of the cultivation trough in real time; Identify and analyze the environmental data to obtain different types of sub-environmental data, and generate a first nutrient solution adjustment instruction based on the different types of sub-environmental data; Performing matrix conversion on the sub-environment data of different types and mapping them to the pre-built digital twin scene; Analyzing the spatiotemporal data of the plant in real time in the digital twin scene, and triggering a second nutrient solution adjustment instruction when the growth stage of the plant changes; Based on the first nutrient solution adjustment instruction and / or the second nutrient solution adjustment instruction, the concentration of the nutrient solution in the cultivation tank is adjusted.

9. The plant cultivation method according to claim 8, characterized in that: Also includes: Based on a preset growth model and an artificial intelligence visual recognition model, the environmental data is identified and analyzed to obtain a plurality of target environmental data; The plurality of target environment data are classified according to the numbers of the sensors to obtain different types of sub-environment data.

10. The plant cultivation method according to claim 8, characterized in that: The environmental data includes ambient temperature, greenhouse humidity and light intensity, and also includes: Generate an environmental adjustment instruction based on the ambient temperature, the greenhouse humidity and the light intensity; Based on the environmental adjustment instruction, the ambient temperature, the greenhouse humidity and the light intensity are adjusted respectively.

Images