A vegetable greenhouse environment intelligent control method and system

Abstract

The present invention relates to the field of intelligent environmental control technology, and in particular to a method and system for intelligent control of vegetable greenhouse environment. The method comprises the following steps: obtaining all-weather lighting data and internal environment data of the vegetable greenhouse through sensors; identifying air heat exchange paths based on the internal environment data of the vegetable greenhouse to obtain internal air heat exchange path data; performing heat flux period temperature and pressure deposition simulation on the internal air heat exchange path data according to the all-weather lighting data of the vegetable greenhouse, and performing gas exchange barrier effect analysis to obtain gas exchange barrier effect data; performing regional environmental stage-by-stage control on the gas exchange barrier effect data to obtain regional environmental stage-by-stage control data; constructing an environmental control model for the regional environmental stage-by-stage control data to obtain an environmental control logic model. The present invention makes the environmental intelligent control technology more accurate by optimizing the environmental intelligent control technology.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent environmental control, and in particular to an intelligent control method and system for a vegetable greenhouse environment. Background Art

[0002] The intelligent control method aims to integrate a variety of emerging technologies, such as the Internet of Things (IoT), artificial intelligence (AI), sensor technology, and automated control systems to achieve precise management of the internal environment of the greenhouse. This method relies on the real-time monitoring of parameters such as temperature, humidity, light, carbon dioxide concentration, soil moisture, etc. by the sensor network, and combines crop growth models and environmental big data analysis to dynamically adjust the operation mode of ventilation, irrigation, lighting, heating and other facilities to create the best growth environment for crops. At the same time, the intelligent control system can also introduce prediction algorithms to predict the changing trend of environmental conditions based on weather forecasts and historical data, and take preventive measures in advance, such as closing windows in advance to keep warm and adjusting watering in advance. However, a traditional intelligent control method for the environment of vegetable greenhouses has the problems of inaccurate analysis of temperature and heat flux interaction and large errors in regional environmental control. Summary of the invention

[0003] Based on this, it is necessary to provide a method and system for intelligent control of vegetable greenhouse environment to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a method for intelligently controlling the environment of a vegetable greenhouse is provided, the method comprising the following steps:

[0005] Step S1: Obtaining all-weather lighting data of the vegetable greenhouse and internal environment data of the vegetable greenhouse through sensors;

[0006] Step S2: Based on the internal environment data of the vegetable greenhouse, the air heat exchange path is identified to obtain the internal air heat exchange path data; based on the all-weather lighting data of the vegetable greenhouse, the internal air heat exchange path data is simulated for the temperature and pressure deposition during the heat flux period to obtain the temperature and pressure deposition data during the heat flux period; based on the temperature and pressure deposition data during the heat flux period, the gas exchange barrier effect is analyzed to obtain the gas exchange barrier effect data;

[0007] Step S3: Acquire vegetable environment suitability data; perform regional environmental stage-by-stage regulation on the gas exchange barrier effect data based on the vegetable environment suitability data to obtain regional environmental stage-by-stage regulation data;

[0008] Step S4: construct an environmental control model for the regional environmental phased control data to obtain an environmental control logic model; send the environmental control logic model to the cloud platform to perform intelligent control of the vegetable greenhouse environment.

[0009] The present invention uses sensors to collect various environmental data in the vegetable greenhouse in real time, including temperature, humidity, light intensity, air flow, etc. These data can fully reflect the light and air conditions in the greenhouse, and help to analyze the climate change of the greenhouse and its impact on vegetable growth. At the same time, all-weather light data can reveal the changing trend of the external climate and provide basic data support for internal environmental regulation. By analyzing the internal environmental data of the vegetable greenhouse, the heat flow exchange path of the air in the greenhouse is identified, and the temperature, humidity and direction and speed of gas flow are evaluated. This process helps to understand the thermodynamic behavior of the air inside the greenhouse, provides data support for the subsequent heat flux period temperature and pressure deposition simulation, and then predicts the impact of changes in heat and pressure on vegetable growth. In addition, based on the light data, the heat flux period temperature and pressure deposition simulation is carried out, which helps to reveal the changing law of heat in different time periods and provides a basis for the subsequent gas exchange effect analysis. Combined with the growth requirements of vegetable varieties and the climatic conditions in the greenhouse, the optimal environmental data required for vegetable growth is extracted. These data include temperature, humidity, light intensity, etc., which can provide accurate growth environment parameters for each vegetable. By obtaining the data on the suitable environment for vegetables, it is possible to provide the necessary basis for the subsequent analysis of the gas exchange barrier effect and the refined processing of environmental regulation, ensuring that vegetables grow under optimal conditions. According to the regional environmental stage regulation data, an environmental regulation model is constructed, which can comprehensively consider multiple factors such as temperature, humidity, and light to achieve precise control of the environment in the greenhouse. The environmental regulation logic model can automatically adjust the parameters such as air circulation, temperature and humidity in the greenhouse according to real-time data to ensure that the environment in the greenhouse continues to remain in the most suitable state for vegetable growth. This model can be remotely monitored and adjusted through the cloud platform to ensure the intelligence and precision of environmental regulation, and automatically adjust strategies at different environmental stages to optimize crop yield and quality.

[0010] Preferably, step S2 comprises the following steps:

[0011] Step S21: identifying the air heat flow exchange path based on the internal environment data of the vegetable greenhouse to obtain the internal air heat flow exchange path data;

[0012] Step S22: Acquire greenhouse material characteristic data;

[0013] Step S23: performing light source heat conduction fluctuation analysis on greenhouse material characteristic data according to the all-weather illumination data of the vegetable greenhouse to obtain light source heat conduction fluctuation data;

[0014] Step S24: performing a heat flux period temperature and pressure deposition simulation on the internal air heat exchange path data based on the light source heat conduction fluctuation data to obtain the heat flux period temperature and pressure deposition data;

[0015] Step S25: performing a gas exchange barrier effect analysis on the internal air heat flow exchange path data according to the heat flux period temperature and pressure deposition data to obtain gas exchange barrier effect data.

[0016] The present invention identifies and analyzes the heat exchange path of the air in the greenhouse by collecting environmental data inside the vegetable greenhouse, such as temperature, humidity, air flow velocity, etc. This process helps to understand the heat distribution and air flow mode inside the greenhouse, and provides a basis for the subsequent analysis of heat flux and gas exchange effect. By accurately identifying the air heat exchange path, the temperature distribution and heat exchange effect of different areas inside the greenhouse can be effectively predicted, thereby providing data support for environmental control strategies. The material property data related to the structure of the vegetable greenhouse are obtained, including the thermal insulation, light transmittance, thermal conductivity coefficient, etc. of the greenhouse. These material properties directly affect the heat exchange process in the greenhouse, such as temperature maintenance, heat flow and light conduction. By analyzing these material property data, the impact of different materials on the internal environment can be better understood, providing an important basis for further optimizing the heat management and gas exchange effect of the greenhouse. Based on all-weather lighting data, combined with the thermal conductivity characteristics of greenhouse materials, the conduction fluctuation analysis of light source heat is carried out. This analysis helps to reveal how changes in light intensity affect temperature fluctuations in the greenhouse, especially the heat fluctuations conducted to the internal air through the surfaces of different materials. The obtained light source heat conduction fluctuation data can provide a reference for simulating temperature changes and heat distribution, thereby optimizing light and temperature management to ensure heat balance and a suitable growth environment inside the greenhouse. By combining the light source heat conduction fluctuation data with the internal air heat flow exchange path data, a heat flux period temperature and pressure deposition simulation is performed. The simulation process takes into account the changes in temperature and pressure in different time periods and analyzes how heat is deposited and propagated inside the greenhouse. Through this simulation, the temperature and humidity fluctuations in different areas of the greenhouse and their potential impact on crop growth can be predicted, helping to design more efficient temperature control and ventilation systems to maintain an ideal environment for crop growth. Based on the heat flux period temperature and pressure deposition data obtained in the previous stage, a gas exchange barrier effect analysis is performed. Through this analysis, the impact of the distribution of heat and airflow inside the greenhouse on gas exchange is evaluated, especially whether air circulation is hindered under temperature and pressure fluctuations. The gas exchange barrier effect data can reveal the exchange status of gases such as carbon dioxide and oxygen in the greenhouse at different times and regions, which helps to optimize the greenhouse ventilation system and ensure smooth gas exchange, thereby improving the photosynthesis efficiency of crops and the quality of the growth environment.

[0017] Preferably, step S24 includes the following steps:

[0018] Step S241: performing spatiotemporal discretization processing on the light source heat conduction fluctuation data to obtain spatiotemporal discrete data of heat conduction fluctuation;

[0019] Step S242: Calculating the heat density difference of the exchange path between different time periods based on the heat conduction fluctuation spatiotemporal discrete data, and obtaining the heat density difference data of the path;

[0020] Step S243: performing path geometry orientation convection potential difference analysis on the internal air heat exchange path data according to the path heat density difference data to obtain path geometry orientation convection potential difference data;

[0021] Step S244: performing pressure potential difference streamline distribution analysis on the flow potential difference data based on the path geometry orientation to obtain pressure potential difference streamline distribution data;

[0022] Step S245: Perform a heat flux period temperature and pressure deposition simulation on the internal air heat exchange path data according to the path geometry orientation convection potential difference data, pressure potential difference streamline distribution data and path heat density difference data to obtain the heat flux period temperature and pressure deposition data.

[0023] The present invention converts continuous illumination and heat change data into discrete spatiotemporal data that can be analyzed by performing spatiotemporal discretization processing on the heat conduction fluctuation data of the light source. This processing can more clearly reveal the influence of illumination fluctuations at different time periods and spatial positions on the temperature and heat distribution in the greenhouse. Through spatiotemporal discretization, an accurate data format can be provided for subsequent heat density calculation and heat flux simulation, ensuring that the modeling and analysis of the heat conduction process are more refined and efficient. According to the spatiotemporal discrete data of the previous step, the heat density difference between different time periods of the air heat flow exchange path inside the greenhouse is calculated. Through this difference calculation, the change of heat flow in the greenhouse can be identified and quantified, especially the deposition and transfer process of heat on the air flow path under the influence of external factors such as changes in light intensity and temperature. This data provides an important basis for subsequent convection analysis and heat distribution prediction, making the temperature and humidity control in the greenhouse more accurate. Based on the path heat density difference data, the geometric orientation and convection potential difference of the air heat flow exchange path inside the greenhouse are analyzed. The convection potential difference is the airflow driving force caused by the difference in heat density between different regions, which affects the flow direction and speed of the air. Through this analysis, the uneven airflow in the heat transfer path can be identified, especially in areas with large temperature and pressure differences. This information is crucial for optimizing the airflow distribution and air flow strategy in the greenhouse. By analyzing the pressure potential difference streamline distribution of the path geometry and orientation convection potential difference data, the pressure gradient formed by the temperature and heat difference inside the greenhouse and its distribution in space are revealed. The pressure potential difference streamline analysis can clearly point out the main direction of the airflow and its flow change law, which helps to further understand the air flow pattern in the greenhouse. This analysis provides important spatial distribution information for subsequent temperature and humidity control, gas exchange and air circulation optimization, making the greenhouse environment control more scientific and accurate. Combined with the path geometry and orientation convection potential difference data, pressure potential difference streamline distribution data and path heat density difference data, the air heat exchange path inside the greenhouse is comprehensively simulated to obtain the temperature and pressure deposition data during the heat flux period. Through this simulation, the changing laws of temperature, humidity and pressure in the greenhouse in different time periods, as well as the heat deposition process in various areas, can be predicted. The simulation results provide detailed time-space data support for fine-grained control of the greenhouse environment, which helps optimize heat distribution in the greenhouse and improve air circulation and crop growth environment. From time-space discretization to heat flux period simulation, a step-by-step in-depth process has been formed. Through precise analysis and modeling, the dynamic changes of factors such as heat flow, air flow, and gas exchange in the vegetable greenhouse can be fully understood. Each step provides a scientific basis and data support for subsequent environmental optimization, especially the analysis results of path heat density difference, convection potential difference, pressure potential difference streamline, etc., which provide a strong guarantee for the efficiency and accuracy of environmental control.Overall, the implementation of these steps can significantly improve the level of intelligence in vegetable greenhouse environmental management, thereby ensuring the optimal conditions for crop growth and improving production efficiency.

[0024] Preferably, performing path geometric orientation convection potential difference analysis on the internal air heat exchange path data according to the path heat density difference data comprises the following steps:

[0025] The heat density differential gradients on different paths are calculated for the internal air heat flow exchange path data according to the path heat density difference data, so as to obtain the heat density differential gradient data on different paths;

[0026] The heat density differential gradient data on different paths are used to analyze the change of heat convection intensity between horizontal planes to obtain the change data of horizontal heat convection intensity;

[0027] The heat density differential gradient data on different paths are analyzed for vertical heat convection intensity changes to obtain vertical heat convection intensity change data;

[0028] The spatial geometric curl is calculated according to the horizontal heat convection intensity change data and the vertical heat convection intensity change data to obtain the convection spatial geometric curl data;

[0029] The convection cross-section curl difference is calculated based on the convection space geometric curl data to obtain the convection cross-section curl difference;

[0030] According to the convection space geometric curl data and the convection cross-section curl difference, the path geometric orientation convection potential difference analysis is performed on the internal air heat exchange path data to obtain the path geometric orientation convection potential difference data.

[0031] The present invention first calculates the differential gradient of heat density of the internal air heat exchange path according to the path heat density difference data. By performing gradient calculation on the heat density difference on different paths, the heat density change rate on each path is obtained. This helps to accurately understand how heat is distributed and flows in space. The differential gradient data provides a basis for subsequent analysis, can reveal the flow characteristics of heat on different paths, and lay a data foundation for subsequent convection intensity and convection potential difference analysis. The heat density differential gradient data on different paths are analyzed for the change of heat convection intensity between horizontal planes. By analyzing the heat flow intensity on the horizontal plane, the heat flow characteristics of each path in the horizontal direction can be revealed. This analysis can effectively identify the unevenness of heat transfer on the horizontal plane, and then help optimize the management of heat distribution in the space, ensure the efficiency and uniformity of heat exchange, and is of practical significance in space utilization design. In the analysis of the change of heat convection intensity in the vertical direction, the heat density gradient data is used to analyze the change of heat flow intensity on different paths with the vertical direction. This helps to identify and understand the differences and complexity of air flow and heat transfer in the vertical direction, especially in multi-layer structures or vertical flow environments. This analysis helps determine the heat exchange efficiency of different areas, especially in high-rise buildings, ventilation system design and temperature control equipment, and plays an important role in optimizing spatial thermal management. According to the data of heat convection intensity changes in the horizontal and vertical directions, the convection space geometric curl is calculated. Curl can be used to characterize the local rotation characteristics of air flow and the spatial variability of heat convection. The calculation of the convection space geometric curl provides a quantitative indicator for understanding and optimizing the flow of heat in space, helping to identify the vortex phenomenon in air flow and its impact on heat flow. This step can provide an important basis for the optimization of spatial flow patterns and improve the accuracy of air heat flow management. The convection section curl difference is calculated using the convection space geometric curl data and the convection section curl difference. This step can reveal the differences in heat flow between different sections and identify the non-uniformity in the path. The calculation of the curl difference can help evaluate whether the heat flow in different areas has achieved the expected uniformity, further optimize the ventilation and heat exchange strategies, and combine the convection space geometric curl data and the convection section curl difference to perform path geometric orientation convection potential difference analysis. The goal of this step is to evaluate the impact of the spatial geometric orientation of the heat exchange path on the heat flow efficiency. Through this analysis, the impact of the path geometry and direction on heat transfer can be revealed, thus providing a basis for optimizing the design and adjusting the heat flow path. This helps to regulate the heat flow and optimize aerodynamics within the space, ensure the reasonable distribution of the heat exchange path, and improve the overall thermal efficiency of the system.

[0032] Preferably, step S3 comprises the following steps:

[0033] Step S31: Obtaining vegetable environment suitability data;

[0034] Step S32: quantifying the regional temperature and humidity imbalance on the gas exchange barrier effect data and the temperature and pressure deposition data during the heat flux period according to the vegetable environment suitability data, to obtain regional temperature and humidity imbalance quantification data;

[0035] Step S33: Based on the vegetable environment suitability data, the regional temperature and humidity imbalance quantification data and the gas exchange barrier effect data are regulated in stages to obtain regional environment stage regulation data.

[0036] The present invention obtains parameters such as temperature, humidity, and light intensity suitable for vegetable growth by collecting and analyzing environmental data for vegetable growth. These suitable data are the basis for subsequent analysis and decision-making, ensuring that accurate environmental regulation and management can be performed according to the growth requirements of different vegetables. By using the suitable data of the vegetable environment, the gas exchange barrier effect and the temperature and pressure deposition data of the heat flux period in the region are analyzed to quantify the temperature and humidity imbalance in the region. This process quantifies the temperature and humidity imbalance into specific data indicators through data modeling and calculation, helps identify the phenomenon of unsuitable environment in the region, such as excessive temperature difference or low humidity, etc., and provides a scientific basis for subsequent regulation. Based on the suitable data of the vegetable environment, the regional temperature and humidity imbalance quantification data and the gas exchange barrier effect data are analyzed to formulate a targeted environmental regulation strategy. By staged regulation of parameters such as temperature, humidity, and gas exchange, the regional environment is optimized to ensure that vegetables grow under optimal growth conditions. The regulation measures may include adjusting temperature control equipment, increasing humidity, or improving air circulation, etc., to further improve vegetable yield and quality, and ensure the continuous suitability of the growth environment.

[0037] Preferably, step S33 includes the following steps:

[0038] Step S331: performing regional temperature and humidity difference numerical calculation on the regional temperature and humidity imbalance quantification data to obtain regional temperature and humidity difference numerical data;

[0039] Step S332: performing temperature and humidity accumulation intensity analysis between different regions according to the gas exchange barrier effect data and the regional temperature and humidity difference numerical data, and obtaining temperature and humidity accumulation intensity data between different regions;

[0040] Step S333: Based on the gas exchange barrier effect data, the temperature and humidity accumulation intensity data between different areas are regulated by air flow characteristics to obtain air flow characteristics data;

[0041] Step S334: Compensating for the temperature and humidity loss of the vegetable environment suitability data and the temperature and humidity accumulation intensity data between different areas according to the air flow characteristic data, and obtaining the air flow temperature and humidity loss compensation data;

[0042] Step S335: Perform phased control of the regional environment according to the airflow characteristic data and the airflow temperature and humidity loss compensation data to obtain phased control data of the regional environment.

[0043] The present invention calculates the difference of the temperature and humidity imbalance quantification data in the region to obtain the temperature and humidity difference values ​​between different regions. This calculation can quantify the imbalance of temperature and humidity distribution in different regions, reveal which regions have the phenomenon of too high or too low temperature and humidity, and provide clear data support for the subsequent optimization of environmental conditions. This step helps to discover potential environmental problems, thereby providing an important basis for subsequent regulation. By combining the gas exchange barrier effect data with the regional temperature and humidity difference numerical data, the temperature and humidity accumulation intensity between different regions is analyzed. The temperature and humidity accumulation intensity reflects the accumulation of heat and moisture in different regions, and can reveal the phenomenon of abnormal accumulation of temperature and humidity in some regions. Through this analysis, the environmental regions that cause uneven growth of vegetables can be identified, providing data basis for environmental optimization, which helps to carry out regional regulation more targetedly. According to the gas exchange barrier effect and the temperature and humidity accumulation intensity data, the air flow characteristics are regulated. This step improves the gas exchange between regions and optimizes the temperature and humidity distribution by adjusting the speed and direction of the air flow. Good air flow characteristics can help balance the temperature and humidity of each region, eliminate the accumulation effect, and ensure the uniformity of the vegetable growth environment. The regulation of airflow characteristics is crucial to improving air quality and enhancing plant health, and helps to improve the yield and quality of vegetables. Using airflow characteristics data, combined with vegetable environment suitability data and temperature and humidity accumulation intensity in different regions, temperature and humidity loss compensation is performed. Through this compensation process, the temperature and humidity loss caused by poor airflow or environmental imbalance can be corrected to ensure that vegetables can grow under suitable environmental conditions. This compensation mechanism helps to maintain the balance of temperature and humidity, avoid plant growth obstruction caused by improper temperature and humidity, and further improve the growth efficiency of vegetables. Taking into account the airflow characteristics data and airflow temperature and humidity loss compensation data, the regional environment is regulated in stages. The goal of this step is to flexibly adjust parameters such as airflow, temperature and humidity according to environmental requirements in different time periods to ensure that each area is in the most suitable growth state for vegetables. Through precise staged regulation, the adverse effects caused by environmental changes can be effectively avoided, thereby maximizing the growth potential of vegetables, improving resource utilization efficiency and reducing energy consumption.

[0044] Preferably, regulating the airflow characteristics of the temperature and humidity accumulation intensity data between different areas includes the following steps:

[0045] The temperature and humidity accumulation intensity data between different regions are mapped to the local area static airflow density to obtain the local area static airflow density data;

[0046] Calculate the static airflow mass based on the static airflow density data of the local area to obtain the static airflow mass data;

[0047] Based on the gas exchange barrier effect data, the required superposition force for airflow circulation is evaluated on the static airflow mass data to obtain the required superposition force for airflow circulation;

[0048] According to the superposition force required for air flow circulation and the gas exchange barrier effect data, the air flow conveying control angle data is calculated for the static air flow mass data to obtain the air flow conveying control angle data;

[0049] According to the airflow conveying control angle data and the superposition force required for airflow circulation, the static airflow mass data is subjected to the airflow circulation rate balance analysis between regions to obtain the airflow circulation rate balance data;

[0050] Based on the superposition force required for air flow circulation, the air flow delivery control angle data and the air flow rate balance data, the temperature and humidity accumulation intensity data between different areas are used to regulate the air flow characteristics to obtain the air flow characteristics data.

[0051] The present invention generates a static airflow density map of a local area by analyzing the temperature and humidity accumulation intensity data of different areas. Static airflow density refers to the degree of stagnation of airflow in the area, which can reflect the strength of air flow. Through this mapping, it is possible to accurately identify which areas have problems of airflow accumulation or lack of flow. This data provides an intuitive basis for subsequent airflow regulation, which helps to accurately judge the adjustment requirements of airflow, thereby improving the air circulation efficiency of the vegetable growth environment. Based on the static airflow density data of the local area, the static airflow quality is calculated. Static airflow quality refers to the quality of airflow per unit volume, which is usually affected by temperature, humidity and gas composition. By quantifying the airflow quality, the effectiveness and potential environmental impact of airflow in the area can be further evaluated. The key to this step is to determine whether the airflow needs to be adjusted and how to adjust it, so as to help ensure the uniform distribution of airflow in the area to improve the stability of the overall environment. Combined with the gas exchange barrier effect data, the superposition force required for the static airflow quality is evaluated. The superposition force of airflow circulation refers to the external force required to be applied when the airflow passes through different areas to overcome airflow obstruction and barrier effects and ensure that the airflow can flow effectively. This assessment can accurately calculate the required external force, help optimize the airflow regulation scheme, ensure that the airflow can penetrate or bypass the area where there is a gas exchange barrier, and thus improve the efficiency and effect of airflow circulation. According to the superposition force required for airflow circulation and the gas exchange barrier effect data, the control angle of airflow delivery is calculated. The airflow delivery control angle determines the flow direction and path of the airflow and optimizes the airflow distribution. By scientifically calculating a reasonable airflow delivery angle, it can ensure that the airflow is balanced and distributed among the various areas, avoid the phenomenon of airflow concentration, and reduce the accumulation of temperature and humidity in local areas. The optimization of this step can improve the accuracy of environmental control and reduce resource waste. Based on the airflow delivery control angle data and the required superposition force, a balance analysis of the airflow circulation rate is performed. The balance of airflow circulation rate refers to the reasonable distribution of airflow rates between different areas, ensuring that the airflow flows at an appropriate speed in each area, and avoiding environmental imbalance caused by too fast or too slow airflow. Through this balance analysis, the airflow rate between different areas can be accurately adjusted to achieve balanced control of temperature and humidity between areas and optimize the entire planting environment. The superposition force required for airflow circulation, the airflow delivery control angle data, and the circulation rate balance data are combined to control the airflow circulation characteristics of the temperature and humidity accumulation intensity data between different areas. The goal of this regulation is to ensure that the air flow between areas is precisely controlled to optimize the temperature and humidity distribution. By adjusting the flow characteristics of the airflow, it is possible to effectively manage the accumulation of temperature and humidity in different areas, eliminate temperature and humidity differences, and ensure that vegetables grow in the best environment. The resulting airflow characteristics data provides a scientific basis for subsequent environmental optimization.

[0052] Preferably, the flow temperature and humidity loss compensation for the vegetable environment suitability data and the temperature and humidity accumulation intensity data between different areas according to the air flow characteristic data includes the following steps:

[0053] Performing airflow intensity evaluation on the airflow characteristic data to obtain airflow intensity data;

[0054] According to the airflow intensity data, the temperature and humidity accumulation intensity data between different regions are used to calculate the regional temperature and humidity circulation loss difference, and the regional temperature and humidity circulation loss difference data is obtained;

[0055] The regional temperature and humidity circulation loss difference data are analyzed for inter-regional loss superposition to obtain regional temperature and humidity circulation loss superposition data;

[0056] Extract the suitable temperature and humidity for the vegetable environment to obtain the suitable temperature and humidity for the vegetable environment;

[0057] According to the suitable temperature and humidity data of the vegetable environment, the regional temperature and humidity circulation loss superposition data is used to compensate for the circulation temperature and humidity loss, and the air flow circulation temperature and humidity loss compensation data is obtained.

[0058] The present invention can evaluate the intensity of airflow by analyzing the airflow flow characteristic data. This includes analyzing the speed, direction, distribution and other factors of air flow, so as to determine the flow capacity of airflow in different areas. This evaluation result provides data support for subsequent temperature and humidity management, and can reveal the influence range and flow efficiency of airflow in different areas, so as to provide a basis for the optimization of temperature and humidity flow. Based on the airflow flow intensity data, the second step is to reveal the difference in temperature and humidity changes between various areas by performing flow loss differential calculation on the temperature and humidity accumulation intensity data between different areas. Specifically, when the airflow passes through different areas, the flow efficiency of temperature and humidity is different due to factors such as environmental characteristics, airflow speed, and area size, thereby generating temperature and humidity losses. This calculation helps to clarify the temperature and humidity loss level of each area during the airflow flow process, and provides a quantitative basis for subsequent compensation. Through the superposition analysis of the temperature and humidity flow loss differential data of each area, the cumulative effect of temperature and humidity loss in multiple areas during the overall airflow flow process is further evaluated. This analysis can reveal whether the temperature and humidity flow loss between areas has a superposition effect, that is, whether the loss will gradually increase as the airflow passes through multiple areas, thereby affecting the balance of the overall temperature and humidity, and provide a reference for adjustment and compensation strategies. By extracting the suitable temperature and humidity data required for vegetable growth, targeted reference can be provided for environmental management. Different types of vegetables have different requirements for temperature and humidity. Therefore, extracting suitable data for vegetable growth environment can help determine the optimal temperature and humidity range required. In the subsequent compensation process, these data can be used to match the regional circulation loss data to ensure that the temperature and humidity of the vegetable environment meet its growth requirements. According to the suitable temperature and humidity data of the vegetable environment, the temperature and humidity circulation loss superposition data between regions is compensated to achieve the purpose of correcting and optimizing the temperature and humidity circulation effect. By compensating for the temperature and humidity loss during the circulation process, the temperature and humidity distribution can be adjusted to make it more in line with the suitable range for vegetable growth, thereby optimizing the growth environment of vegetables and improving yield and quality. In addition, circulation temperature and humidity loss compensation can also improve energy efficiency and reduce waste in temperature and humidity control.

[0059] Preferably, step S4 comprises the following steps:

[0060] Step S41: performing control logic integration processing on the regional environmental phased control data to obtain environmental control logic integrated data;

[0061] Step S42: constructing an environmental control model for the environmental control logic integration data based on the Boosting algorithm to obtain an environmental control logic model;

[0062] Step S43: Send the environmental control logic model to the cloud platform to perform intelligent control of the vegetable greenhouse environment.

[0063] The present invention first integrates and processes the staged control data of the regional environment, and summarizes the environmental change information of different time periods and different regions. The purpose of this integration process is to logically classify and integrate the control data of various environmental factors such as temperature, humidity, airflow, and light to form a clear control framework. These data can help identify the most suitable control strategy by analyzing the needs and change trends of different regions, and provide a basis for the subsequent intelligent decision-making system. The beneficial effect of this step is that the law of environmental change in each stage can be clearly depicted, laying a data foundation for precise control. The Boosting algorithm is used to process the environmental control logic integration data and construct an environmental control model. Boosting is an integrated learning method that can effectively improve the prediction ability and accuracy of the model by training weak learners multiple times and combining their prediction results. In the environmental control of vegetable greenhouses, the Boosting algorithm can process complex environmental data relationships, identify key factors affecting environmental changes, and optimize control strategies. Through the construction of the model, the changing trends of different environmental factors can be accurately predicted, and a more intelligent and dynamic control scheme can be formulated. Its beneficial effect is to improve the accuracy and response speed of the control system and achieve efficient management of the environment. Finally, the constructed environment control logic model will be uploaded to the cloud platform for further execution and real-time monitoring. The cloud platform can realize remote management and monitoring, and adjust the environmental control strategy according to the real-time data from the greenhouse. Through the computing and scheduling capabilities of the cloud platform, it can process a large amount of sensor data and environmental information, automatically adjust temperature, humidity, light and other conditions, and ensure that the environment in the vegetable greenhouse is always in the most suitable state. The beneficial effect of this step is to realize the automation and intelligence of environmental control, improve operational efficiency and response speed, reduce manual intervention, reduce management costs, and ensure the continuous optimization of vegetable growth.

[0064] Preferably, the present invention further provides an intelligent control system for a vegetable greenhouse environment, which is used to execute the intelligent control method for a vegetable greenhouse environment as described above, and the intelligent control system for a vegetable greenhouse environment comprises:

[0065] Environmental data acquisition module, used to obtain all-weather lighting data of the vegetable greenhouse and internal environmental data of the vegetable greenhouse through sensors;

[0066] The heat deposition analysis module is used to identify the air heat flow exchange path based on the internal environment data of the vegetable greenhouse to obtain the internal air heat flow exchange path data; perform a heat flux period temperature and pressure deposition simulation on the internal air heat flow exchange path data according to the all-weather lighting data of the vegetable greenhouse to obtain the heat flux period temperature and pressure deposition data; perform a gas exchange barrier effect analysis based on the heat flux period temperature and pressure deposition data to obtain the gas exchange barrier effect data;

[0067] The regional environment control module is used to obtain the vegetable environment suitability data; based on the vegetable environment suitability data, the gas exchange barrier effect data is controlled in a phased manner to obtain the regional environment phased control data;

[0068] The environmental control model construction module is used to construct the environmental control model for the regional environmental phased control data to obtain the environmental control logic model; the environmental control logic model is sent to the cloud platform to execute intelligent control of the vegetable greenhouse environment.

[0069] The beneficial effects of the present invention are that the present invention optimizes a traditional intelligent control method for vegetable greenhouse environment, solves the problems of inaccurate temperature and heat flux interaction analysis and large error in regional environmental control in the traditional intelligent control method for vegetable greenhouse environment, improves the accuracy of temperature and heat flux interaction analysis, and reduces the error in regional environmental control. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Figure 1 A schematic diagram of the steps of a method for intelligently controlling the environment of a vegetable greenhouse;

[0071] Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart;

[0072] Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0073] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0074] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0075] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0076] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0077] To achieve this, please refer to Figures 1 to 3 , a method for intelligently controlling the environment of a vegetable greenhouse, the method comprising the following steps:

[0078] Step S1: Obtaining all-weather lighting data of the vegetable greenhouse and internal environment data of the vegetable greenhouse through sensors;

[0079] Step S2: Based on the internal environment data of the vegetable greenhouse, the air heat exchange path is identified to obtain the internal air heat exchange path data; based on the all-weather lighting data of the vegetable greenhouse, the internal air heat exchange path data is simulated for the temperature and pressure deposition during the heat flux period to obtain the temperature and pressure deposition data during the heat flux period; based on the temperature and pressure deposition data during the heat flux period, the gas exchange barrier effect is analyzed to obtain the gas exchange barrier effect data;

[0080] Step S3: Acquire vegetable environment suitability data; perform regional environmental stage-by-stage regulation on the gas exchange barrier effect data based on the vegetable environment suitability data to obtain regional environmental stage-by-stage regulation data;

[0081] Step S4: construct an environmental control model for the regional environmental phased control data to obtain an environmental control logic model; send the environmental control logic model to the cloud platform to perform intelligent control of the vegetable greenhouse environment.

[0082] In the embodiment of the present invention, reference Figure 1 The figure is a schematic diagram of the steps of a method for intelligently controlling the environment of a vegetable greenhouse according to the present invention. In this example, the method for intelligently controlling the environment of a vegetable greenhouse includes the following steps:

[0083] Step S1: Obtaining all-weather lighting data of the vegetable greenhouse and internal environment data of the vegetable greenhouse through sensors;

[0084] In an embodiment of the present invention, by arranging light sensors and environmental sensors in the vegetable greenhouse, data on all-weather light intensity and environmental parameters such as temperature, humidity, and carbon dioxide concentration in the greenhouse are collected respectively. Light sensors need to be placed at different heights and positions to capture evenly distributed light information to ensure that there are no blind spots within the coverage area. Environmental sensors need to be arranged in an evenly spaced grid to avoid obstructions that affect their measurement accuracy. The collected data is transmitted to a central storage device in real time via wired or wireless means, and is uniformly stored as a data set in the form of a time series. The data format uses a standard tabular form, and the fields include collection time, sensor number, location, measurement value, etc.

[0085] Step S2: Based on the internal environment data of the vegetable greenhouse, the air heat exchange path is identified to obtain the internal air heat exchange path data; based on the all-weather lighting data of the vegetable greenhouse, the internal air heat exchange path data is simulated for the temperature and pressure deposition during the heat flux period to obtain the temperature and pressure deposition data during the heat flux period; based on the temperature and pressure deposition data during the heat flux period, the gas exchange barrier effect is analyzed to obtain the gas exchange barrier effect data;

[0086] In an embodiment of the present invention, the data of the environmental sensor in the greenhouse is used to identify the temporal and spatial variation characteristics of temperature and humidity by establishing a set of equations based on physical thermodynamics. The finite difference method is used to calculate the thermal gradient of each area inside the greenhouse, and the main path of air heat flow is analyzed in combination with the principle of fluid dynamics. The output data includes a heat flow path diagram and main node information. The distribution of heat flux inside the greenhouse in different time periods is simulated based on the energy conservation theory and the heat diffusion equation by using the changes in light intensity in the all-weather lighting data, combined with the heat flow path. The numerical integration method is used to calculate the heat distribution in each time period in sections, and the gradient deposition characteristic data of temperature and air pressure are obtained. The output data is "heat flux time period temperature and pressure deposition data", which includes a distribution diagram and a time axis decomposition. According to the heat flux time period temperature and pressure deposition data, the molecular diffusion and convection heat transfer theory are applied to quantify the gas exchange rate in different areas, and the barrier effect model is constructed in combination with the actual barrier position in the greenhouse (such as pillars and shade cloth). The scope and degree of influence of internal barriers on gas exchange in the greenhouse are calculated through an iterative algorithm, and the "gas exchange barrier effect data" is output, including the barrier factor value and the influence distribution map.

[0087] Step S3: Acquire vegetable environment suitability data; perform regional environmental stage-by-stage regulation on the gas exchange barrier effect data based on the vegetable environment suitability data to obtain regional environmental stage-by-stage regulation data;

[0088] In an embodiment of the present invention, a target environmental condition parameter set is constructed based on the growth requirements of different vegetables, with reference to botanical literature and agricultural practice data, including suitable temperature, humidity, light intensity, carbon dioxide concentration, etc. Based on the vegetable environmental suitability data, the gas exchange barrier effect data is compared and analyzed. By comparing the current data and the target data, the substandard regional environmental parameters are identified, and the phased control periods are divided according to the characteristics of environmental fluctuations. The linear programming method is used to allocate control resources so that the environmental conditions gradually approach the target values, and "regional environmental phased control data" is generated, including the control parameter adjustment plan and priority ranking for each period.

[0089] Step S4: construct an environmental control model for the regional environmental phased control data to obtain an environmental control logic model; send the environmental control logic model to the cloud platform to perform intelligent control of the vegetable greenhouse environment.

[0090] In an embodiment of the present invention, the adjustment scheme in the regional environmental phased control data is converted into an executable control rule. A decision tree algorithm is used to generate a rule chain, and the current state of the environmental parameters is associated with the control measures corresponding to the target state to generate a tree-shaped logical structure. The logical node includes a trigger condition and an execution operation, and the leaf node stores specific control instructions, such as turning on or off a fan, heater, etc. The constructed environmental control logic model is uploaded to the cloud platform through a network protocol (such as MQTT or HTTP). On the cloud platform, the model is decomposed into specific control instructions, and the operation is implemented through the greenhouse's execution equipment (such as ventilation equipment, shading equipment, spray devices, etc.) to adjust the environmental parameters in the greenhouse. The cloud platform also monitors the feedback data to ensure that the execution effect meets expectations, and records the new environmental status data in real time for subsequent optimization.

[0091] Step S2 includes the following steps:

[0092] Step S21: identifying the air heat flow exchange path based on the internal environment data of the vegetable greenhouse to obtain the internal air heat flow exchange path data;

[0093] Step S22: Acquire greenhouse material characteristic data;

[0094] Step S23: performing light source heat conduction fluctuation analysis on greenhouse material characteristic data according to the all-weather illumination data of the vegetable greenhouse to obtain light source heat conduction fluctuation data;

[0095] Step S24: performing a heat flux period temperature and pressure deposition simulation on the internal air heat exchange path data based on the light source heat conduction fluctuation data to obtain the heat flux period temperature and pressure deposition data;

[0096] Step S25: performing a gas exchange barrier effect analysis on the internal air heat flow exchange path data according to the heat flux period temperature and pressure deposition data to obtain gas exchange barrier effect data.

[0097] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0098] Step S21: identifying the air heat flow exchange path based on the internal environment data of the vegetable greenhouse to obtain the internal air heat flow exchange path data;

[0099] In an embodiment of the present invention, based on environmental parameters such as temperature, humidity, wind speed, etc. in the vegetable greenhouse, a multivariate interpolation algorithm is used to construct a spatial distribution field and identify the air heat exchange path. First, real-time environmental data is obtained by arranging evenly distributed multi-point sensors in the vegetable greenhouse, and these data are generated into a multidimensional matrix with point distribution according to the sensor position. Subsequently, the data is spatially expanded using the Kriging interpolation method to obtain a continuous distribution field of each environmental variable. Next, the fluid dynamics equations (Navier-Stokes equations) are used to calculate the velocity field and flow field of the air flow path with the temperature and humidity gradient as the driving force, combined with the wind speed and airflow direction. Through iterative calculation, the main air heat exchange path and its flow intensity in the greenhouse are determined, and the output "internal air heat exchange path data" includes the spatial and temporal distribution of the path coordinate points, flow velocity, flow direction and flow rate.

[0100] Step S22: Acquire greenhouse material characteristic data;

[0101] In the embodiment of the present invention, the thermal and optical property data of the main structural materials of the vegetable greenhouse are obtained through laboratory testing and literature review. The laboratory test includes the measurement of thermal conductivity, specific heat capacity, light transmittance and reflectance, and the specific test operation adopts the steady-state plate method and spectrophotometer. For some materials that have not been experimented, the material characteristic parameters are supplemented with literature data. All data are standardized and organized into a data table format, and the fields include material name, density, thermal conductivity, specific heat capacity, light transmittance, absorptivity, reflectivity and test condition description to generate "greenhouse material characteristic data".

[0102] Step S23: performing light source heat conduction fluctuation analysis on greenhouse material characteristic data according to the all-weather illumination data of the vegetable greenhouse to obtain light source heat conduction fluctuation data;

[0103] In an embodiment of the present invention, the dynamic influence of light intensity on the thermal conductivity characteristics of greenhouse materials is analyzed based on the all-weather lighting data collected in real time and the light and heat characteristics data of greenhouse materials. First, the all-weather lighting data is input in the form of a time series, and the change curve of the light energy density per unit time is calculated. Then, according to the light transmittance and absorptivity of the material, the amount of light energy absorbed on the surface of the material is calculated, and combined with the Fourier heat conduction equation, the law of heat energy transfer along the inside of the material is determined. The specific calculation adopts the finite difference method, with the thermal conductivity and specific heat capacity of the material as the core parameters, and the heat conduction is gradually iterated to generate the material internal temperature distribution and heat flux density change data of the time series. By calculating the transfer fluctuation amplitude and delay characteristics of heat energy under different light intensity conditions, the "light source heat conduction fluctuation data" outputted includes key parameters such as material surface temperature change, dynamic distribution of heat flux density and conduction fluctuation delay.

[0104] Step S24: performing a heat flux period temperature and pressure deposition simulation on the internal air heat exchange path data based on the light source heat conduction fluctuation data to obtain the heat flux period temperature and pressure deposition data;

[0105] In an embodiment of the present invention, the heat flux distribution and temperature and pressure deposition process of a specific period in a vegetable greenhouse are simulated by using the heat conduction fluctuation data of the light source and the internal air heat flow exchange path data. First, the time series of the heat conduction fluctuation data of the light source and the flow field information of the internal air heat flow exchange path data are synchronized, and the light heat conduction distribution and the air heat flow motion characteristics at the same time point are coupled and calculated. In the calculation process, a thermodynamic equation group based on energy conservation and mass conservation is adopted, in which the heat flux density is calculated by Fourier's heat conduction law, and the pressure change is simulated by the ideal gas state equation combined with air humidity compensation correction. Secondly, the accumulated heat and pressure of each area in the greenhouse in different time periods are calculated by the numerical integration method, and the temperature and pressure distribution diagram of each time period is generated. Finally, the calculation results are marked by region, the heat deposition and pressure change characteristics of each area are recorded, and the "heat flux time period temperature and pressure deposition data" are output. The data includes the heat flux density, temperature distribution, pressure distribution and corresponding coordinate information of each time period in the greenhouse.

[0106] Step S25: performing a gas exchange barrier effect analysis on the internal air heat flow exchange path data according to the heat flux period temperature and pressure deposition data to obtain gas exchange barrier effect data.

[0107] In an embodiment of the present invention, based on the temperature and pressure deposition data of the heat flux period, the barrier effect of the temperature and pressure gradient on the gas exchange inside the greenhouse is analyzed. First, the distribution information of the temperature and pressure deposition data of the heat flux period is superimposed with the air heat flow exchange path data, and the temperature gradient and pressure gradient at each path node are calculated to identify the influence area of ​​the heat and pressure change on the gas flow. Then, the critical conditions of laminar and turbulent flow in fluid mechanics are used, combined with the dynamic changes of gas density difference and viscosity, to calculate the effective flux change of each air flow path. During the calculation process, with the Bernoulli equation as the core, the velocity and flow rate of the airflow under different temperature and pressure conditions are corrected, and the flow barrier area and key barrier factors are identified. Finally, the analysis results are output in the form of a path diagram, and the flux change and barrier effect index of each path are marked to generate "gas exchange barrier effect data". The data includes the coordinate range of the barrier area, the gas flux reduction ratio, the flow direction offset and the temperature and pressure gradient characteristics.

[0108] Step S24 includes the following steps:

[0109] Step S241: performing spatiotemporal discretization processing on the light source heat conduction fluctuation data to obtain spatiotemporal discrete data of heat conduction fluctuation;

[0110] Step S242: Calculating the heat density difference of the exchange path between different time periods based on the heat conduction fluctuation spatiotemporal discrete data, and obtaining the heat density difference data of the path;

[0111] Step S243: performing path geometry orientation convection potential difference analysis on the internal air heat exchange path data according to the path heat density difference data to obtain path geometry orientation convection potential difference data;

[0112] Step S244: performing pressure potential difference streamline distribution analysis on the flow potential difference data based on the path geometry orientation to obtain pressure potential difference streamline distribution data;

[0113] Step S245: Perform a heat flux period temperature and pressure deposition simulation on the internal air heat exchange path data according to the path geometry orientation convection potential difference data, pressure potential difference streamline distribution data and path heat density difference data to obtain the heat flux period temperature and pressure deposition data.

[0114] In the embodiment of the present invention, the light source heat conduction fluctuation data is processed by time and space discretization to facilitate data matching and calculation optimization in subsequent analysis. First, based on the collected greenhouse all-weather lighting data and the dynamic changes of its heat conduction effect, the data is divided into small time steps according to the time dimension. Usually, the light data of a day is divided into a time node per minute to form a time series discretization unit. Secondly, according to the three-dimensional coordinate information of the greenhouse geometric structure, the spatial dimension is divided, and the internal space of the greenhouse is divided into several equal units by the finite volume method, and each unit is used as the basic calculation unit of heat conduction. Subsequently, the heat conduction data in the discrete unit is redistributed by using the interpolation algorithm to ensure that the data maintains the spatial continuity of light heat conduction during the discretization process. Finally, the discretized time node is associated with the spatial unit data to generate a heat value table containing each time point and the corresponding spatial unit, and the result is output as "heat conduction fluctuation time and space discrete data". The heat conduction fluctuation time and space discrete data is coupled with the internal air heat flow exchange path data for analysis, and the density difference of heat transferred along the path in different time periods is calculated. First, the predefined air heat exchange path in the greenhouse is selected. Each path is divided into multiple segment nodes according to the direction of heat flow. The position of each node is aligned with the spatial unit of the discrete spatiotemporal data of heat conduction fluctuations. Secondly, at each path segment node, the heat value of different time periods is extracted, and the difference method is used to calculate the difference in heat density changes in adjacent time periods. The calculation formula of heat density is: the heat value divided by the volume of the spatial unit of the path node, which reflects the change of heat per unit volume. Subsequently, the difference of different time periods of each segment node on each path is accumulated to generate a heat density difference distribution map of the entire path. Finally, the time series heat density difference data of each path is recorded and output as "path heat density difference data". Based on the path heat density difference data, the influence of geometric orientation on the air heat flow convection potential difference is analyzed, and a quantitative model of the relationship between heat distribution and path direction is established. First, according to the three-dimensional geometric orientation data of the path, the direction vector and angle change information of each path segment are extracted. The temperature gradient between the path segments and its projection on the direction vector are calculated through the path heat density difference data, and the consistency between the temperature gradient and the path direction is identified. Secondly, the convection potential difference calculation formula is used: p=kt cosθ, where p is the convection potential difference, k is the aerodynamic constant, t is the temperature gradient, and θ represents the angle between the path direction and the temperature gradient direction, where θ is not equal to 90 degrees and 270 degrees, to calculate the convection potential difference value of each segment in the path. Subsequently, the segmented convection potential difference values ​​of each path are accumulated to form an overall convection potential difference distribution map. Finally, a comprehensive data table containing the path geometry and the corresponding convection potential difference values ​​is generated and output as "path geometry and orientation convection potential difference data".In another embodiment, the path geometry orientation convection potential difference analysis of the internal air heat exchange path data can also be combined with the path heat density difference data and the geometric layout information of the path to perform a segmented analysis on the heat flow direction of each path. The path geometry layout information is defined by the three-dimensional coordinate points in the greenhouse, and each path is divided into multiple direction vectors. The convection potential difference of each path segment is calculated by performing a dot product operation on the path direction vector and the heat density difference to obtain the degree of directional consistency. The positive and negative properties of the convection potential difference are used to distinguish the directional characteristics of heat flow. Then, the convection potential difference data and the path geometry information are superimposed to generate a geometric orientation convection potential difference distribution map of the path. The distribution map represents the directionality and intensity of convection by the arrow direction and the arrow size. Finally, the path geometry orientation convection potential difference data file is exported, and the data content includes the convection potential difference value, the direction vector, and the heat density difference sequence of each path segment for subsequent analysis steps. The convective potential difference value and direction vector of each path segment are extracted from the path geometric orientation convective potential difference data. Combined with the air pressure distribution data inside the vegetable greenhouse, the pressure potential difference value on the path is loaded into the three-dimensional path model. Secondly, the distribution characteristics of the streamlines are calculated using the pressure potential difference value and geometric orientation information. The pressure difference value of the path segment is subjected to gradient analysis, and the pressure gradient direction is determined by calculating the pressure change rate between each path segment. Next, the streamlines in the path are fitted using fluid dynamics theory. The continuity and stability of the streamline distribution are ensured by the continuity equation, and finally a streamline distribution map is generated. Finally, a pressure potential difference streamline distribution data file is generated, which contains the streamline direction, pressure gradient value and streamline distribution intensity of each path segment as the basic data for subsequent heat flux simulation. The path geometric orientation convective potential difference data, pressure potential difference streamline distribution data and path heat density difference data are input into the heat flux simulation tool, and the data are spatially superimposed and time-synchronized. The spatial superposition uses the path node as the benchmark to comprehensively match the values ​​of different data sources. Then, a time series model of heat flux is established. The time dimension is divided into multiple segments, and the heat flux distribution value on the path in each time period is calculated separately. The heat flux value is determined by the heat density difference and the streamline distribution intensity. Next, the temperature and pressure deposition characteristics on the path are analyzed. In each time period, the temperature and pressure deposition are cumulatively calculated according to the heat flux change rate of the path node, and the high temperature and high pressure areas are marked. Finally, a heat flux period temperature and pressure deposition data file is generated, which includes the heat flux distribution map, temperature and pressure deposition matrix, and high temperature and high pressure marked areas in each time period, providing a basis for greenhouse environmental control strategies.

[0115] Performing path geometry orientation convection potential difference analysis on internal air heat exchange path data based on path heat density difference data includes the following steps:

[0116] The heat density differential gradients on different paths are calculated for the internal air heat flow exchange path data according to the path heat density difference data, so as to obtain the heat density differential gradient data on different paths;

[0117] The heat density differential gradient data on different paths are used to analyze the change of heat convection intensity between horizontal planes to obtain the change data of horizontal heat convection intensity;

[0118] The heat density differential gradient data on different paths are analyzed for vertical heat convection intensity changes to obtain vertical heat convection intensity change data;

[0119] The spatial geometric curl is calculated according to the horizontal heat convection intensity change data and the vertical heat convection intensity change data to obtain the convection spatial geometric curl data;

[0120] The convection cross-section curl difference is calculated based on the convection space geometric curl data to obtain the convection cross-section curl difference;

[0121] According to the convection space geometric curl data and the convection cross-section curl difference, the path geometric orientation convection potential difference analysis is performed on the internal air heat exchange path data to obtain the path geometric orientation convection potential difference data.

[0122] In an embodiment of the present invention, the path heat density difference data is arranged in order according to the path nodes to construct the heat density distribution curve of each path. The data of each path is fitted using a piecewise linear function to ensure the continuity of the data change. The first-order derivative of the fitted curve is calculated to obtain the gradient value of the heat density changing with the path. The gradient value is calculated by the difference method, that is, between every two adjacent nodes of the path, after the calculation is completed, the heat density differential gradient value is recorded according to the spatial coordinates of the path node, and a heat density differential gradient data table on different paths is generated. The data table contains the path number, node coordinates and their corresponding gradient value information, which is convenient for subsequent spatial convection analysis. The node gradient values ​​belonging to the same horizontal plane in the path heat density differential gradient data are extracted, and the gradient value distribution in the horizontal planes of different heights is collected in layers based on the ground in the greenhouse. The mean and standard deviation of the heat density gradient in each horizontal plane are calculated by statistical methods, and the gradient change law between the paths is analyzed. The basic principle of heat convection is used to characterize the convection intensity. The heat gradient difference between adjacent horizontal planes is calculated. After the calculation is completed, a horizontal heat convection intensity change data is generated, which includes the height, gradient mean, standard deviation of each horizontal plane and the gradient difference of adjacent horizontal planes. The vertical coordinate information of the path segment is extracted from the heat density differential gradient data, and the gradient distribution of each path in the vertical direction is analyzed. Through three-dimensional coordinate transformation, the direction vector of the path segment is decomposed into vertical components, and the vertical gradient value of each path segment is calculated. The vertical gradient value of the path is summarized to the corresponding height level by the accumulation method of vertical components, and its mean is calculated. The vertical gradient changes between different height levels are compared by the cumulative comparison method, and the changes in the convection intensity of heat in the vertical direction are analyzed. After the calculation is completed, a vertical heat convection intensity change data is generated, which includes the vertical gradient mean and its change intensity information of each height level. Combining the horizontal heat convection intensity change data and the vertical heat convection intensity change data, the heat flow direction and intensity of each path point are processed in three dimensions, and the heat flow vector field of the path point is constructed. The curl value is calculated by numerical difference method, and the three components of the curl are calculated based on the neighborhood gradient value of the path point. The curl values ​​of all path points are summarized to generate the geometric curl data of the convection space and recorded in the form of a three-dimensional vector field. The curl value of the path section is extracted from the geometric curl data of the convection space, and the specific section position is selected as the analysis area. The curl value in the section is integrated to obtain the cross-sectional curl intensity, and the curl difference between different sections is compared. The cross-sectional curl is accumulated by numerical integration method, and the difference in total curl between sections is compared to quantify the curl change of the convection section. After the calculation is completed, the convection section curl difference data table is generated. The geometric orientation convection potential difference characteristics of the path are analyzed using the convection space geometric curl data and the convection section curl difference.The dot product operation is performed on the direction vector and the curl vector of each path to calculate the coupling strength between the path direction and the convective curl. According to the positive and negative value and absolute value of the coupling strength value, the convective potential difference direction and intensity level of the path are marked. Finally, the path geometric orientation convective potential difference data file is generated, which includes the path number, direction vector, curl value and potential difference intensity information, providing complete data support for subsequent thermal flow analysis.

[0123] Step S3 includes the following steps:

[0124] Step S31: Obtaining vegetable environment suitability data;

[0125] Step S32: quantifying the regional temperature and humidity imbalance on the gas exchange barrier effect data and the temperature and pressure deposition data during the heat flux period according to the vegetable environment suitability data, to obtain regional temperature and humidity imbalance quantification data;

[0126] Step S33: Based on the vegetable environment suitability data, the regional temperature and humidity imbalance quantification data and the gas exchange barrier effect data are regulated in stages to obtain regional environment stage regulation data.

[0127] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes:

[0128] Step S31: Obtaining vegetable environment suitability data;

[0129] In the embodiment of the present invention, first, the vegetable variety to be planted is determined. Different vegetables have different requirements for environmental conditions, including temperature, humidity, light intensity, CO 2 concentration, etc. By consulting agricultural research materials, planting manuals or communicating with agricultural experts, you can find out the best growing conditions for each vegetable. For example, the suitable growing temperature for tomatoes is 20-25°C and the humidity is 60%-70%, while the suitable temperature for lettuce is 15-18°C and the humidity is 70%-80%.

[0130] Step S32: quantifying the regional temperature and humidity imbalance on the gas exchange barrier effect data and the temperature and pressure deposition data during the heat flux period according to the vegetable environment suitability data, to obtain regional temperature and humidity imbalance quantification data;

[0131] In the embodiment of the present invention, the regional temperature and humidity imbalance quantification is based on the vegetable environment suitability data, and the gas exchange barrier effect data and the temperature and pressure deposition data of the heat flux period are systematically analyzed. First, the actual temperature and humidity values ​​of each region in the vegetable environment suitability data are extracted, and the difference calculation is performed with the standard suitable range to obtain preliminary temperature and humidity imbalance data. The difference calculation adopts the point-by-point comparison method to compare the value of each sampling point in the region with the benchmark independently, and record the type of excess (too high or too low). Secondly, the regional information of air flow restriction is obtained from the gas exchange barrier effect data. This information includes gas flow velocity, obstacle distribution and the degree of obstruction to temperature and humidity diffusion. Such data are superimposed and analyzed with the preliminary imbalance data, and the temperature and humidity gradient enhancement area caused by the gas barrier effect is calculated by the vector superposition method to form a spatial correlation map. At the same time, the heat accumulation of each region is extracted from the temperature and pressure deposition data of the heat flux period. These data are interpolated using the heat pressure distribution law to calculate the periodic influence of heat conduction in each region on the temperature and humidity imbalance. Finally, through superposition analysis, the above three types of data are integrated into a unified three-dimensional coordinate system, and the grid integration method is used to calculate the comprehensive imbalance value in each cell to generate regional temperature and humidity imbalance quantitative data. The quantitative data is recorded in the form of a matrix, which contains information such as the imbalance value size, type and spatial location.

[0132] Step S33: Based on the vegetable environment suitability data, the regional temperature and humidity imbalance quantification data and the gas exchange barrier effect data are regulated in stages to obtain regional environment stage regulation data.

[0133] In the embodiment of the present invention, the phased regulation of the regional environment takes the vegetable environment suitability data as the target benchmark, and combines the regional temperature and humidity imbalance quantitative data and the gas exchange barrier effect data to formulate a regional regulation plan. First, according to the imbalance degree and type of each area in the temperature and humidity imbalance quantitative data, the greenhouse space is divided into high imbalance area, medium imbalance area and low imbalance area. The division standard adopts the quantile method, and the data is sorted by size and then segmented according to the proportion. For each area, the air flow condition is analyzed in combination with the gas exchange barrier effect data. The finite difference method is used to simulate the air flow diffusion path in the area, and the optimal layout position of the control equipment (such as fans or vents) is located. On this basis, ventilation adjustment is given priority to the high imbalance area, and its temperature and humidity imbalance value is reduced by changing the wind speed and direction of the fan. At the same time, the temperature and pressure deposition data of the heat flux period are reversely analyzed to evaluate its impact on the imbalance area. For areas that are greatly affected by heat deposition, local heat accumulation can be reduced by adding shading curtains and reducing light intensity; while for areas with more heat loss, heat retention is improved by using insulation materials or adjusting the heat source configuration. The control process adopts a time-division control strategy, and formulates operation plans according to the different changing rules of the daytime and nighttime environments. After the control is completed, the real-time collection values ​​of the control equipment operating parameters and environmental factors in each area are recorded to generate regional environmental stage control data. The control data table contains equipment operating time, adjustment parameters, spatial distribution and corresponding environmental change information, providing data support for subsequent refined management.

[0134] Step S33 includes the following steps:

[0135] Step S331: performing regional temperature and humidity difference numerical calculation on the regional temperature and humidity imbalance quantification data to obtain regional temperature and humidity difference numerical data;

[0136] Step S332: performing temperature and humidity accumulation intensity analysis between different regions according to the gas exchange barrier effect data and the regional temperature and humidity difference numerical data, and obtaining temperature and humidity accumulation intensity data between different regions;

[0137] Step S333: Based on the gas exchange barrier effect data, the temperature and humidity accumulation intensity data between different areas are regulated by air flow characteristics to obtain air flow characteristics data;

[0138] Step S334: Compensating for the temperature and humidity loss of the vegetable environment suitability data and the temperature and humidity accumulation intensity data between different areas according to the air flow characteristic data, and obtaining the air flow temperature and humidity loss compensation data;

[0139] Step S335: Perform phased control of the regional environment according to the airflow characteristic data and the airflow temperature and humidity loss compensation data to obtain phased control data of the regional environment.

[0140] In the embodiment of the present invention, the regional temperature and humidity difference numerical calculation is based on the regional temperature and humidity imbalance quantitative data, and is completed by the point-by-point difference calculation method. First, the area in the greenhouse is divided into several equally divided grids, each grid represents an independent calculation unit. In each unit, the temperature and humidity imbalance quantitative data are extracted, including the temperature deviation value and the humidity deviation value. Then, the temperature and humidity data between adjacent grids are numerically differentiated to obtain the temperature and humidity difference values ​​between regions. The regional temperature and humidity accumulation intensity analysis is completed by quantifying the relationship between the degree of gas exchange restriction and the temperature and humidity difference in the region. In order to deal with multi-point differences in the region, all difference values ​​are integrated using a weighted average method, and the weight is determined based on the sampling frequency and coverage area of ​​the sensor in the grid. The difference data is recorded in a matrix form, and each element corresponds to the average temperature and humidity difference value of a grid. Finally, the completed regional temperature and humidity difference numerical data provides a basis for subsequent accumulation intensity analysis. The airflow channel resistance value and gas circulation velocity information of each region are extracted from the gas exchange barrier effect data. These data are obtained by measuring the vent position and the fan operation rate, and analyzing the velocity vector field of the local air flow. Secondly, the gas barrier effect data is superimposed with the regional temperature and humidity difference numerical data. The temperature and humidity accumulation intensity is calculated by accumulating the temperature difference and humidity difference in the region and dividing it by the gas flow resistance value in the region. Among them, the temperature difference and humidity difference represent the degree of imbalance of temperature and humidity in the region, respectively, and the gas flow resistance value reflects the difficulty of airflow exchange. It can be understood that the imbalance of temperature and humidity is combined with the obstruction of gas flow to obtain the intensity of temperature and humidity accumulation in the region. The regulation of airflow characteristics aims to optimize gas exchange and reduce temperature and humidity accumulation. During the regulation process, the airflow accumulation points and the areas with large gas resistance are first analyzed, and the airflow distribution path is simulated by finite element analysis, and the airflow velocity change and the location of resistance concentration in the channel are calibrated. According to the simulation results, the fan operating parameters are adjusted, including wind speed, wind direction and opening and closing time. For areas with high accumulation intensity, the fan flow is increased to enhance gas exchange; for areas with strong gas barrier effect, the ventilation hole layout is redesigned to reduce flow resistance. At the same time, the real-time monitoring data of the wind speed sensor is combined to verify the regulation effect to ensure that the adjusted airflow characteristics meet the expected requirements. After the control is completed, the changes in wind speed, air pressure and airflow direction in each area are recorded, and the data is stored as airflow characteristic data for the next step of circulation temperature and humidity loss compensation. Circulation temperature and humidity loss compensation is based on airflow characteristic data and vegetable environment suitability data, with the goal of reducing heat and humidity losses during airflow circulation. First, analyze the temperature and humidity losses that occur in the airflow circulation path, including the temperature and humidity differences when air is transmitted between different areas. The energy conservation method and humidity balance equation are used to calculate the heat loss and moisture loss of the airflow during transmission. Based on these calculation results, heating devices or humidification equipment are arranged in high-loss areas.For example, by adding a humidifier at the end of the ventilation path to increase air humidity, or installing an auxiliary heating device at the starting point of ventilation to reduce heat attenuation during transmission. After the compensation operation, the compensated temperature and humidity values ​​are measured and compared with the vegetable environment suitability data. The compensation data is recorded in the form of time series and spatial distribution to form airflow temperature and humidity loss compensation data. The regional environmental phased regulation aims at global optimization, comprehensively considers the airflow characteristic data and the temperature and humidity loss compensation data, and achieves the dynamic balance of the greenhouse environment through phased adjustment. During the regulation process, a regional and phased operation plan is formulated, and the temperature and humidity parameters are adjusted for high imbalance areas, such as adjusting the ventilation frequency and adding additional regulation equipment. During the implementation of the regulation, the temperature and humidity changes in each area are monitored in real time, the actual effect is fed back by the sensor network, and the impact of the adjustment on other areas is calculated in combination with the data model. If the regulation does not meet the target requirements, the optimization process is repeated until all areas reach a stable state. Finally, the regional environmental phased regulation data formed includes the target value, real-time value and adjustment parameters of each area, comprehensively records the details of the changes in the regulation process, and provides support for subsequent long-term intelligent regulation.

[0141] The air flow characteristics control based on the temperature and humidity accumulation intensity data between different areas includes the following steps:

[0142] The temperature and humidity accumulation intensity data between different regions are mapped to the local area static airflow density to obtain the local area static airflow density data;

[0143] Calculate the static airflow mass based on the static airflow density data of the local area to obtain the static airflow mass data;

[0144] Based on the gas exchange barrier effect data, the required superposition force for airflow circulation is evaluated on the static airflow mass data to obtain the required superposition force for airflow circulation;

[0145] According to the superposition force required for air flow circulation and the gas exchange barrier effect data, the air flow conveying control angle data is calculated for the static air flow mass data to obtain the air flow conveying control angle data;

[0146] According to the airflow conveying control angle data and the superposition force required for airflow circulation, the static airflow mass data is subjected to the airflow circulation rate balance analysis between regions to obtain the airflow circulation rate balance data;

[0147] Based on the superposition force required for air flow circulation, the air flow delivery control angle data and the air flow rate balance data, the temperature and humidity accumulation intensity data between different areas are used to regulate the air flow characteristics to obtain the air flow characteristics data.

[0148] In an embodiment of the present invention, in each region, according to the temperature and humidity accumulation intensity data, the distribution density of the static airflow in the region is mapped and calculated using the continuity equation in fluid mechanics. The specific operation is to convert the temperature and humidity data in each grid unit into a density field through an integral method, and calculate the airflow density of each small cell in the region. The airflow density is determined by the gas state formula, that is, the density of the gas is equal to the pressure divided by the product of the temperature and the gas constant. For the small cells in each region, the temperature and pressure values ​​of each grid are calculated by a discretization method, and then the static airflow density of these small cells is calculated one by one using the gas state formula. Subsequently, these density values ​​are summarized in a matrix form to form a static airflow density distribution in a local area. The static airflow density data of the local area is multiplied by the volume data of each region, and the total mass of the static airflow in each region is calculated by integral summation. The specific process is: first, the three-dimensional region is divided into a network, and the mass of the gas in the unit is calculated according to the static airflow density of each small unit and the volume of the unit. Specifically, the static airflow density value in each grid is multiplied by the volume value of the grid to obtain the airflow mass in the grid; the airflow mass of all grids is summed to obtain the static airflow mass data of the entire area. The gas exchange barrier effect data and the static airflow mass data are used to calculate the superposition force required for airflow circulation through the dynamic equation, and the airflow mass data and the gas exchange barrier effect data are used to evaluate the additional external force required for airflow to start circulation from a static state. The force on the static airflow is calculated by the product of mass and gravitational acceleration. At the same time, the resistance loss caused by the gas exchange barrier effect is considered, and the additional force required for circulation is evaluated by correcting the resistance coefficient. The additional force is equal to the product of the parameter reflecting the resistance size in the barrier effect and the airflow mass. By analyzing the direction and magnitude of the superposition force required for airflow circulation, combined with the boundary permeability coefficient in the gas exchange barrier effect data, the optimal conveying angle of airflow in the region is calculated. The vector field analysis method is used to align the direction of the airflow with the temperature and humidity gradient in the region, so that the conveying direction is consistent with the regional control target. In the specific calculation, first, according to the vector direction of the superposition force required for airflow circulation, the airflow is rotated three-dimensionally using the azimuth and elevation definitions to optimize the conveying path. The final calculated airflow control angle is expressed in the form of an angle matrix to guide the actual adjustment of the fan or airflow regulating equipment in the area. Using the airflow control angle data and the superposition force required for airflow circulation, the velocity distribution of the airflow is numerically simulated to calculate the rate balance of airflow circulation between regions. The Euler method is used to iteratively solve the velocity of the flowing gas in each grid unit in steps, and the calculated velocity distribution is combined with the static airflow mass data to determine the degree of balance of the airflow between different regions. In specific operations, it is also necessary to consider the energy dissipation after the gas flow is obstructed, and make a secondary correction to the velocity distribution to ensure that the calculated velocity balance data can truly reflect the dynamic changes of the airflow in the region.Combined with the superposition force required for airflow, the conveying control angle data, and the rate balance data, the airflow characteristics in the area are regulated through a dynamic optimization strategy. In the specific implementation process, the wind direction is adjusted using the airflow conveying control angle data, the wind speed is optimized based on the size of the superposition force, and the fan operating frequency is dynamically adjusted according to the rate balance data. Through continuous iterative calculations, the dynamic stable state of the airflow in the area is established, and finally the airflow characteristic data is output to provide a basis for further regulating temperature and humidity.

[0149] Compensating for the loss of temperature and humidity based on the airflow characteristics data of the vegetable environment and the temperature and humidity accumulation intensity data between different areas includes the following steps:

[0150] Performing airflow intensity evaluation on the airflow characteristic data to obtain airflow intensity data;

[0151] According to the airflow intensity data, the temperature and humidity accumulation intensity data between different regions are used to calculate the regional temperature and humidity circulation loss difference, and the regional temperature and humidity circulation loss difference data is obtained;

[0152] The regional temperature and humidity circulation loss difference data are analyzed for inter-regional loss superposition to obtain regional temperature and humidity circulation loss superposition data;

[0153] Extract the suitable temperature and humidity for the vegetable environment to obtain the suitable temperature and humidity for the vegetable environment;

[0154] According to the suitable temperature and humidity data of the vegetable environment, the regional temperature and humidity circulation loss superposition data is used to compensate for the circulation temperature and humidity loss, and the air flow circulation temperature and humidity loss compensation data is obtained.

[0155] In an embodiment of the present invention, the air flow characteristic data is evaluated by the air flow rate, flow rate and directional parameters in the region. First, according to the flow field distribution, the region is divided into several small units, and the air flow velocity vector of each unit is recorded. By calculating the modulus of the velocity vector, the velocity distribution of the air flow in each unit is obtained. Secondly, according to the overall directionality and pressure difference of the air flow, the momentum conservation equation is used to evaluate the air flow transmission intensity between each unit. Finally, the intensity values ​​of each unit are superimposed to obtain the air flow intensity data in the entire region. After clarifying the air flow intensity, the temperature and humidity loss value caused by air flow is calculated by establishing a continuity equation for the temperature and humidity changes in the region. First, the temperature and humidity accumulation intensity data is mapped to the grid coordinates consistent with the air flow characteristics. Secondly, the finite difference method is used to calculate the temperature and humidity changes caused by air flow in each grid. The change is obtained by multiplying the temperature and humidity concentration gradient and the flow rate. Finally, these differential values ​​are superimposed to generate the temperature and humidity circulation loss differential data in the region. On the basis of the regional loss differential data, by analyzing the temperature and humidity change trends between each region, it is determined whether there is a superposition effect of loss. The specific operations include: first, group the loss difference data by region, and use the spatial interpolation method to construct the temperature and humidity loss distribution in each region. Secondly, identify the loss superposition location by the temperature and humidity change difference at the regional boundary. Finally, use the accumulation algorithm to quantify the loss in the superposition area to form the regional temperature and humidity circulation loss superposition data. The vegetable environment suitable data includes the suitable temperature and humidity range and time node information. Through the data analysis tool, separate the temperature and humidity related fields, and extract the suitable upper and lower limits as the control benchmark. For specific vegetable types, the interval division method is used to further refine the suitable conditions, and divide them into standard data sets of different stages according to the time dimension to form the vegetable environment suitable temperature and humidity data. Based on the vegetable environment suitable temperature and humidity data, the superposition loss data is adjusted to the suitable range. The specific method is: first, match the suitable temperature and humidity data with the temperature and humidity circulation loss superposition data in the region. Then, use the compensation equation to calculate the temperature and humidity values ​​that need to be supplemented. The compensation equation is dynamically adjusted according to the deviation difference between the circulation loss and the vegetable demand. Finally, the compensation operation is performed by manually adjusting the heat source or cold source, humidification or dehumidification equipment, and verify whether the adjusted temperature and humidity meet the suitable range. After completion, air flow temperature and humidity loss compensation data is generated.

[0156] Step S4 includes the following steps:

[0157] Step S41: performing control logic integration processing on the regional environmental phased control data to obtain environmental control logic integrated data;

[0158] Step S42: constructing an environmental control model for the environmental control logic integration data based on the Boosting algorithm to obtain an environmental control logic model;

[0159] Step S43: Send the environmental control logic model to the cloud platform to perform intelligent control of the vegetable greenhouse environment.

[0160] In the embodiment of the present invention, in this step, the regional environmental stage control data is logically analyzed and integrated to ensure the coherence and scientificity of the control logic. First, the regional environmental stage control data is sorted according to the time axis, and data fields related to temperature and humidity control, light control, airflow control, etc. are extracted. Then, the control relationship is constructed by the logic tree method to clarify the logical dependency between time, region, and control variables. For example, in the temperature and humidity control data of a specific area, if the deviation between the target humidity and the current humidity is too large, it is necessary to perform the humidification operation first, and this operation affects the circulation of the airflow, so it is necessary to add priority rules in the logic tree. Secondly, the conditions of each control variable are merged and the contradiction test is performed through Boolean logic operations. Assuming that there is a conflict in the control demand in a certain area, such as requiring cooling and increasing the light intensity at the same time, the priority weight is calculated by Boolean logic to clarify the operation to be performed first. Finally, the integrated logic is output to the data file to generate the environmental control logic integration data, and the triggering conditions and specific operation instructions of each control logic are recorded in the form of key-value pairs. The Boosting algorithm is used to train and construct the model of the environmental control logic integration data. First, feature engineering is performed on the integrated data of environmental control logic, and the temperature and humidity difference, light intensity difference, airflow rate and other indicators in the data are normalized to ensure that the numerical range of the input features is consistent. At the same time, according to the control data of different time periods in the region, classification labels are set, such as "humidification", "cooling", "increasing light" and other operation types as target outputs. Then, the decision tree-based Boosting algorithm (such as Gradient Boosting Decision Tree, GBDT) is used to optimize the control logic model in a step-by-step iterative manner. In the initial stage, the first weak classifier is used to preliminarily classify the integrated data of environmental control logic to obtain the residual. Then, the residual is used as the input of the next round of classifiers to generate a new weak classifier. This cycle is repeated until the preset classification error threshold meets the requirements and the final environmental control logic model is generated. Finally, the classification results of the model are verified. The classification accuracy is evaluated by comparing the known results in the historical control data with the model prediction results. If the error is large, the Boosting parameters need to be readjusted until the logical classification ability of the model reaches the expected standard. After the environment control logic model is built, this step is responsible for deploying the model to the cloud platform and realizing the intelligent control function. First, the model file and related parameters are packaged into a data package in a standard format using a data interface protocol (such as RESTful API). The data package contains a detailed description of the control logic rules, control instructions for each area, and trigger conditions. Subsequently, the packaged data package is sent to the cloud platform via a network protocol (such as HTTPS), and a dedicated control logic processor is configured in the cloud platform.The cloud platform establishes a command parsing module for controlling the vegetable greenhouse environment based on the received logic model file. This module receives real-time data input from greenhouse sensors, including real-time data such as temperature and humidity, light intensity, and airflow rate, and generates corresponding control instructions based on the control logic model. Finally, through the remote control function of the cloud platform, the control instructions are sent to specific equipment in the greenhouse, such as heaters, humidifiers, and sunshade equipment, to achieve efficient intelligent environmental control.

[0161] The present invention also provides a vegetable greenhouse environment intelligent control system, which is used to execute the vegetable greenhouse environment intelligent control method as described above. The vegetable greenhouse environment intelligent control system includes:

[0162] Environmental data acquisition module, used to obtain all-weather lighting data of the vegetable greenhouse and internal environmental data of the vegetable greenhouse through sensors;

[0163] The heat deposition analysis module is used to identify the air heat flow exchange path based on the internal environment data of the vegetable greenhouse to obtain the internal air heat flow exchange path data; perform a heat flux period temperature and pressure deposition simulation on the internal air heat flow exchange path data according to the all-weather lighting data of the vegetable greenhouse to obtain the heat flux period temperature and pressure deposition data; perform a gas exchange barrier effect analysis based on the heat flux period temperature and pressure deposition data to obtain the gas exchange barrier effect data;

[0164] The regional environment control module is used to obtain the vegetable environment suitability data; based on the vegetable environment suitability data, the gas exchange barrier effect data is controlled in a phased manner to obtain the regional environment phased control data;

[0165] The environmental control model construction module is used to construct the environmental control model for the regional environmental phased control data to obtain the environmental control logic model; the environmental control logic model is sent to the cloud platform to execute intelligent control of the vegetable greenhouse environment.

[0166] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0167] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for intelligently controlling the environment of a vegetable greenhouse, characterized in that: The following steps are involved: Step S1: Obtaining all-weather lighting data of the vegetable greenhouse and internal environment data of the vegetable greenhouse through sensors; Step S2: identifying the air heat flow exchange path based on the internal environment data of the vegetable greenhouse to obtain the internal air heat flow exchange path data; According to the all-weather lighting data of the vegetable greenhouse, the temperature and pressure deposition data of the internal air heat exchange path during the heat flux period are simulated to obtain the temperature and pressure deposition data during the heat flux period; The gas exchange barrier effect is analyzed according to the temperature-pressure deposition data during the heat flux period to obtain the gas exchange barrier effect data; wherein step S2 comprises: Step S21: identifying the air heat flow exchange path based on the internal environment data of the vegetable greenhouse to obtain the internal air heat flow exchange path data; Step S22: Acquire greenhouse material characteristic data; Step S23: performing light source heat conduction fluctuation analysis on greenhouse material characteristic data according to the all-weather illumination data of the vegetable greenhouse to obtain light source heat conduction fluctuation data; Step S24: Based on the light source heat conduction fluctuation data, the internal air heat exchange path data is simulated for the heat flux period temperature and pressure deposition to obtain the heat flux period temperature and pressure deposition data; wherein step S24 includes: Step S241: performing spatiotemporal discretization processing on the light source heat conduction fluctuation data to obtain spatiotemporal discrete data of heat conduction fluctuation; Step S242: Calculating the heat density difference of the exchange path between different time periods based on the heat conduction fluctuation spatiotemporal discrete data, and obtaining the heat density difference data of the path; Step S243: performing path geometry orientation convection potential difference analysis on the internal air heat exchange path data according to the path heat density difference data to obtain path geometry orientation convection potential difference data; wherein step S243 includes: The heat density differential gradients on different paths are calculated for the internal air heat flow exchange path data according to the path heat density difference data, so as to obtain the heat density differential gradient data on different paths; The heat density differential gradient data on different paths are used to analyze the change of heat convection intensity between horizontal planes to obtain the change data of horizontal heat convection intensity; The heat density differential gradient data on different paths are analyzed for vertical heat convection intensity changes to obtain vertical heat convection intensity change data; The spatial geometric curl is calculated according to the horizontal heat convection intensity change data and the vertical heat convection intensity change data to obtain the convection spatial geometric curl data; The convection cross-section curl difference is calculated based on the convection space geometric curl data to obtain the convection cross-section curl difference; According to the convection space geometric curl data and the convection cross-section curl difference, the path geometric orientation convection potential difference analysis is performed on the internal air heat exchange path data to obtain the path geometric orientation convection potential difference data; Step S244: performing pressure potential difference streamline distribution analysis on the flow potential difference data based on the path geometry orientation to obtain pressure potential difference streamline distribution data; Step S245: performing a heat flux period temperature and pressure deposition simulation on the internal air heat exchange path data according to the path geometric orientation convection potential difference data, the pressure potential difference streamline distribution data and the path heat density difference data, to obtain the heat flux period temperature and pressure deposition data; Step S25: performing a gas exchange barrier effect analysis on the internal air heat flow exchange path data according to the heat flux period temperature and pressure deposition data to obtain gas exchange barrier effect data; Step S3: Acquire vegetable environment suitability data; perform regional environmental stage-by-stage regulation on the gas exchange barrier effect data based on the vegetable environment suitability data to obtain regional environmental stage-by-stage regulation data; Step S4: construct an environmental control model for the regional environmental phased control data to obtain an environmental control logic model; send the environmental control logic model to the cloud platform to perform intelligent control of the vegetable greenhouse environment.

2. The method for intelligently controlling the vegetable greenhouse environment according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: Obtaining vegetable environment suitability data; Step S32: quantifying the regional temperature and humidity imbalance on the gas exchange barrier effect data and the temperature and pressure deposition data during the heat flux period according to the vegetable environment suitability data, to obtain regional temperature and humidity imbalance quantification data; Step S33: Based on the vegetable environment suitability data, the regional temperature and humidity imbalance quantification data and the gas exchange barrier effect data are regulated in stages to obtain regional environment stage regulation data.

3. The method for intelligently controlling the vegetable greenhouse environment according to claim 2, characterized in that: Step S33 includes the following steps: Step S331: performing regional temperature and humidity difference numerical calculation on the regional temperature and humidity imbalance quantification data to obtain regional temperature and humidity difference numerical data; Step S332: performing temperature and humidity accumulation intensity analysis between different regions according to the gas exchange barrier effect data and the regional temperature and humidity difference numerical data, and obtaining temperature and humidity accumulation intensity data between different regions; Step S333: Based on the gas exchange barrier effect data, the temperature and humidity accumulation intensity data between different areas are regulated by air flow characteristics to obtain air flow characteristics data; Step S334: Compensating for the temperature and humidity loss of the vegetable environment suitability data and the temperature and humidity accumulation intensity data between different areas according to the air flow characteristic data, and obtaining the air flow temperature and humidity loss compensation data; Step S335: Perform phased control of the regional environment according to the airflow characteristic data and the airflow temperature and humidity loss compensation data to obtain phased control data of the regional environment.

4. The method for intelligently controlling the vegetable greenhouse environment according to claim 3, characterized in that: The air flow characteristics control based on the temperature and humidity accumulation intensity data between different areas includes the following steps: The temperature and humidity accumulation intensity data between different regions are mapped to the local area static airflow density to obtain the local area static airflow density data; Calculate the static airflow mass based on the static airflow density data of the local area to obtain the static airflow mass data; Based on the gas exchange barrier effect data, the required superposition force for airflow circulation is evaluated on the static airflow mass data to obtain the required superposition force for airflow circulation; According to the superposition force required for air flow circulation and the gas exchange barrier effect data, the air flow conveying control angle data is calculated for the static air flow mass data to obtain the air flow conveying control angle data; According to the airflow conveying control angle data and the superposition force required for airflow circulation, the static airflow mass data is subjected to the airflow circulation rate balance analysis between regions to obtain the airflow circulation rate balance data; Based on the superposition force required for air flow, air flow control angle data and air flow rate balance data, the temperature and humidity accumulation intensity data between different areas are used to regulate the air flow characteristics to obtain the air flow characteristics data.

5. The method for intelligently controlling the vegetable greenhouse environment according to claim 3, characterized in that: Compensating for the loss of temperature and humidity based on the airflow characteristics data of the vegetable environment and the temperature and humidity accumulation intensity data between different areas includes the following steps: Performing airflow intensity evaluation on the airflow characteristic data to obtain airflow intensity data; According to the airflow intensity data, the temperature and humidity accumulation intensity data between different regions are used to calculate the regional temperature and humidity circulation loss difference, and the regional temperature and humidity circulation loss difference data is obtained; The regional temperature and humidity circulation loss difference data are analyzed for inter-regional loss superposition to obtain regional temperature and humidity circulation loss superposition data; Extract the suitable temperature and humidity for the vegetable environment to obtain the suitable temperature and humidity for the vegetable environment; According to the suitable temperature and humidity data of the vegetable environment, the regional temperature and humidity circulation loss superposition data is used to compensate for the circulation temperature and humidity loss, and the air flow circulation temperature and humidity loss compensation data is obtained.

6. The method for intelligently controlling the vegetable greenhouse environment according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: performing control logic integration processing on the regional environmental phased control data to obtain environmental control logic integrated data; Step S42: constructing an environmental control model for the environmental control logic integration data based on the Boosting algorithm to obtain an environmental control logic model; Step S43: Send the environmental control logic model to the cloud platform to perform intelligent control of the vegetable greenhouse environment.

7. An intelligent control system for vegetable greenhouse environment, characterized in that: Used to execute the vegetable greenhouse environment intelligent control method according to claim 1, the vegetable greenhouse environment intelligent control system comprises: Environmental data acquisition module, used to obtain all-weather lighting data of the vegetable greenhouse and internal environmental data of the vegetable greenhouse through sensors; The heat deposition analysis module is used to identify the air heat flow exchange path based on the internal environment data of the vegetable greenhouse to obtain the internal air heat flow exchange path data; perform a heat flux period temperature and pressure deposition simulation on the internal air heat flow exchange path data according to the all-weather lighting data of the vegetable greenhouse to obtain the heat flux period temperature and pressure deposition data; perform a gas exchange barrier effect analysis based on the heat flux period temperature and pressure deposition data to obtain the gas exchange barrier effect data; The regional environment control module is used to obtain the vegetable environment suitability data; based on the vegetable environment suitability data, the gas exchange barrier effect data is controlled in a phased manner to obtain the regional environment phased control data; The environmental control model construction module is used to construct the environmental control model for the regional environmental phased control data to obtain the environmental control logic model; the environmental control logic model is sent to the cloud platform to execute intelligent control of the vegetable greenhouse environment.

Images