Intelligent response control method for greenhouse based on environmental parameters

Abstract

The present invention discloses an intelligent response control method for greenhouses based on environmental parameters, which relates to the technical field of agricultural intelligent control. The method comprises: obtaining target crops and collecting canopy infrared temperature in real time; dynamically collecting distributed greenhouse environmental parameters through a distributed multi-source sensor array; traversing predetermined related indicators in the distributed environmental parameters to obtain a first crop heat demand index; performing normalized weighted calculation on factor environmental data to obtain an environmental impact coefficient; calibrating the first crop heat demand index to obtain a second crop heat demand index; and retrieving a response control plan to intelligently control the greenhouse. The method solves the technical problems existing in the prior art, such as environmental control ignoring crop physiological feedback, uneven distribution of environmental parameters, and insufficient analysis of multi-factor coupling effects, which lead to poor greenhouse control accuracy and adaptability. The method achieves the technical effect of dynamically and accurately responding to crop needs, optimizing environmental control strategies, and improving greenhouse control accuracy and adaptability.

Description

Technical Field

[0001] The present application relates to the technical field related to agricultural intelligent control, and in particular to a greenhouse intelligent response control method based on environmental parameters. Background Art

[0002] Greenhouses can effectively regulate the crop growth environment and improve crop yield and quality. However, traditional greenhouse environmental control relies on static threshold control of single environmental parameters such as temperature, humidity, and light, which makes it difficult to fully reflect the actual growth needs of crops. This is especially true under complex and changing environmental conditions, which can easily lead to delayed or over-responsive control, affecting crop growth efficiency. Among them, crop canopy infrared temperature can directly reflect crop transpiration, water status, and heat stress levels, reflecting the crop's physiological state. At the same time, greenhouse environmental parameters such as air temperature and humidity, light intensity, CO2 concentration, and soil temperature and humidity are unevenly distributed spatially, making it difficult to fully characterize the environmental state. The key to the current agricultural environmental control field is how to comprehensively utilize multiple environmental parameters and canopy infrared temperature to construct an accurate crop thermal demand model and implement intelligent control based on this model. Furthermore, environmental control strategies lack dynamic analysis of the coupling effects of multiple environmental parameters and do not fully consider the real-time physiological feedback of the crop itself, resulting in insufficient control precision and difficulty in achieving precise environmental optimization.

[0003] At present, relevant technologies have technical problems such as environmental regulation ignoring crop physiological feedback, uneven distribution of environmental parameters, and insufficient analysis of multi-factor coupling, which lead to poor greenhouse control accuracy and adaptability. Summary of the Invention

[0004] This application provides a greenhouse intelligent response control method based on environmental parameters, which solves the technical problems in the existing technology that environmental control ignores crop physiological feedback, environmental parameters are unevenly distributed, and multi-factor coupling analysis is insufficient, resulting in poor greenhouse control accuracy and adaptability. It achieves the technical effect of dynamically and accurately responding to crop needs, optimizing environmental control strategies, and improving greenhouse control accuracy and adaptability.

[0005] The present application provides an intelligent response control method for a greenhouse based on environmental parameters, the method comprising: acquiring a target crop and acquiring the canopy infrared temperature of the target crop in real time; dynamically acquiring the distributed environmental parameters of the greenhouse where the target crop is located through a distributed multi-source sensor array; traversing predetermined related indicators in the distributed environmental parameters to obtain related environmental data, and coordinating with the canopy infrared temperature to obtain a first crop thermal demand index; performing normalized weighted calculation on the factor environmental data obtained by traversing the distributed environmental parameters based on predetermined factor indicators to obtain an environmental impact coefficient; calibrating the first crop thermal demand index with the environmental impact coefficient to obtain a second crop thermal demand index; and based on the second crop thermal demand index, calling a response control plan to perform intelligent control on the greenhouse.

[0006] In a possible implementation, the greenhouse intelligent response control method based on environmental parameters also performs the following processing: extracting the first indicator among the predetermined related indicators; traversing and screening the distributed environmental parameters based on the first indicator to obtain a first parameter set; extracting the first parameter in the first parameter set, and the first parameter corresponds to the first sensor in the first distributed sensor; forming a first visual environment structure network based on the first corresponding relationship between the first sensor and the first parameter; and organizing the relevant environmental data based on the first visual environment structure network.

[0007] In a possible implementation, the greenhouse intelligent response control method based on environmental parameters further performs the following processing: the predetermined related indicators include air temperature and solar radiation.

[0008] In a possible implementation, the greenhouse intelligent response control method based on environmental parameters also performs the following processing: obtaining the target planting point of the target crop; rendering the target planting point to the first visual environment structure network to obtain a first target visual map; processing and analyzing the first target visual map according to a predetermined sampling aggregation strategy to obtain a first processing value; based on the first processing value, assembling the relevant environmental data; which includes: in the first target visual map, constructing a crop neighborhood with the target planting point as the center of the circle, wherein the crop neighborhood includes a first-level neighborhood and a second-level neighborhood; obtaining a second-level sensor set corresponding to the second-level neighborhood, and randomly sampling a second-level detection value set corresponding to the second-level sensor set to obtain a first sampling result; aggregating the first sampling result according to the predetermined sampling aggregation strategy to obtain a first aggregation value; obtaining a first-level sensor set corresponding to the first-level neighborhood, and randomly sampling a first-level detection value set corresponding to the first-level sensor set to obtain a second sampling result; aggregating the second sampling result according to the predetermined sampling aggregation strategy to obtain a second aggregation value; and weighting the first aggregation value and the second aggregation value by variation to obtain the first processing value.

[0009] In a possible implementation, the greenhouse intelligent response control method based on environmental parameters also performs the following processing: obtaining the predetermined temperature threshold of the target crop; and obtaining the first crop thermal demand index by coordinating the relevant environmental data, the canopy infrared temperature and the lower limit of the predetermined temperature threshold.

[0010] In a possible implementation, the greenhouse intelligent response control method based on environmental parameters further performs the following processing: the predetermined factor indicators include air humidity, wind speed and force, soil temperature and humidity, and carbon dioxide concentration.

[0011] In a possible implementation, the greenhouse intelligent response control method based on environmental parameters also performs the following processing: extracting the temperature control plan in the response control plan; when the second crop heat demand index is at a first threshold, according to the temperature control plan, activating the heat storage-release system to perform intelligent control on the greenhouse; when the second crop heat demand index is at a second threshold, according to the temperature control plan, activating the surface cooler-fan heat collection and release system to perform intelligent control on the greenhouse; when the second crop heat demand index is at a third threshold, according to the temperature control plan, activating the solar energy-ground source heat pump composite heating system to perform intelligent control on the greenhouse.

[0012] In a possible implementation, the greenhouse intelligent response control method based on environmental parameters also performs the following processing: extracting the fertilization control plan in the response control plan; obtaining the age of the greenhouse and matching the fertility influence coefficient corresponding to the age of the greenhouse; and performing fertilization control correction on the greenhouse based on the fertility influence coefficient.

[0013] In a possible implementation, the greenhouse intelligent response control method based on environmental parameters also performs the following processing: generating a real-time heat demand curve of the target crop based on the second crop heat demand index; traversing the real-time heat demand curve in the historical heat demand curve database of the target crop to obtain the most similar historical curve; predicting the heat demand index of the target crop based on the most similar historical curve to obtain a predicted crop heat demand index; based on the predicted crop heat demand index, calling the response control plan to perform predictive pre-control on the greenhouse.

[0014] In a possible implementation, the greenhouse intelligent response control method based on environmental parameters also performs the following processing: extracting the first historical curve from the historical heat demand curve database; calculating the first curve distance between the real-time heat demand curve and the first historical curve; arranging the curves in the historical heat demand curve database in ascending order based on the first curve distance to obtain an ascending list of historical curves; and taking the first historical curve in the ascending list of historical curves as the most similar historical curve.

[0015] The proposed greenhouse intelligent response control method based on environmental parameters is intended to acquire target crops and collect canopy infrared temperature in real time. The distributed environmental parameters of the greenhouse are dynamically collected through a distributed multi-source sensor array. Predetermined relevant indicators are traversed through the distributed environmental parameters to obtain a first crop thermal demand index. Normalized weighted calculations are performed on the factor environmental data to obtain an environmental impact coefficient. The first crop thermal demand index is calibrated to obtain a second crop thermal demand index. The response control plan is then called to intelligently control the greenhouse. This solves the technical problems in existing technologies, such as environmental control ignoring crop physiological feedback, uneven distribution of environmental parameters, and insufficient analysis of multi-factor coupling, which lead to poor greenhouse control accuracy and adaptability. This method achieves the technical effect of dynamically and accurately responding to crop needs, optimizing environmental control strategies, and improving greenhouse control accuracy and adaptability. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings of the embodiments of the present invention are briefly introduced below. Flowcharts are used in this application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in precise order. Instead, various steps may be processed in reverse order or simultaneously as needed. Furthermore, other operations may be added to these processes, or one or more operations may be removed from these processes.

[0017] Figure 1 A flow chart of the greenhouse intelligent response control method based on environmental parameters provided in an embodiment of the present application.

[0018] Figure 2 This is a schematic diagram of the process of obtaining relevant environmental data in the greenhouse intelligent response control method based on environmental parameters provided in an embodiment of the present application. DETAILED DESCRIPTION

[0019] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0020] In order to make the purpose, technical solutions and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limiting this application. All other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0021] In the following description, reference is made to “some embodiments”, which describes a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms “first\second” involved are merely to distinguish similar objects and do not represent a specific ordering of the objects. The terms “including” and “having” and any variations are intended to cover non-exclusive inclusions. For example, a process, method, product, or server comprising a series of steps is not necessarily limited to those steps clearly listed, but may include other steps that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs. The terms used herein are for the purpose of describing the embodiments of this application only.

[0022] The embodiment of the present application provides a greenhouse intelligent response control method based on environmental parameters, such as Figure 1 As shown, the method includes:

[0023] Step S100: acquiring a target crop and collecting the infrared temperature of the canopy of the target crop in real time.

[0024] Preferably, target crops are selected, that is, specific crop types that need to be monitored and regulated, such as tomatoes, cucumbers, strawberries, etc., and then inspection robots or drones with integrated infrared thermometers or thermal imaging cameras are used to detect the infrared temperature of the canopy of the target crops in real time in a non-contact manner. The canopy refers to the stem and leaf group of the crop, that is, the leaf layer on the upper part of the plant, which is the main part for the crop to exchange heat, water and gas with the environment. Specifically, all crops will emit infrared radiation, and its intensity is related to the surface temperature. The infrared sensor receives radiation and calculates the temperature value. The canopy temperature directly reflects the transpiration cooling effect of the crop. If the temperature rises abnormally, it may indicate water shortage or overheating of the environment. Combined with environmental parameters such as air temperature and humidity, the actual heat demand of the crop can be calculated to avoid errors caused by relying solely on air temperature control.

[0025] Step S200 : dynamically collecting distributed environmental parameters of the greenhouse where the target crop is located through a distributed multi-source sensor array.

[0026] Preferably, multiple sensors of different types are deployed in the greenhouse to monitor the key parameters of the crop growth environment in real time in a spatially distributed manner, and achieve comprehensive and accurate environmental perception through data fusion. Among them, the distributed multi-source sensor array is based on the greenhouse structure, crop distribution and environmental change laws, and multiple monitoring nodes are reasonably arranged in space. For example, multiple sensors of different types are deployed at the top, middle, near the crop canopy, on the ground, etc. to capture the spatial heterogeneity of greenhouse environmental parameters, such as temperature distribution, temperature gradient, etc. Specifically, the distributed multi-source sensor array is used to dynamically collect distributed environmental parameters of the greenhouse where the target crop is located at a high frequency (such as every minute or every second), including temperature sensors collecting air temperature and soil temperature, humidity sensors collecting air humidity and soil moisture content, light sensors collecting photosynthetically active radiation PAR and light intensity, carbon dioxide concentration sensors monitoring carbon dioxide concentration, wind speed / direction sensors monitoring ventilation conditions, and soil EC value, pH value, etc.; multiple sensors are composed of a sensor network in a wired or wireless manner to realize centralized data transmission and processing.

[0027] Step S300 , traversing the predetermined related indicators in the distributed environmental parameters to obtain related environmental data, and coordinating with the canopy infrared temperature to obtain a first crop heat demand index.

[0028] Furthermore, step S300 also includes that the predetermined related indicators include air temperature and solar radiation.

[0029] Preferably, environmental parameters corresponding to predetermined indicators related to crop thermal demand are screened from the multidimensional environmental data collected by distributed sensors. These parameters are then combined with canopy infrared temperature to quantify the crop's current thermal load through a computational model, forming a preliminary crop thermal demand assessment index. The predetermined indicators are pre-determined environmental parameters that significantly impact crop thermal demand, including air temperature and solar radiation. Specifically, data corresponding to the predetermined indicators, air temperature and solar radiation, are extracted from the environmental data collected by all distributed sensors. Similar environmental data from different locations are spatially interpolated or weighted averaged to eliminate local interference, resulting in the relevant environmental data. The environmental parameters, air temperature and solar radiation, are then correlated with canopy temperature through an energy balance model or empirical formula to calculate crop thermal demand, i.e., a first crop thermal demand index. The first crop thermal demand index represents the crop's current thermal load. Low values ​​indicate a suitable environment and no intervention is required; high values ​​indicate that the crop is facing heat stress and requires cooling measures, such as ventilation, shading, or spraying. Through the coordinated analysis of canopy temperature and environmental parameters, the crop's true thermal demand can be more accurately identified.

[0030] Further, such as Figure 2 As shown, step S300 also includes step S310, extracting the first indicator among the predetermined related indicators; step S320, traversing and screening the distributed environment parameters based on the first indicator to obtain a first parameter set; step S330, extracting the first parameter in the first parameter set, and the first parameter corresponds to the first sensor in the first distributed sensor; step S340, forming a first visual environment structure network according to the first corresponding relationship between the first sensor and the first parameter; step S350, organizing the related environment data based on the first visual environment structure network.

[0031] Preferably, any one of the predetermined related indicators is extracted as the first indicator, and then the relevant data is traversed and filtered out from the distributed environmental parameters according to the first indicator to obtain a first parameter set and eliminate abnormal values. For example, if the first indicator is air temperature, the measured values ​​of all temperature sensors are filtered out to form a parameter set of temperature data; then any one of the first parameters is extracted from the first parameter set as the first parameter, and the first sensor corresponding to the first parameter in the first distributed sensor is obtained, and its position, model, calibration parameters, etc. are recorded. Then, according to the first correspondence between the first sensor and the first parameter, a first visual environment structure network is constructed, that is, information such as sensors, environmental parameters, and crop positions are associated to form a visual environment structure network, such as a sensor distribution heat map in a greenhouse, in which nodes are sensors, crop areas, and control devices, and edges represent data flow relationships and physical location relationships; finally, using the association relationship in the visual environment structure network, environmental data that is strongly correlated with the first indicator is extracted from the distributed sensors. For example, if the first indicator is air temperature, the humidity and light data of the area are further associated to generate a structured data set, and the synergistic effect of temperature and humidity is analyzed to facilitate the calculation of the crop heat demand index.

[0032] Furthermore, step S350 also includes step S351, obtaining the target planting point of the target crop; step S352, rendering the target planting point to the first visual environment structure network to obtain a first target visual graph; step S353, processing and analyzing the first target visual graph according to a predetermined sampling aggregation strategy to obtain a first processing value; step S354, based on the first processing value, assembling the relevant environmental data.

[0033] Preferably, the target planting locations of the target crops are obtained using a pre-set planting plan, or by using RFID tags, QR codes to mark plants, or drones or cameras to scan crop distribution. This means obtaining the specific physical location information of the target crops within the greenhouse, including spatial coordinates such as ridge numbers and row / plant spacing; regional divisions, such as Area A - Tomato Planting Area - Ridge 3; and growth stage markers, such as seedling stage and flowering stage, as different stages have different environmental requirements. The target planting locations are then overlaid with the visual environment structure network to form a more complete spatial data view, namely the first target visual map, which includes a base layer, a crop layer, and associated relationships. The base layer displays sensor nodes and the environmental data they collect; the crop layer displays the location, density, and growth status labels of the target crops; and the associated relationships represent the mapping between crops and distributed sensors. Crop areas and sensor coverage areas are then marked with different colors.

[0034] Preferably, the first target visual map is then processed and analyzed according to a predetermined sampling and aggregation strategy. This strategy is a data extraction and calculation strategy designed based on crop requirements to extract key feature values ​​from massive amounts of environmental data. This strategy may include spatial aggregation and temporal aggregation. Spatial aggregation refers to averaging sensor data within a certain radius around the crop site or dividing it by planting area. Temporal aggregation refers to calculating the data mean using a sliding window and adjusting parameter weights based on the crop growth stage to obtain a first processed value, such as an effective mean temperature of 28.5°C and a peak canopy light intensity of 1200 μmol / m² / s in the target crop area. Finally, based on the first processed value, relevant environmental data is assembled, including the first processed value, relevant environmental parameters, and the associated specific crop area.

[0035] Further, step S353 includes step a, in the first target visual map, constructing a crop neighborhood with the target planting point as the center of the circle, wherein the crop neighborhood includes a first-level neighborhood and a second-level neighborhood; step b, obtaining a second-level sensor set corresponding to the second-level neighborhood, and randomly sampling the second-level detection value set corresponding to the second-level sensor set to obtain a first sampling result; step c, aggregating the first sampling result according to the predetermined sampling aggregation strategy to obtain a first aggregation value; step d, obtaining a first-level sensor set corresponding to the first-level neighborhood, and randomly sampling the first-level detection value set corresponding to the first-level sensor set to obtain a second sampling result; step e, aggregating the second sampling result according to the predetermined sampling aggregation strategy to obtain a second aggregation value; step f, variably weighting the first aggregation value and the second aggregation value to obtain the first processed value.

[0036] Preferably, based on spatially layered environmental data sampling and aggregation, a crop neighborhood is constructed and sensor data is processed in a layered and weighted manner to finally obtain a first processed value that can accurately reflect the crop microenvironment. Specifically, in the first target visual map, the target planting point, such as the root coordinates of a tomato plant, is taken as the center of the circle, and two concentric circle areas are divided according to the crop physiological characteristics and sensor deployment density to construct a first-level neighborhood and a second-level neighborhood. The first-level neighborhood refers to a smaller radius, such as 0.5 meters, which directly reflects the crop rhizosphere and canopy microenvironment, and the second-level neighborhood refers to a larger radius, such as 1.2 meters, which reflects the environmental trend around the target crop. All sensors located in the second-level neighborhood, including temperature and humidity sensors, are obtained, and then the second-level detection value set corresponding to the second-level sensor set is randomly sampled to obtain a first sampling result, and the first sampling result is aggregated according to a predetermined strategy to obtain a first aggregated value. For example, 5 of the 10 temperature sensors in the second-level neighborhood are randomly selected, and the average value of their collected temperature data is calculated as the background environmental temperature.

[0037] Preferably, a first-level sensor set corresponding to the first-level neighborhood is obtained, which is usually closer to the stems, leaves or roots of the crop. Some sensors are randomly selected for detection, and the obtained first-level detection value set is randomly sampled to obtain a second sampling result. The second sampling result is then aggregated to obtain a second aggregate value. For example, all three humidity sensors in the first-level neighborhood are sampled, and the median is taken as the core humidity of the rhizosphere. Finally, the first aggregate value and the second aggregate value are weighted by variation, that is, the weighted weight is dynamically adjusted according to the degree of difference between the first-level neighborhood data and the second-level neighborhood data for calculation. If the difference between the two levels of data is small, it means that the environment is uniform and the weight of the second-level neighborhood can be increased; if the difference is large, it means that the crop microenvironment is special and the weight of the first-level neighborhood is higher. Finally, the weighted calculation is performed to obtain the first processed value, and then the environmental data around the crop is converted into a highly reliable processed value.

[0038] Furthermore, step S300 also includes step S360, obtaining a predetermined temperature threshold of the target crop; and step S370, obtaining the first crop heat demand index by coordinating the relevant environmental data, the canopy infrared temperature and the lower limit of the predetermined temperature threshold.

[0039] Preferably, the thermal demand index of the crop is dynamically calculated by collaboratively analyzing environmental parameters, canopy infrared temperature, and crop physiological thresholds to quantify whether it requires external intervention for cooling or insulation. Specifically, in combination with agronomic experimental data or agricultural database, the ideal temperature range is pre-set according to the crop type and growth stage as the predetermined temperature threshold for the target crop, usually including a lower temperature limit and an upper temperature limit, wherein the lower temperature limit refers to the lowest tolerable temperature, such as not less than 15°C during the tomato seedling stage, and the upper temperature limit refers to the highest tolerable temperature, such as not higher than 30°C during the tomato flowering stage. The system then coordinates relevant environmental data, canopy infrared temperature, and the lower limit of a predetermined temperature threshold. Specifically, the deviation between the current ambient temperature and the lower limit of the crop temperature is compared—that is, the ratio of the difference between the current ambient temperature and the lower limit of the crop temperature to the lower limit of the crop temperature. A negative deviation indicates that the ambient temperature is below the crop's requirements and requires heating or insulation. A positive deviation indicates that the ambient temperature is above the lower limit and requires further analysis in conjunction with canopy temperature. The system then calculates the difference between the canopy infrared temperature and the ambient temperature. If the difference is greater than 0, it indicates that the canopy is warmer than the environment, possibly due to insufficient transpiration or excessive radiation. If the difference is approximately 0, it indicates that the crop and environment are in normal thermal equilibrium. If the difference is less than 0, it indicates that the canopy is cooler than the environment. Finally, the deviation is combined with the canopy temperature difference and a weighted calculation is used to generate a first crop thermal requirement index to identify the crop's actual physiological state, such as whether water shortages are leading to insufficient cooling.

[0040] Step S400 , performing normalized weighted calculation on the factor environment data obtained by traversing the distributed environmental parameters based on predetermined factor indicators to obtain an environmental impact coefficient.

[0041] Step S400 further includes that the predetermined factor indicators include air humidity, wind speed and force, soil temperature and humidity, and carbon dioxide concentration.

[0042] Preferably, key factor environmental parameters are screened from the distributed environmental parameters through predetermined factor indicators, and normalized weighted calculations are performed to generate a comprehensive environmental impact coefficient for objectively evaluating the overall impact of the current environment on crop growth. The predetermined factor indicators include air humidity, wind speed and force, soil temperature and humidity, and carbon dioxide concentration. Air humidity affects crop transpiration and disease risk, wind speed and force determine greenhouse ventilation efficiency and heat distribution, soil temperature and humidity directly affect root activity and water absorption, and carbon dioxide concentration restricts photosynthesis efficiency. Specifically, all environmental data corresponding to the predetermined factor indicators are extracted from the distributed environmental parameters. For example, For example, real-time data collected by 10 humidity sensors, 5 anemometers, 8 soil probes, and 3 CO2 sensors are screened out from 50 sensors, and outliers and redundant data are excluded. Then, multiple environmental parameters of different units and dimensions are normalized, that is, each parameter is normalized using range normalization or Z-score standardization to convert it into a dimensionless value of 0~1. Finally, dynamic weights are assigned to each type of factor based on the crop growth stage and agricultural knowledge, such as air humidity 0.3, wind speed and force 0.2, soil temperature and humidity 0.3, and carbon dioxide concentration 0.2. The environmental impact coefficient is obtained by weighted calculation to facilitate environmental regulation in precision agriculture.

[0043] Step S500: calibrating the first crop heat demand index with the environmental impact coefficient to obtain a second crop heat demand index.

[0044] Preferably, the first crop heat requirement index is corrected by the environmental impact coefficient to obtain a second crop heat requirement index that is more accurate and more in line with actual growth conditions, wherein the first crop heat requirement index is calculated based only on canopy infrared temperature, air temperature, and basic light environmental parameters, without fully considering the synergistic effects of environmental factors such as humidity, CO2, and wind speed. This may lead to reduced crop transpiration cooling efficiency in high humidity environments, and the same canopy temperature may represent more severe stress. Under strong wind conditions, canopy heat dissipation is accelerated, and the heat requirement index may be overestimated. The environmental impact coefficient is used to quantify the multi-factor coupling effect to correct the deviation of the first crop heat requirement index. Specifically, the environmental impact coefficient comprehensively reflects the overall suitability of humidity, wind speed, soil, CO2 and other conditions for crops. When it is close to 1, it means that the environment is highly suitable, the heat requirement may be overestimated, and it needs to be corrected downward; when it is close to 0, it means that the environment is seriously unsuitable, the heat requirement may be underestimated, and it needs to be corrected upward. The first crop heat requirement index is then calibrated through weighted adjustment. When the overall environment is unfavorable, such as high humidity and no wind, the actual heat stress corresponding to the same canopy temperature is stronger, and the crop heat requirement index needs to be increased. When the environment is ideal, such as suitable humidity and ventilation, the same canopy temperature may not require intervention, and the crop heat requirement index needs to be lowered. Finally, the second crop heat requirement index is obtained, which significantly improves the control accuracy of the target crop greenhouse environment.

[0045] Step S600: Based on the second crop heat demand index, a response control plan is retrieved to perform intelligent control on the greenhouse.

[0046] Step S600 further includes step S610, extracting the temperature control plan in the response control plan; step S620, when the second crop heat demand index is at the first threshold, according to the temperature control plan, activating the heat storage-release system to intelligently control the greenhouse; step S630, when the second crop heat demand index is at the second threshold, according to the temperature control plan, activating the surface cooler-fan heat collection and release system to intelligently control the greenhouse; step S640, when the second crop heat demand index is at the third threshold, according to the temperature control plan, activating the solar energy-ground source heat pump composite heating system to intelligently control the greenhouse.

[0047] Preferably, by dividing the crop's thermal demand index (second index) into different threshold intervals and matching the corresponding intelligent control plans, accurate and energy-saving environmental control is achieved, and the temperature control plan in the response control plan is extracted, wherein the response control plan includes a temperature control plan and a fertilization control plan. The temperature control plan refers to a pre-set multi-level temperature control scheme, which includes a first threshold value, a second threshold value, and a third threshold value of the temperature. The equipment combination and control logic corresponding to different thermal demand levels are different. Specifically, when the second crop thermal demand index is at the first threshold value, it indicates mild heat stress, that is, the temperature is slightly lower than the crop demand at night or during low temperature periods, and the temperature difference between day and night is large. The transition period control activates the heat storage-release system to perform intelligent control of the greenhouse, including the release of heat energy by the heat storage body, and the slow release of heat energy stored during the day, such as phase change materials and water heat storage tanks, and the canopy area is evenly heated through hot air ducts or radiation panels. At the same time, the vents are closed to reduce heat loss and the flow of hot air is promoted through the internal circulation fan.

[0048] Preferably, when the second crop heat demand index is at the second threshold, it indicates moderate heat stress, that is, the ambient temperature during the daytime high temperature period exceeds the suitable range for crops and the canopy temperature is significantly higher than the air temperature. Then, according to the temperature control plan, the surface cooler-fan heat collection and release system is activated to intelligently control the greenhouse, including cooling the surface cooler, circulating cold water through the surface cooler fins, forcing the air to exchange heat and cool down, and at the same time using the top fan to discharge hot air and opening the side windows to let in air to form vertical convection, thereby enhancing heat dissipation efficiency. When the second crop heat demand index is at the third threshold, it indicates severe heat stress, that is, extreme low temperature cold wave or long-term rainy weather, and low soil temperature affects root vitality. According to the temperature control plan, the solar energy-ground source heat pump composite heating system is activated to intelligently control the greenhouse, including solar energy heating, using solar collectors to heat the hot water storage tank during the day, and transferring heat through floor radiation pipes. At the same time, the ground source heat pump is used to assist in extracting heat or cold from the underground constant temperature layer and cooperate with the air handling unit to achieve precise temperature control. This enables closed-loop management from crop physiological needs to equipment execution, combining precision, energy efficiency, and reliability.

[0049] Furthermore, step S600 also includes step S650, extracting the fertilization control plan in the response control plan; step S660, obtaining the age of the greenhouse and matching the fertility influence coefficient corresponding to the greenhouse age; step S670, performing fertilization control correction on the greenhouse based on the fertility influence coefficient.

[0050] Preferably, the fertilization control plan in the response control plan is extracted, wherein the fertilization control plan refers to a standardized fertilization plan pre-set according to the crop nutrition model, soil test report or historical fertilization database, including basic fertilization amount, fertilization method and triggering conditions. The basic fertilization amount is the ratio of nutrients such as nitrogen, phosphorus and potassium set according to the crop type and growth stage. The fertilization method includes drip irrigation, foliar spraying, deep application of solid fertilizer, etc. The triggering conditions include soil EC value, crop phenotype or growth cycle node; the age of the greenhouse is the age of the greenhouse. The number of years of continuous use is then calibrated through long-term experiments to quantify the degree of soil fertility decline caused by greenhouse age, resulting in a fertility impact coefficient. For example, a greenhouse age of 1 to 3 years has a fertility impact coefficient of 1, indicating sufficient fertility with no significant degradation. A greenhouse age of 4 to 6 years has a fertility impact coefficient of 0.8, indicating a 10% to 20% decrease in organic matter and the need for humus supplementation. A greenhouse age of 7 to 10 years has a fertility impact coefficient of 0.6, indicating salinization risk and trace element imbalance. A greenhouse age of more than 10 years has a fertility impact coefficient of 0.4, indicating severe compaction and the need for soil improvement. Finally, based on the fertility impact coefficient, greenhouse fertilization control is adjusted to compensate for the natural decline in soil fertility caused by greenhouse age and avoid over- or under-fertilization. By quantifying the impact of historical planting history on soil through greenhouse age, dynamically matching crop needs, and achieving quantitative compensation for the greenhouse soil's historical state, the greenhouse's control accuracy and adaptability are improved.

[0051] Furthermore, step S600 also includes step S680, generating a real-time thermal demand curve of the target crop based on the second crop thermal demand index; step S690, traversing the real-time thermal demand curve in the historical thermal demand curve database of the target crop to obtain the most similar historical curve; step S6100, predicting the thermal demand index of the target crop based on the most similar historical curve to obtain a predicted crop thermal demand index; step S6110, based on the predicted crop thermal demand index, calling the response control plan to perform predictive pre-control on the greenhouse.

[0052] Preferably, based on the continuous monitoring value of the heat demand index of the second crop, the horizontal axis is time (such as the past 24 hours) and the vertical axis is the heat demand index value of the second crop, a real-time heat demand curve of the target crop is generated, and then the real-time heat demand curve is used to traverse the historical heat demand curve database of the target crop, wherein the historical heat demand curve database stores the historical heat demand curves of the same crop variety at different growth stages and under different environmental conditions, and each curve is associated with environmental parameters, control measures and crop response results, and then the real-time heat demand curve is traversed in the historical heat demand curve database of the target crop, that is, dynamic time warping or Euclidean distance is used to calculate the similarity between the real-time heat demand curve and the historical heat demand curve, and the historical curves with a similarity greater than 90% are screened in combination with the waveform shape consistency and the time axis expansion tolerance. The line is taken as the most similar historical curve. If there are multiple matches, the curve at the same growth stage or the curve with good crop performance after regulation is given priority; then the heat demand index of the target crop is predicted based on the most similar historical curve, that is, the subsequent change trend of the most similar historical curve is used as a template to generate a predicted value of the heat demand index and output the predicted heat demand index; finally, based on the predicted crop heat demand index, the response control plan is called to perform predictive pre-control on the greenhouse. For example, when entering the first threshold, the heat storage system is started in advance to preheat to avoid stress caused by a sudden drop in temperature; when entering the second threshold, the surface cooler is pre-cooled and the fan is operated at a low speed to relieve the high temperature peak pressure; when entering the third threshold, the solar heat storage and ground source heat pump are started and put on standby to cope with extreme weather; thereby significantly improving the stability of the greenhouse environment and resource utilization efficiency.

[0053] Furthermore, step S690 also includes step S691, extracting the first historical curve in the historical heat demand curve database; step S692, calculating the first curve distance between the real-time heat demand curve and the first historical curve; step S693, arranging the curves in the historical heat demand curve database in ascending order based on the first curve distance to obtain an ascending list of historical curves; step S694, taking the first historical curve in the ascending list of historical curves as the most similar historical curve.

[0054] Preferably, a historical curve is randomly extracted from the historical heat demand curve database as the first historical curve, which contains the continuous changes in the crop heat demand index over a certain period of time in the past, usually accompanied by environmental parameters and control records. The first curve distance between the real-time heat demand curve and the first historical curve is calculated using the Euclidean distance, where the first curve distance is a numerical indicator used to measure the difference in the morphology of two curves, with smaller values ​​indicating higher similarity. The curves in the historical heat demand curve database are then sorted in ascending order based on the first curve distance, i.e., the Euclidean distance between the real-time heat demand curve and all historical heat demand curves in the historical heat demand curve database are calculated and sorted from smallest to largest to obtain an ascending list of historical curves. Finally, the first historical curve with the smallest distance in the ascending list of historical curves is selected as the most similar historical curve, and the curve distance is checked to see if it is less than a preset threshold. At the same time, it is confirmed that the associated environmental scenario matches the current greenhouse state. This converts the complex crop heat demand pattern matching into quantifiable data retrieval, facilitating precise predictive control of greenhouses and achieving intelligent control of the agricultural environment.

[0055] The above specific embodiments do not constitute a limitation to the scope of protection of this application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of this application should be included in the scope of protection of this application. In some cases, the actions or steps recorded in this application can be performed in an order different from that in the embodiments and can still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. The greenhouse intelligent response control method based on environmental parameters is characterized by: include: Acquire target crops and collect infrared temperature of the canopy of the target crops in real time; Dynamically collecting distributed environmental parameters of the greenhouse where the target crop is located through a distributed multi-source sensor array; Traversing the predetermined related indicators in the distributed environmental parameters to obtain related environmental data, and coordinating with the canopy infrared temperature to obtain a first crop heat demand index, the first crop heat demand index indicating the current heat load level of the crop; Performing normalized weighted calculation on factor environment data obtained by traversing the distributed environmental parameters based on predetermined factor indicators to obtain an environmental impact coefficient; calibrating the first crop heat demand index using the environmental impact coefficient to obtain a second crop heat demand index; Based on the second crop heat demand index, a response control plan is called to perform intelligent control on the greenhouse.

2. The greenhouse intelligent response control method based on environmental parameters as claimed in claim 1, characterized in that: Traversing the predetermined related indicators in the distributed environment parameters to obtain related environment data, including: Extracting a first indicator from the predetermined related indicators; Traversing and screening the distributed environment parameters based on the first indicator to obtain a first parameter set; Extracting a first parameter from the first parameter set, where the first parameter corresponds to a first sensor in the first distributed sensor; forming a first visual environment structure network according to a first correspondence between the first sensor and the first parameter; The relevant environment data is constructed based on the first visual environment structure network.

3. The greenhouse intelligent response control method based on environmental parameters as claimed in claim 2, characterized in that: The predetermined related indicators include air temperature and solar radiation.

4. The greenhouse intelligent response control method based on environmental parameters as claimed in claim 2, characterized in that: The relevant environment data is formed based on the first visual environment structure network, including: Obtaining target planting locations for the target crops; Rendering the target planting point to the first visual environment structure network to obtain a first target visual map; Processing and analyzing the first target visibility graph according to a predetermined sampling and aggregation strategy to obtain a first processed value; Based on the first processed value, the relevant environmental data is obtained; Among them, including: In the first target visual map, a crop neighborhood is constructed with the target planting point as the center of a circle, wherein the crop neighborhood includes a primary neighborhood and a secondary neighborhood; Acquire a secondary sensor set corresponding to the secondary neighborhood, and randomly sample a secondary detection value set corresponding to the secondary sensor set to obtain a first sampling result; Aggregating the first sampling result according to the predetermined sampling aggregation strategy to obtain a first aggregate value; Obtaining a first-level sensor set corresponding to the first-level neighborhood, and randomly sampling a first-level detection value set corresponding to the first-level sensor set to obtain a second sampling result; Aggregating the second sampling result according to the predetermined sampling aggregation strategy to obtain a second aggregate value; The first aggregate value and the second aggregate value are weighted by variation to obtain the first processed value.

5. The greenhouse intelligent response control method based on environmental parameters as claimed in claim 1, characterized in that: Traversing the predetermined related indicators in the distributed environmental parameters to obtain related environmental data, and coordinating with the canopy infrared temperature to obtain a first crop heat demand index, including: obtaining a predetermined temperature threshold of the target crop; The first crop heat demand index is obtained by coordinating the relevant environmental data, the canopy infrared temperature and the lower temperature limit of the predetermined temperature threshold.

6. The greenhouse intelligent response control method based on environmental parameters as claimed in claim 1, characterized in that: The predetermined factor indicators include air humidity, wind speed and force, soil temperature and humidity, and carbon dioxide concentration.

7. The greenhouse intelligent response control method based on environmental parameters as claimed in claim 1, characterized in that: Based on the second crop heat demand index, calling a response control plan to intelligently control the greenhouse includes: Extracting a temperature control plan from the response control plan; When the second crop heat demand index is at a first threshold, activating the heat storage-release system to perform intelligent control on the greenhouse according to the temperature control plan; When the second crop heat demand index is at a second threshold, according to the temperature control plan, the surface cooler-fan heat collection and release system is activated to perform intelligent control on the greenhouse; When the second crop heat demand index is at a third threshold value, according to the temperature control plan, the solar energy-ground source heat pump composite heating system is activated to perform intelligent control on the greenhouse.

8. The greenhouse intelligent response control method based on environmental parameters as claimed in claim 1, characterized in that: Based on the second crop heat demand index, calling a response control plan to intelligently control the greenhouse includes: Extracting a fertilization control plan from the response control plan; Obtaining the age of the greenhouse and matching the fertility influence coefficient corresponding to the greenhouse age; Fertilization control of the greenhouse is corrected based on the fertility influence coefficient.

9. The greenhouse intelligent response control method based on environmental parameters as claimed in claim 1, characterized in that: After calling a response control plan based on the second crop heat demand index to perform intelligent control on the greenhouse, the method further includes: generating a real-time heat demand curve of the target crop based on the second crop heat demand index; Traversing the real-time heat demand curve in the historical heat demand curve database of the target crop to obtain the most similar historical curve; Predicting the heat requirement index of the target crop based on the most similar historical curve to obtain a predicted crop heat requirement index; Based on the predicted crop heat demand index, the response control plan is called to perform predictive pre-control on the greenhouse.

10. The greenhouse intelligent response control method based on environmental parameters as claimed in claim 9, characterized in that: Traversing the real-time heat demand curve in the historical heat demand curve database of the target crop to obtain the most similar historical curve includes: Extracting a first historical curve from the historical heat demand curve database; Calculating a first curve distance between the real-time heat demand curve and the first historical curve; Arranging the curves in the historical heat demand curve database in ascending order based on the first curve distance to obtain an ascending list of historical curves; The first historical curve in the ascending list of historical curves is used as the most similar historical curve.

Images