Load heterogeneous control system for greenhouse planting
By designing a load heterogeneous control system for environmental data acquisition, control parameter setting and optimization of control modules in greenhouse planting, using deep learning and multi-sensing technology, the precise adjustment of environmental parameters in greenhouses is achieved, and multiple varieties of planting are solved The insufficient resource optimization allocation in the country has improved crop yield and quality.
Patent Information
- Application Number
- CN202411222844.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-02
- Publication Date
- 2024-11-29
- Estimated Expiration
- 2044-09-02
AI Technical Summary
The existing load heterogeneous control system has shortcomings in the cultivation of multiple varieties and the optimal allocation of resources, and it is difficult to accurately identify and adjust the environmental parameters of different areas of the greenhouse, resulting in waste of resources and degradation of crop yield quality.
A load heterogeneous control system including environmental data acquisition module, control parameter setting module and optimization and regulation module was designed. Through real-time environmental data detection, deep learning analysis and multi-sensing technology, the light, humidity, temperature, etc. in the greenhouse are realized. Accurate adjustment of parameters, automatic adjustment of irrigation and temperature control, and optimize resource allocation.
It achieves accurate response to different plant growth needs, optimizes resource utilization, reduces energy consumption, and improves crop yield and quality, solving the problems of resource waste and yield decline caused by inaccurate response in traditional systems.
Smart Images

Figure CN119045583A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of agricultural engineering, and in particular to a load heterogeneous control system for greenhouse planting. Background Art
[0002] In modern greenhouse cultivation, environmental control systems are an important part of ensuring the healthy growth of crops. These systems usually provide plants with an ideal growth environment by controlling key parameters such as light, humidity, and temperature. However, traditional control methods often manage the entire greenhouse area with a unified standard, ignoring the specific needs of different plant species and crops in different areas. This is particularly evident in the case of multi-variety cultivation.
[0003] In the existing technology, load heterogeneous control manages the environmental factors in the greenhouse through a variety of control strategies and hardware combinations to better adapt to the growth requirements of different plants. However, due to the lack of precise control and real-time response capabilities, these systems have certain deficiencies in resource allocation and equipment control. For example, when multiple crops are planted in a greenhouse at the same time, it is difficult for the system to effectively identify and adjust the environmental parameters of each area, resulting in the inability to provide the most suitable growth conditions for each crop. This inaccurate response is not only likely to cause waste of resources, but may also affect the yield and quality of crops. The existing load heterogeneous control systems have obvious limitations in coping with multi-variety planting and optimal resource allocation. Summary of the invention
[0004] The purpose of the present invention is to provide a load heterogeneous control system for greenhouse planting, so as to solve the problem that the existing load heterogeneous control system has obvious limitations in dealing with multi-variety planting and resource optimization allocation.
[0005] To achieve the above object, the present invention provides the following technical solution: a load heterogeneous control system for greenhouse planting, the system comprising: Environmental data acquisition module, used to detect the working status of load heterogeneous equipment based on real-time environmental data; The control parameter setting module connected to the environmental data acquisition module is used to automatically set differentiated control parameters according to the crop types in each region to accurately meet the needs of the corresponding growth stage; The optimization and control module connected to the environmental data acquisition module and the control parameter setting module is used to continuously optimize the control logic through deep learning analysis of historical data and implement dynamic matching; The feedback signal adjustment module connected to the environmental data acquisition module, the control parameter setting module and the optimization and regulation module is used to utilize multi-sensor technology to integrate the feedback signal and adjust the execution mechanism in real time.
[0006] Preferably, the environmental data acquisition module detects the working status of load heterogeneous devices based on real-time environmental data, including: Based on the real-time temperature data, determine whether the temperature in the greenhouse is higher than the set temperature T upper limit; if it is higher, turn on the cooling device; Based on real-time monitoring of light intensity and adjusting the fill light time according to the light sensitivity index I; Adjust ventilation volume in real time based on CO2 concentration to ensure CO2 concentration is within an appropriate range; Determine whether the soil moisture is lower than the preset lower limit H, and if so, activate the watering device; The method of judging whether the temperature in the greenhouse is higher than the set upper limit T based on the real-time temperature data, and if higher, starting the cooling device also includes: According to the relationship between temperature change ΔT and time interval Δt, the heating rate is calculated as K1=ΔT / Δt; If K1>VT, (where VT is the speed threshold), it is considered that the current greenhouse environment is rising rapidly, and high-power ventilation and cooling devices are turned on first; If the temperature rise is less than the temperature difference warning value ΔTmin, the air conditioner is turned off to save power consumption but the window is kept slightly open; For the heating rate of the current environment, if K1 ≥ VTmin (where VTmin is the greenhouse cooling warning value), the judgment condition result is true and the corresponding operation is performed.
[0007] Preferably, the heating rate of the current environment is judged by a condition that if K1≥VTmin, the judgment condition result is true, and the corresponding operation is performed, which more specifically includes: Compare K1 with the greenhouse cooling warning value VTmin. If [K1 ≥ VTmin], it means that active cooling measures need to be taken and the air conditioning equipment should be started for forced cooling. Otherwise, cooling can only be carried out through natural ventilation. Use a timing strategy to ensure equipment operation efficiency. When temperature control conditions are met, check every 15 minutes to see if equipment needs to be adjusted. Adjust the air conditioning power and fan rotation speed to ensure that the temperature control target of the greenhouse environment is achieved, that is, in every other cycle, that is, t=n×cycle, if K1≥VTmin, start the air conditioning to cool down, where n=[1,2,3,...]; Set conditions to prevent excessive energy consumption due to extreme weather in a short period of time. Do not change the air conditioning settings until the temperature difference ΔT reaches the temperature difference compensation threshold ΔTc; The setting conditions are as follows to prevent excessive energy consumption due to extreme weather in a short period of time and not to change the air conditioning settings before the temperature difference ΔT reaches the temperature difference compensation threshold ΔTc: Record the greenhouse temperature data Ts under the current air-conditioning operation state and the target set temperature Tr when the air-conditioning operation starts; Using the difference between the current ambient temperature Ts and the target set temperature Tr, the real-time temperature difference ΔT=Ts−Tr is calculated; Determine whether the real-time temperature difference reaches the preset temperature difference compensation threshold ΔTc, that is, determine (|ΔT|≤|ΔTc|). If the condition is not met, it means that there is no need to change the device settings. Otherwise, the device needs to be adjusted according to the current environmental conditions. Set the air conditioning working mode adjustment cycle C, and execute it according to the above conditions. When the cycle C ends and |ΔT|>|ΔTc|) or the system determines that the external temperature has changed, adjust the working state to respond to the new demand.
[0008] Preferably, the judging method (|ΔT|≤|ΔTc|) further includes: if the condition is not satisfied, it means that there is no need to change the device settings; otherwise, the device needs to be adjusted according to the current environmental conditions. Record the last adjustment time To and the current temperature Ts, and obtain the external reference temperature Te at this time; Environmental assessment, determining that when |Ts−Tr|>|ΔTc| and the time interval between the last adjustment at the current time t is greater than the minimum allowed adjustment period, the trigger condition is updated, indicating that the control strategy should be reset; Dynamically change the set temperature or equipment operation mode according to the update situation to maintain the internal environment stable, and set the update condition as |Ts−Tr|>|ΔTc|; Execute the above determination and make corresponding adjustments, record the latest status and send adjustment instructions to the control parameter setting module when necessary.
[0009] Preferably, the control parameter module automatically sets differentiated control parameters according to the crop types in each region to accurately meet the needs of the corresponding growth stage, including: Combine the classification data of crops in the planting area with geographic information technology to determine the location distribution information of each crop; The combined database searches for the range of suitable growing conditions required for each growth cycle of the crop; Automatically generate control parameter setting rule files according to the specific needs of the growth stage in each area; Implement differentiated irrigation and temperature regulation programs to simulate artificial climate environments that best suit the developmental needs of current plant species; Calibration checks are regularly performed for the specific needs of specific crops to ensure standards are met or strategies are updated to improve results.
[0010] Preferably, the control parameter module automatically sets differentiated control parameters according to the crop types in each region to accurately meet the needs of the corresponding growth stage. More details include: The classification data of different crops in the greenhouse are combined with geographic information technology to determine the specific location distribution of each crop. The formula is: Li = GIS (Xi, Yi, Zi), Among them, Li represents the spatial position of the i-th crop, Xi, Yi, Zi are geographical coordinates; By searching the database, we can obtain the suitable environmental conditions required by each crop at each growth stage. The condition data is stored in the form of a multidimensional matrix, which represents the various parameter requirements of the crop. The formula is: Ci,j=Retrieve(Di,Gj), Among them, Ci,j is the environmental condition required by crop i at growth stage j, Di is the crop data, and Gj is the growth stage; According to the growth requirements of crops, the control parameter setting rule file is automatically generated, and the lighting time and intensity are set using the formula: , Among them, Iij is the light intensity required by the i-th crop at growth stage j, Imax,j is the optimal light intensity, Tij,Hij are temperature and humidity respectively, Topt,j,Hopt,j are the optimal temperature and humidity; The temperature control setting adopts the formula: , Where Tset,i is the target temperature of the i-th crop, and ΔTi is the temperature deviation adjusted according to the current environmental conditions; According to the generated control parameter rule file, the system implements differentiated irrigation and temperature regulation for crops in different areas. The irrigation water volume is calculated using the formula: , Among them, Wi is the irrigation amount of the i-th crop, Wbase,i is the basic irrigation amount, ki is the adjustment coefficient, and Si is the real-time reading of the soil moisture sensor; The system adjusts the temperature based on the deviation between the real-time temperature data and the preset temperature target. The temperature adjustment adopts the formula: , Among them, ΔTadj,i is the temperature deviation that needs to be adjusted, and Tcurrent is the current ambient temperature; For the specific needs of each crop, the system will perform regular calibration checks to ensure that the control parameters are consistent with the actual needs of the crop. The calibration process is completed through the feedback signal adjustment module. Multi-sensor technology is used to monitor and feedback environmental changes in the greenhouse in real time, using the formula: , Among them, Fi is the comprehensive feedback signal, and Si,k is the kth sensor data of the i-th crop.
[0011] Preferably, the optimization and control module continuously optimizes the control logic through deep learning analysis of historical data to achieve dynamic matching and self-adaptation, including: Collect long-term accumulated operating parameters and output data sets as historical databases; Establish an environmental control model and continue to use newly added historical data to train and adjust the prediction accuracy; In-depth analysis of past environmental change trends and their inherent regularity in affecting production; Add an automated fault recovery function to ensure that the system can be quickly restarted and run automatically in the event of a sudden accident causing a system crash; Online monitoring of the deviation between actual performance and theoretical optimal configuration enables timely dynamic parameter adjustment to optimize control performance and reduce energy loss levels.
[0012] Preferably, the optimization and control module continuously optimizes the control logic through deep learning analysis of historical data to achieve dynamic matching and self-adaptation, further comprising: Collect the long-term accumulated operating parameters and output data of the greenhouse as the basis for subsequent modeling and optimization, using the formula: Dhist={(Ti,Hi,Ii,Ci,Wi,Yi)|i=1,2,…,n}, Among them, Dhist represents the data set of the historical database, Ti, Hi, Ii, Ci, Wi represent the temperature, humidity, light intensity, carbon dioxide concentration and irrigation amount collected for the i-th time, and Yi represents the corresponding crop yield or quality; The environmental control model is established using the historical database Dhist. The control model is in the form of: Y=f(T,H,I,C,W)+ϵ, Among them, Y is the expected yield or quality of the crop, f is the control model, ϵ is the model error, T, H, I, C, and W represent the collected temperature, humidity, light intensity, carbon dioxide concentration, and irrigation amount, respectively; During the model training process, the system continuously uses the newly added historical data to retrain the model and update the weights and parameters. The loss function in the training process uses the mean square error (MSE) to measure the deviation between the predicted value and the actual value. The specific formula is: , Where MSE is the mean square error, Yi is the actual value of the i-th sample, represents the predicted value of the i-th sample, and n represents the total number of samples; Through in-depth analysis of historical data, the system identifies the long-term impact of changes in environmental parameters on crop yield and quality, extracts the inherent regularity, and uses the formula: X(t)=ϕ1X(t−1)+ϕ2X(t−2)+⋯+θ0+ϵt, Among them, X(t) represents the environmental parameters at time t, ϕ and θ are the coefficients of the model respectively.
[0013] Based on the trend analysis results, the system predicts future environmental changes and adjusts control parameters in advance to optimize the climate conditions in the greenhouse; Monitor the working status of each module online. When an abnormality or fault is detected, the fault recovery mechanism is automatically triggered. The fault detection formula is: , Fault(t) represents the fault state at time t, X(t) represents the actual measured value of the system at time t, Xset is the desired control parameter, δ is the allowable deviation range, and when a fault occurs, it automatically switches to the backup mode, quickly restores key control functions, and restarts in the background to diagnose the cause of the fault; Real-time monitoring of the deviation between the environmental parameters in the greenhouse and the theoretical optimal configuration. By comparing the difference between the actual monitoring data Xactual and the optimal setting value Xopt, the control parameters are dynamically adjusted. The dynamic adjustment of the control parameters uses the formula: ΔX=Kp·(Xopt-Xactual)+Ki·∑(Xopt-Xactual)+Kd·(d(Xopt-Xactual) / dt), Among them, ΔX is the control parameter that needs to be adjusted, Xopt is the theoretical optimal setting value, Xactual is the actual monitored environmental parameter value, Kp is the proportional control coefficient, Ki is the integral control coefficient, and Kd is the differential control coefficient.
[0014] Preferably, the feedback signal adjustment module utilizes multi-sensor technology to integrate the feedback signal, and the real-time adjustment execution mechanism includes: Set up information transmission interfaces between various types of sensing instruments to be compatible with various types of sensor input ports; Comprehensively and weigh the importance and weight of different indicator types to build a unified feedback evaluation standard; Independently detect and isolate sources of signal interference on a single router; Regularly calibrate the reading accuracy of all measuring tools; Equipped with disaster recovery switching backup circuit.
[0015] Preferably, the feedback signal adjustment module utilizes multi-sensor technology to integrate the feedback signal, and the real-time adjustment execution mechanism further includes: Set a unified sensor information transmission interface using the formula: Ij=f(Sj,Pj), Where Ij represents the information transmission interface of the jth sensor, Sj represents the model of the jth sensor, Pj represents the data format of the jth sensor, and f is the interface adaptation function; Taking into account the sensitivity and volatility of various environmental indicators, appropriate weights are assigned to different indicators. Based on these weights, a unified feedback evaluation standard is constructed. The formula used to construct the unified feedback evaluation standard is: , Among them, Feval is the unified feedback evaluation standard, m is the total number of environmental indicators, wk is the weight of the kth indicator, Xk is the current actual value of the kth indicator, Xset,k is the target setting value of the kth indicator, and σk is the volatility or standard deviation of the kth indicator; Independently detect and isolate the signal interference source on a single router. The signal interference detection judgment formula is as follows: , Where Dint(t) is the signal interference state at time t, 1 indicates interference is detected, 0 indicates no interference, R(t) is the signal transmission rate at time t, and δR is the threshold of signal interference; Regularly calibrate the reading accuracy of all measuring tools. The calibration formula for regular calibration is: Ck=Xk+Δk, Where Ck is the reading of the kth sensor after calibration, Xk is the actual measurement value before calibration, and Δk is the calibration deviation; Equipped with a disaster recovery switchover backup circuit, it will automatically switch to the backup circuit when a core component fails or the environment is bad. The judgment and triggering conditions for disaster recovery switching are as follows: , Wherein, Ssw(t) is the disaster recovery switching state at time t, 1 indicates triggering the backup circuit, 0 indicates normal operation, Fcrit(t) is the critical fault parameter at time t, and τ is the threshold of disaster recovery switching.
[0016] It can be seen from the above technical solution that the present invention has the following beneficial effects: The load heterogeneous control system for greenhouse planting detects the working status of load heterogeneous equipment based on real-time environmental data through the environmental data acquisition module. The control parameter setting module automatically sets differentiated control parameters according to the crop types in each region to accurately meet the needs of the corresponding growth stage. The optimization and control module continuously optimizes the control logic through deep learning analysis of historical data and implements dynamic matching. The feedback signal adjustment module is used to use multi-sensor technology to integrate feedback signals and adjust the execution mechanism in real time, thereby realizing accurate adjustment of key parameters such as light, humidity, and temperature in the greenhouse. This accurate adjustment can not only respond to the growth needs of different plants in real time, but also effectively optimize the allocation and utilization of resources, reduce unnecessary energy consumption, and maintain a stable control effect in a complex environment where multiple varieties of plants coexist, avoiding waste of resources and reduction of crop quality caused by inaccurate response of traditional systems. The problem that the existing technology has certain deficiencies in resource allocation and equipment control due to the lack of accurate control and real-time response capabilities, and inaccurate response not only easily causes waste of resources, but also may affect the yield and quality of crops, and has obvious limitations in coping with multiple varieties of planting and optimal resource allocation. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] Figure 1 This is a schematic diagram of module connection of the present invention. DETAILED DESCRIPTION
[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0019] like Figure 1 As shown in the figure, in order to deal with the problem of inaccurate response of load heterogeneous control systems to different plant growth requirements in greenhouse cultivation, a new load heterogeneous control method for greenhouse cultivation is proposed. This system uses real-time sensor data analysis and machine learning technology to achieve refined management, precision irrigation and other optimal configuration of agricultural operations, ensuring that different plant types can get the most optimized environmental regulation support at different growth stages. The system includes: Environmental data acquisition module for detecting the working status of load heterogeneous equipment based on real-time environmental data. In order to deal with the problem of inaccurate response of load heterogeneous control systems to the growth requirements of different plants in greenhouse cultivation, we proposed a load heterogeneous control method for greenhouse cultivation. This method combines real-time sensor data analysis and machine learning technology to achieve refined management, precision irrigation and other optimal configuration of agricultural operations through multiple steps, ensuring that different plant types can get the most optimized environmental regulation support at different growth stages.
[0020] The next step is to automatically set differentiated control parameters for specific areas to accurately meet the needs of the corresponding growth stage, and the control parameter setting module connected to the environmental data acquisition module. In practical applications, for example, in a comprehensive experimental greenhouse, small tomatoes that like cool and humid conditions, large tomatoes that need sufficient sunlight, and other crops are planted. Under this premise, we need the system to automatically adjust various control parameters according to the characteristics of the crop varieties, such as irrigation frequency, ventilation, lighting time, and CO2 supply ratio. In this way, they can meet their different requirements for water and light during growth. For example: when the system recognizes the area where large tomatoes are planted, it will automatically adjust according to the preset logic to increase the light during the daytime and reduce the amount of water irrigation to adapt to the heat-loving and drought-resistant characteristics.
[0021] Through deep learning analysis of historical data, the control logic is continuously optimized, and the optimization control module is dynamically matched and connected with the environmental data acquisition module and the control parameter setting module. By analyzing and sorting out the relevant monitoring data accumulated in the past, it is possible to find the rules for the best greenhouse conditions required for a specific type of vegetable from the germination stage to the harvest state. These experiences will be used to guide more effective control plans for the cultivation of the same or similar crops in the future. For example, in the process of summarizing the data of shallot planting in the previous cycle, it was concluded that the first 35-45 days of the growth cycle of this type of plant is a rapid growth period. At this time, maintaining relatively high water and light supply has a good promoting effect on increasing yields; then when encountering a new round of the same planting, the adjustment strategy can be made in time to make the production link more effective.
[0022] The feedback signal adjustment module uses multi-sensor technology to integrate feedback signals, adjust the execution mechanism in real time, and connect with the environmental data acquisition module, control parameter setting module, and optimization and regulation module. In this process, each adjustment and control is inseparable from the comprehensive use and precise feedback of multiple sensors. For example, in the process of monitoring irrigation conditions, the soil moisture sensor will continuously feedback the moisture status in the soil to determine when to make the next water replenishment or stop spraying; the air temperature and light level are tracked by infrared and ultraviolet sensing technology. Only in this way can the smooth operation of the entire regulation chain be ensured, thereby forming a benign adaptive regulation cycle.
[0023] In summary, this innovative solution aims to improve the efficiency of intelligent greenhouse cultivation while achieving the goal of cost savings. Through strict supervision of each Mokui and the use of advanced technical means, it ensures that each variety thrives under conditions suitable for its growth, ultimately bringing the agricultural industry closer to sustainable development.
[0024] The environmental data acquisition module detects the working status of load heterogeneous equipment based on real-time environmental data, including: Based on the real-time temperature data, determine whether the temperature in the greenhouse is higher than the set temperature T upper limit; if it is higher, turn on the cooling device; Based on real-time monitoring of light intensity and adjusting the fill light time according to the light sensitivity index I; Adjust ventilation volume in real time based on CO2 concentration to ensure CO2 concentration is within an appropriate range; Determine whether the soil moisture is lower than the preset lower limit H, and if so, activate the watering device; The method of judging whether the temperature in the greenhouse is higher than the set upper limit T based on the real-time temperature data, and if higher, starting the cooling device also includes: According to the relationship between temperature change ΔT and time interval Δt, the heating rate is calculated as K1=ΔT / Δt; If K1>VT, (where VT is the speed threshold), it is considered that the current greenhouse environment is rising rapidly, and high-power ventilation and cooling devices are turned on first; If the temperature rise is less than the temperature difference warning value ΔTmin, the air conditioner is turned off to save power consumption but the window is kept slightly open; For the heating rate of the current environment, if K1 ≥ VTmin (where VTmin is the greenhouse cooling warning value), the judgment condition result is true and the corresponding operation is performed.
[0025] The environmental data acquisition module monitors key parameters such as temperature, light, carbon dioxide concentration and soil moisture in the greenhouse in real time through various sensors. The system determines whether the temperature in the greenhouse exceeds the set upper limit T based on the temperature data. If it exceeds, the cooling equipment is turned on, and the high-power ventilation and cooling device is decided based on the calculation result of the temperature change rate K1. In addition, the system adjusts the light filling time according to the light intensity and light sensitivity index I to ensure that the crops get enough light. The real-time monitoring of carbon dioxide concentration and the adjustment of ventilation volume ensure the appropriate CO2 level. When the soil moisture is lower than the lower limit H, the system will automatically activate the watering equipment.
[0026] Through real-time monitoring and regulation, the system can respond in the shortest possible time to ensure that the greenhouse environment is always in the optimal state for crop growth. By calculating the heating rate and combining different control strategies, the system can save energy while efficiently cooling down, avoid over-reliance on a single cooling method, and improve the flexibility of the system and energy efficiency.
[0027] The environmental data acquisition module can use other types of sensors, such as thermocouple sensors instead of traditional temperature sensors, or ultrasonic humidity sensors instead of capacitive humidity sensors to cope with special environmental conditions. The calculation method of the light sensitivity index I can also be adjusted or replaced, such as using a different spectral range or a different calculation algorithm to adapt to the lighting requirements of specific crops.
[0028] For the heating rate of the current environment, if K1≥VTmin, the conditional judgment result is true, and the corresponding operation is performed, which specifically includes: Compare K1 with the greenhouse cooling warning value VTmin. If [K1 ≥ VTmin], it means that active cooling measures need to be taken and the air conditioning equipment should be started for forced cooling. Otherwise, cooling can only be carried out through natural ventilation. Use a timing strategy to ensure equipment operation efficiency. When temperature control conditions are met, check every 15 minutes to see if equipment needs to be adjusted. Adjust the air conditioning power and fan rotation speed to ensure that the temperature control target of the greenhouse environment is achieved, that is, in every other cycle, that is, t=n×cycle, if K1≥VTmin, start the air conditioning to cool down, where n=[1,2,3,...]; Set conditions to prevent excessive energy consumption due to extreme weather in a short period of time. Do not change the air conditioning settings until the temperature difference ΔT reaches the temperature difference compensation threshold ΔTc; The setting conditions are as follows to prevent excessive energy consumption due to extreme weather in a short period of time and not to change the air conditioning settings before the temperature difference ΔT reaches the temperature difference compensation threshold ΔTc: Record the greenhouse temperature data Ts under the current air-conditioning operation state and the target set temperature Tr when the air-conditioning operation starts; Using the difference between the current ambient temperature Ts and the target set temperature Tr, the real-time temperature difference ΔT=Ts−Tr is calculated; Determine whether the real-time temperature difference reaches the preset temperature difference compensation threshold ΔTc, that is, determine (|ΔT|≤|ΔTc|). If the condition is not met, it means that there is no need to change the device settings. Otherwise, the device needs to be adjusted according to the current environmental conditions. Set the air conditioning working mode adjustment cycle C, and execute it according to the above conditions. When the cycle C ends and |ΔT|>|ΔTc|) or the system determines that the external temperature has changed, adjust the working state to respond to the new demand.
[0029] By calculating the current environment's heating rate K1 and comparing it with the greenhouse cooling warning value VTmin, the system determines whether cooling measures need to be taken immediately. If the conditions are met, the air conditioner is started for forced cooling, otherwise natural ventilation is used. During the operation of the equipment, the system will regularly check the temperature control effect and adjust the air conditioning power and fan speed according to the temperature control target to ensure the stability of the greenhouse environment. In addition, the system sets conditions to prevent excessive energy consumption due to short-term extreme weather changes. The air conditioning settings will only be changed when the temperature difference reaches the compensation threshold ΔTc. This implementation method can effectively identify emergency situations of ambient temperature changes and take corresponding measures in time to ensure the stability of the greenhouse environment. Through timing strategies and condition settings, the system not only improves the cooling effect, but also avoids energy waste, and improves the overall operating efficiency and economy.
[0030] Under different environmental conditions, the cooling warning value VTmin can be adjusted according to actual needs. For example, a lower VTmin value can be set under warmer climate conditions. At the same time, the system can integrate other control measures, such as using a liquid cooling system as a supplementary cooling method to improve the ability to cope with high temperature environments. The interval time of the timing strategy can also be adjusted according to the size of the greenhouse and the type of crop to ensure the adaptability and flexibility of the cooling strategy.
[0031] According to the judgment (|ΔT|≤|ΔTc|), if the condition is not met, it means that there is no need to change the device settings, otherwise the device needs to be adjusted according to the current environmental conditions, and further includes: Record the last adjustment time To and the current temperature Ts, and obtain the external reference temperature Te at this time; Environmental assessment, determining that when |Ts−Tr|>|ΔTc| and the time interval between the last adjustment at the current time t is greater than the minimum allowed adjustment period, the trigger condition is updated, indicating that the control strategy should be reset; Dynamically change the set temperature or equipment operation mode according to the update situation to maintain the internal environment stable, and set the update condition as |Ts−Tr|>|ΔTc|; Execute the above determination and make corresponding adjustments, record the latest status and send adjustment instructions to the control parameter setting module when necessary.
[0032] The system monitors the changes in temperature inside and outside the greenhouse in real time, combines historical data records with environmental assessments, and determines whether the current temperature control equipment needs to be adjusted. First, the current temperature Ts and external temperature Te are recorded, and the difference between them and the set temperature Tr is evaluated. If the temperature difference |Ts − Tr| exceeds the preset compensation threshold ΔTc, or the external temperature Te is lower than the reference temperature difference ΔTt, and the time interval from the last adjustment has exceeded the minimum allowable adjustment period, the system will re-evaluate and update the control strategy, and dynamically adjust the set temperature or the operating mode of the equipment according to the updated conditions to ensure the stability of the greenhouse environment. After performing the adjustment operation, the system will record the latest status and send the adjustment instruction to the control parameter setting module when necessary to ensure the automation and accuracy of the system.
[0033] This implementation method enhances the system's ability to adapt to changes in the external environment, especially when faced with drastic changes in external temperature or other extreme weather. The system can respond quickly and make corresponding adjustments to avoid energy waste and maintain ideal growing conditions in the greenhouse. Through recording and monitoring, the system can automatically adjust settings when needed, avoiding frequent manual intervention, further improving the system's intelligence level and operating efficiency.
[0034] In different environments, the reference baseline value of the external temperature Te and the temperature difference threshold ΔTc can be adjusted according to specific needs. For example, under relatively stable climate conditions, these thresholds can be appropriately relaxed to reduce unnecessary frequent adjustments. In addition, the environmental assessment algorithm can be replaced with other more complex meteorological models to improve the prediction and response capabilities to complex weather conditions. The minimum allowable adjustment period C can also be flexibly set according to the size of the greenhouse and crop requirements to ensure that the system can maintain optimal performance in different application scenarios.
[0035] The control parameter module automatically sets differentiated control parameters according to the crop types in each region to accurately meet the needs of the corresponding growth stage, including: Combine the classification data of crops in the planting area with geographic information technology to determine the location distribution information of each crop; The combined database searches for the range of suitable growing conditions required for each growth cycle of the crop; Automatically generate control parameter setting rule files according to the specific needs of the growth stage in each area; Implement differentiated irrigation and temperature regulation programs to simulate artificial climate environments that best suit the developmental needs of current plant species; Calibration checks are regularly performed for the specific needs of specific crops to ensure standards are met or strategies are updated to improve results.
[0036] The module first uses geographic information technology (GIS) to locate the specific locations of different crops in the greenhouse, combines these locations with crop classification data, and forms a crop distribution information map. Then, the system retrieves the appropriate conditions required for each type of crop during its growth cycle through the database, such as temperature, humidity, light, etc., and generates corresponding control parameter setting rule files. Based on these files, the system will automatically implement differentiated irrigation and temperature regulation to ensure that each crop is in the best growth environment. At the same time, the system will regularly calibrate and check the control parameters to ensure that they are consistent with actual growth needs and update the strategy based on the latest data.
[0037] This implementation method uses GIS technology and database retrieval functions to achieve accurate positioning and environmental condition setting for different crops in the greenhouse, thereby improving the efficiency and quality of crop growth. The differentiated management method enables the system to better adapt to the personalized needs of different crops, reduce resource waste, and optimize environmental control. In addition, regular calibration and update strategies ensure continuous optimization and efficient operation of the system.
[0038] In other embodiments, the control parameter setting module may adopt a more refined control strategy, such as introducing more environmental parameters (such as carbon dioxide concentration, soil pH, etc.) for multi-dimensional adjustment. The crop classification data may also be combined with a real-time monitoring system, such as image recognition technology, to more accurately locate crop distribution. Calibration checks for specific crop needs may be performed by automated robots to improve inspection efficiency and accuracy.
[0039] The control parameter module automatically sets differentiated control parameters according to the crop types in each region to accurately meet the needs of the corresponding growth stage. More details include: The classification data of different crops in the greenhouse are combined with geographic information technology to determine the specific location distribution of each crop. The formula is: Li = GIS (Xi, Yi, Zi), Among them, Li represents the spatial position of the i-th crop, Xi, Yi, Zi are geographical coordinates; By searching the database, we can obtain the suitable environmental conditions required by each crop at each growth stage. The condition data is stored in the form of a multidimensional matrix, which represents the various parameter requirements of the crop. The formula is: Ci,j=Retrieve(Di,Gj), Among them, Ci,j is the environmental condition required by crop i at growth stage j, Di is the crop data, and Gj is the growth stage; According to the growth requirements of crops, the control parameter setting rule file is automatically generated, and the lighting time and intensity are set using the formula: , Among them, Iij is the light intensity required by the i-th crop at growth stage j, Imax,j is the optimal light intensity, Tij,Hij are temperature and humidity respectively, Topt,j,Hopt,j are the optimal temperature and humidity; The temperature control setting adopts the formula: , Where Tset,i is the target temperature of the i-th crop, and ΔTi is the temperature deviation adjusted according to the current environmental conditions; According to the generated control parameter rule file, the system implements differentiated irrigation and temperature regulation for crops in different areas. The irrigation water volume is calculated using the formula: , Among them, Wi is the irrigation amount of the i-th crop, Wbase,i is the basic irrigation amount, ki is the adjustment coefficient, and Si is the real-time reading of the soil moisture sensor; The system adjusts the temperature based on the deviation between the real-time temperature data and the preset temperature target. The temperature adjustment adopts the formula: , Among them, ΔTadj,i is the temperature deviation that needs to be adjusted, and Tcurrent is the current ambient temperature; For the specific needs of each crop, the system will perform regular calibration checks to ensure that the control parameters are consistent with the actual needs of the crop. The calibration process is completed through the feedback signal adjustment module. Multi-sensor technology is used to monitor and feedback environmental changes in the greenhouse in real time, using the formula: , Among them, Fi is the comprehensive feedback signal, and Si,k is the kth sensor data of the i-th crop.
[0040] The control parameter module first locates the spatial position of different crops in the greenhouse through geographic information technology (GIS). The position of each crop is determined by its geographic coordinates (Xi, Yi, Zi). Then, the system retrieves the database to obtain the environmental conditions required for each crop at its different growth stages. These condition data are stored in the form of a multidimensional matrix (Ci, j). Through these data, the system generates differentiated control parameter rule files to set the light intensity, temperature, humidity and other parameters required for each crop at different growth stages. The temperature control setting is based on the comparison between real-time environmental data and preset targets. The system calculates the temperature deviation through a formula and makes corresponding adjustments. In addition, the irrigation amount is also calculated through a formula and dynamically adjusted in combination with real-time soil moisture data. The system also performs regular calibration checks and uses the feedback signal adjustment module to monitor environmental changes in real time using multi-sensor technology to ensure that the control parameters match actual needs.
[0041] This implementation method achieves precise positioning and personalized environment settings for different crops by utilizing the combination of GIS technology and database. Through the parameter setting of the multi-dimensional matrix, the system can accurately control environmental factors such as light, temperature and humidity in the greenhouse, so that each crop can grow under optimal conditions. In addition, through dynamic irrigation and temperature regulation, the system improves resource utilization efficiency, reduces energy consumption, and ensures the stability and optimized control of the greenhouse environment.
[0042] In other embodiments, GIS technology can be replaced by other positioning technologies, such as laser ranging or acoustic positioning, to improve positioning accuracy or adapt to different greenhouse structures. The method of obtaining crop classification data can also be changed from manual input to automatic collection, using image recognition or drone inspection technology. The control algorithms for irrigation and temperature regulation can be further optimized, using adaptive control or fuzzy logic control to cope with complex environmental changes. Calibration checks can be performed by automated equipment to reduce manual intervention and improve the system's self-management capabilities.
[0043] The optimization and control module continuously optimizes the control logic through deep learning analysis of historical data to achieve dynamic matching and self-adaptation, including: Collect long-term accumulated operating parameters and output data sets as historical databases; Establish an environmental control model and continue to use newly added historical data to train and adjust the prediction accuracy; In-depth analysis of past environmental change trends and their inherent regularity in affecting production; Add an automated fault recovery function to ensure that the system can be quickly restarted and run automatically in the event of a sudden accident causing a system crash; Online monitoring of the deviation between actual performance and theoretical optimal configuration enables timely dynamic parameter adjustment to optimize control performance and reduce energy loss levels.
[0044] The optimization and control module first collects the long-term accumulated operating parameters and result data in the greenhouse and builds a historical database. Based on these data, the system establishes an environmental control model to predict crop yield or quality. The model improves the accuracy of prediction through continuous training and updating. The system analyzes the environmental change trends in historical data through deep learning, identifies the key factors affecting yield, and optimizes the control logic. The module also has an automatic fault recovery function. When the system detects an abnormality, it can quickly trigger the fault recovery program to ensure the stable operation of the system. In addition, the system monitors the deviation of the environmental parameters in the greenhouse from the theoretical optimal configuration in real time, and dynamically adjusts the control parameters to reduce energy consumption and improve control performance.
[0045] This implementation method achieves continuous optimization of environmental control logic through deep learning analysis of historical data, can dynamically match the needs of crops at different growth stages, and improves yield and quality. At the same time, the automated fault recovery function ensures the high reliability of the system and can quickly recover in emergencies, reducing downtime and losses. In addition, the real-time dynamic parameter adjustment function can reduce energy consumption and improve the operating efficiency of greenhouses.
[0046] In other embodiments, the collection method of the historical database can be expanded to include more environmental variables, such as carbon dioxide concentration or soil pH value, the environmental control model can adopt more complex machine learning algorithms, such as deep neural networks or reinforcement learning, to improve prediction accuracy and model adaptability, the fault recovery function can also integrate more sensors and monitoring systems to detect a wider range of potential faults, and the dynamic parameter adjustment function can be further optimized. By using self-learning algorithms, the system can adjust control parameters more accurately.
[0047] The optimization and control module continuously optimizes the control logic through deep learning analysis of historical data to achieve dynamic matching and self-adaptation, further including: Collect the long-term accumulated operating parameters and output data of the greenhouse as the basis for subsequent modeling and optimization, using the formula: Dhist={(Ti,Hi,Ii,Ci,Wi,Yi)|i=1,2,…,n}, Among them, Dhist represents the data set of the historical database, Ti, Hi, Ii, Ci, Wi represent the temperature, humidity, light intensity, carbon dioxide concentration and irrigation amount collected for the i-th time, and Yi represents the corresponding crop yield or quality; The environmental control model is established using the historical database Dhist. The control model is in the form of: Y=f(T,H,I,C,W)+ϵ, Among them, Y is the expected yield or quality of the crop, f is the control model, ϵ is the model error, T, H, I, C, and W represent the collected temperature, humidity, light intensity, carbon dioxide concentration, and irrigation amount, respectively; During the model training process, the system continuously uses the newly added historical data to retrain the model and update the weights and parameters. The loss function in the training process uses the mean square error (MSE) to measure the deviation between the predicted value and the actual value. The specific formula is: , Among them, MSE is the mean square error, Yi is the actual value of the i-th sample, represents the predicted value of the i-th sample, and n represents the total number of samples; Through in-depth analysis of historical data, the system identifies the long-term impact of changes in environmental parameters on crop yield and quality, extracts the inherent regularity, and uses the formula: X(t)=ϕ1X(t−1)+ϕ2X(t−2)+⋯+θ0+ϵt, Among them, X(t) represents the environmental parameters at time t, ϕ and θ are the coefficients of the model respectively.
[0048] Based on the trend analysis results, the system predicts future environmental changes and adjusts control parameters in advance to optimize the climate conditions in the greenhouse; Monitor the working status of each module online. When an abnormality or fault is detected, the fault recovery mechanism is automatically triggered. The fault detection formula is: , Fault(t) represents the fault state at time t, X(t) represents the actual measured value of the system at time t, Xset is the desired control parameter, δ is the allowable deviation range, and when a fault occurs, it automatically switches to the backup mode, quickly restores key control functions, and restarts in the background to diagnose the cause of the fault; Real-time monitoring of the deviation between the environmental parameters in the greenhouse and the theoretical optimal configuration. By comparing the difference between the actual monitoring data Xactual and the optimal setting value Xopt, the control parameters are dynamically adjusted. The dynamic adjustment of the control parameters uses the formula: ΔX=Kp·(Xopt-Xactual)+Ki·∑(Xopt-Xactual)+Kd·(d(Xopt-Xactual) / dt), Among them, ΔX is the control parameter that needs to be adjusted, Xopt is the theoretical optimal setting value, Xactual is the actual monitored environmental parameter value, Kp is the proportional control coefficient, Ki is the integral control coefficient, and Kd is the differential control coefficient.
[0049] In this embodiment, the optimization and control module collects environmental data and crop yield data accumulated over a long period of time in the greenhouse to form a historical database (Dhist). The database includes data such as temperature, humidity, light intensity, carbon dioxide concentration, irrigation amount, and corresponding crop yield or quality (Yi). Based on these data, the system establishes an environmental control model. The model predicts crop yield or quality through the formula Y=f(T,H,I,C,W)+ϵ. As new data is continuously added, the system uses these data to retrain the model to optimize the accuracy of the prediction. The loss function in the training process uses the mean square error (MSE) to measure the deviation between the predicted value and the actual value. Through in-depth analysis of historical data, the system identifies the long-term impact of changes in environmental parameters on crop yield, and predicts future environmental changes through the trend analysis formula X(t)=ϕ1X(t−1)+ϕ2X(t−2)+⋯+θ0+ϵt. Based on these prediction results, the system adjusts the control parameters in the greenhouse in advance to optimize climate conditions.
[0050] The system also monitors the working status of each module in real time. When an abnormality or fault is detected, the fault recovery mechanism will be automatically triggered. The system will automatically switch to the backup mode to ensure the continuity of the control function, and restart and diagnose the cause of the fault in the background. For the environmental parameters monitored in real time, the system will compare the actual data (Xactual) with the theoretical optimal setting value (Xopt), and dynamically adjust the control parameters according to the calculated deviation ΔX to ensure that the environment in the greenhouse is always in the best state.
[0051] Through deep learning of historical data and continuous model optimization, the system can accurately predict and control the environmental conditions in the greenhouse, thereby improving crop yield and quality. Real-time monitoring and dynamic parameter adjustment functions ensure the accuracy of environmental control and reduce energy consumption, while also improving the reliability and adaptability of the system. The automated fault recovery function enables the system to respond quickly and resume normal operation in the face of unexpected situations, reducing potential losses.
[0052] In other embodiments, the type and scope of the historical database can be further expanded to include more environmental and biological indicators, such as air pressure, wind speed, crop leaf area, etc. The environmental control model can adopt other advanced machine learning algorithms, such as support vector machines or Bayesian networks, to enhance the predictive ability and adaptability of the model. The fault detection mechanism can add additional redundant systems or multi-layer detection algorithms to enhance the accuracy and response speed of fault detection. The dynamic parameter adjustment algorithm can also be combined with the self-learning system to enable the system to continuously optimize the control strategy during operation.
[0053] The feedback signal adjustment module uses multi-sensor technology to integrate feedback signals, and the real-time adjustment execution mechanism includes: Set up information transmission interfaces between various types of sensing instruments to be compatible with various types of sensor input ports; Comprehensively and weigh the importance and weight of different indicator types to build a unified feedback evaluation standard; Independently detect and isolate sources of signal interference on a single router; Regularly calibrate the reading accuracy of all measuring tools; Equipped with disaster recovery switching backup circuit.
[0054] The feedback signal adjustment module sets a unified sensor information transmission interface to enable sensors of different types and models to be compatible and work together. The module conducts a comprehensive analysis of the importance and volatility of different environmental indicators, assigns appropriate weights, and builds a unified feedback evaluation standard based on these weights. The module also has a signal interference detection function that can independently detect and isolate signal interference sources on a single router to ensure the stability and accuracy of signal transmission. In order to ensure the reliability of measurement data, the module regularly calibrates all measurement tools to ensure the accuracy of readings. In addition, the module is equipped with a disaster recovery switching backup circuit. When the core components of the system fail or operate under harsh conditions, it can automatically switch to the backup circuit to ensure the continuous operation of the system.
[0055] This implementation method achieves seamless integration and collaboration between different sensors through a unified sensor interface design, thereby improving the compatibility and adaptability of the system. The construction of the feedback evaluation standard takes into account the importance and volatility of different environmental indicators, thereby improving the accuracy and reliability of the feedback signal. The signal interference detection and isolation function enhances the system's anti-interference ability and ensures the stability of data transmission. The function of regularly calibrating the measurement tools ensures the accuracy of the system's measurement data, thereby improving the accuracy and effect of environmental control. The disaster recovery switching function provides high availability of the system at critical moments and ensures the stability and continuous operation of the system.
[0056] In other embodiments, the sensor interface can support more sensor types or use more advanced interface protocols to improve the scalability of the system. The construction of feedback evaluation standards can introduce artificial intelligence algorithms to adjust the weights of different environmental indicators in real time to adapt to more complex environmental changes. Signal interference detection can be combined with more network security technologies, such as firewalls or encryption technologies, to improve the security and anti-attack capabilities of the system. The calibration of measuring tools can be performed by automated robots to improve calibration efficiency and accuracy. The disaster recovery switching backup circuit can be designed as a multi-layer redundant structure to ensure that the system can still operate stably under extreme conditions.
[0057] The feedback signal adjustment module uses multi-sensor technology to integrate the feedback signal, and the real-time adjustment execution mechanism further includes: Set a unified sensor information transmission interface using the formula: Ij=f(Sj,Pj), Where Ij represents the information transmission interface of the jth sensor, Sj represents the model of the jth sensor, Pj represents the data format of the jth sensor, and f is the interface adaptation function; Taking into account the sensitivity and volatility of various environmental indicators, appropriate weights are assigned to different indicators. Based on these weights, a unified feedback evaluation standard is constructed. The formula used to construct the unified feedback evaluation standard is: , Among them, Feval is the unified feedback evaluation standard, m is the total number of environmental indicators, wk is the weight of the kth indicator, Xk is the current actual value of the kth indicator, Xset,k is the target setting value of the kth indicator, and σk is the volatility or standard deviation of the kth indicator; Independently detect and isolate the signal interference source on a single router. The signal interference detection judgment formula is as follows: , Where Dint(t) is the signal interference state at time t, 1 indicates interference is detected, 0 indicates no interference, R(t) is the signal transmission rate at time t, and δR is the threshold of signal interference; Regularly calibrate the reading accuracy of all measuring tools. The calibration formula for regular calibration is: Ck=Xk+Δk, Where Ck is the reading of the kth sensor after calibration, Xk is the actual measurement value before calibration, and Δk is the calibration deviation; Equipped with a disaster recovery switchover backup circuit, it will automatically switch to the backup circuit when a core component fails or the environment is bad. The judgment and triggering conditions for disaster recovery switching are as follows: , Wherein, Ssw(t) is the disaster recovery switching state at time t, 1 indicates triggering the backup circuit, 0 indicates normal operation, Fcrit(t) is the critical fault parameter at time t, and τ is the threshold of disaster recovery switching.
[0058] The feedback signal adjustment module in this embodiment is mainly based on multi-sensor technology. By receiving and processing environmental data from different types of sensors, the execution mechanism is adjusted in real time. The core of multi-sensor technology is to integrate multiple environmental parameters and use advanced algorithms to comprehensively evaluate and provide real-time feedback on sensor data to ensure that the environmental conditions in the greenhouse accurately match the growth needs of crops. The system sets a unified information transmission interface to ensure that sensors of different models can be seamlessly integrated. The interface is designed to be highly compatible and scalable, and can adapt to different types of sensor inputs. At the same time, the system dynamically adjusts the environmental parameters in the greenhouse and optimizes the growth conditions of crops by constructing a unified feedback evaluation standard and combining the importance and volatility of each environmental indicator.
[0059] Among them, the information transmission interface ensures that sensor data of different models and formats can be uniformly received and processed, providing the system with an accurate environmental data basis; the feedback evaluation standard integrates the importance and volatility of various environmental parameters to build a unified evaluation standard to ensure that the feedback environmental information accurately reflects the actual situation; the signal interference detection module monitors the signal transmission rate, detects and isolates signal interference in real time, and ensures the accuracy and timeliness of the sensor data; when the disaster recovery switching circuit detects a core component failure or a harsh environment, it automatically switches to the backup circuit to ensure stable operation of the system.
[0060] The system first receives data from various sensors through the information transmission interface. These data are comprehensively analyzed through unified feedback evaluation standards. When the system detects deviations between environmental parameters and preset values, the feedback signal adjustment module will immediately issue adjustment instructions and adjust the execution mechanism. In addition, the signal interference detection module will continuously monitor the transmission rate of sensor signals to ensure accurate data transmission. If interference or failure occurs, the disaster recovery switching circuit will respond in the first time to ensure the continuous and stable operation of the system. The modules are interconnected through the data bus, and the information transmission interface receives and integrates data from different sensors. The feedback evaluation standard is responsible for evaluating the comprehensive impact of environmental data, and the signal interference detection module is responsible for monitoring the stability of data transmission. The disaster recovery switching circuit automatically switches to the backup circuit when a failure is detected to ensure the continuity and reliability of the system.
[0061] This implementation method can more accurately control the environmental parameters in the greenhouse through multi-sensing technology and feedback evaluation standards, thereby improving the adaptability of crops to the growth environment and increasing crop yield and quality. The system adopts an automated feedback and adjustment mechanism, which reduces the need for manual intervention, optimizes resource allocation and energy utilization in the greenhouse, and significantly improves the operating efficiency of the control system. The unified information transmission interface design simplifies the sensor integration and maintenance process, and users can easily add or replace sensors, improving the system's operational convenience and maintainability. The design of the signal interference detection module and the disaster recovery switching circuit ensures that the system can respond quickly and resume normal operation when signal interference or equipment failure occurs, greatly improving the system's safety and stability. The system is highly scalable and can adapt to sensors of different models and types, and ensures the long-term stable operation of the system through the disaster recovery switching circuit, adapting to greenhouse environments of different sizes and types.
[0062] In this embodiment, the material of the information transmission interface can be selected from highly conductive metal or anti-interference optical fiber material according to actual needs to improve the stability of data transmission. The structure of the feedback signal adjustment module can be adjusted according to different greenhouse types. For example, in a large greenhouse, the module can adopt a distributed structure so that signal processing and feedback control can be performed in multiple areas at the same time. In the feedback signal adjustment process, the weight parameters of the signal processing algorithm can be adjusted to cope with sensor data deviations in different environments. This adjustment can be dynamically optimized based on the trend of historical data or real-time monitoring data. In the case of large fluctuations in environmental conditions in the greenhouse, the weight parameters in the feedback evaluation criteria can be adjusted to increase the proportion of key environmental indicators to ensure that the system can still operate stably in extreme environments. In the manufacturing process of the feedback signal adjustment module, modular design and production can be adopted to facilitate flexible deployment in different greenhouses and rapid customization and upgrading as needed. The connection between modules can adopt wireless communication technology to reduce wiring complexity and ensure the security of data transmission through signal encryption technology. In the case of harsh greenhouse environments or frequent changes, the feedback signal adjustment module can be installed in a hanging or embedded manner to ensure the stability of the equipment and the reliability of data transmission.
[0063] The system can also be applied to other scenarios that require precise environmental control, such as biological laboratories, precision manufacturing workshops, etc. By adjusting the feedback evaluation criteria and sensor types, it can adapt to different control needs. The feedback evaluation algorithm used in the system can be replaced with a more advanced machine learning algorithm, such as a deep neural network, to further improve the accuracy and response speed of environmental parameter control. In high humidity or high temperature environments, high temperature resistant and corrosion-resistant sensor materials can be selected, or heat dissipation or protection devices can be added to the feedback signal adjustment module to ensure the stable operation of the system under harsh conditions.
[0064] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.
Claims
1. A load heterogeneous control system for greenhouse planting, characterized in that: The system comprises: Environmental data acquisition module, used to detect the working status of load heterogeneous equipment based on real-time environmental data; The control parameter setting module connected to the environmental data acquisition module is used to automatically set differentiated control parameters according to the crop types in each region to accurately meet the needs of the corresponding growth stage; The optimization and control module connected to the environmental data acquisition module and the control parameter setting module is used to continuously optimize the control logic through deep learning analysis of historical data and implement dynamic matching; The feedback signal adjustment module connected to the environmental data acquisition module, the control parameter setting module and the optimization and regulation module is used to utilize multi-sensor technology to integrate the feedback signal and adjust the execution mechanism in real time.
2. A load heterogeneous control system for greenhouse planting according to claim 1, characterized in that: The environmental data acquisition module detects the working status of load heterogeneous equipment based on real-time environmental data, including: Based on the real-time temperature data, determine whether the temperature in the greenhouse is higher than the set temperature T upper limit; if it is higher, turn on the cooling device; Based on real-time monitoring of light intensity and adjusting the fill light time according to the light sensitivity index I; Adjust ventilation volume in real time based on CO2 concentration to ensure CO2 concentration is within an appropriate range; Determine whether the soil moisture is lower than the preset lower limit H, and if so, activate the watering device; The method of judging whether the temperature in the greenhouse is higher than the set upper limit T based on the real-time temperature data, and if higher, starting the cooling device also includes: According to the relationship between temperature change ΔT and time interval Δt, the heating rate is calculated as K1=ΔT / Δt; If K1>VT, (where VT is the speed threshold), it is considered that the current greenhouse environment is rising rapidly, and high-power ventilation and cooling devices are turned on first; If the temperature rise is less than the temperature difference warning value ΔTmin, the air conditioner is turned off to save power consumption but the window is kept slightly open; For the heating rate of the current environment, if K1 ≥ VTmin (where VTmin is the greenhouse cooling warning value), the judgment condition result is true and the corresponding operation is performed.
3. A load heterogeneous control system for greenhouse planting according to claim 2, characterized in that: For the heating rate of the current environment, if K1≥VTmin, the conditional judgment result is true, and the corresponding operation is performed, which specifically includes: Compare K1 with the greenhouse cooling warning value VTmin. If [K1 ≥ VTmin], it means that active cooling measures need to be taken and the air conditioning equipment should be started for forced cooling. Otherwise, cooling can only be carried out through natural ventilation. Use a timing strategy to ensure equipment operation efficiency. When temperature control conditions are met, check every 15 minutes to see if equipment needs to be adjusted. Adjust the air conditioning power and fan rotation speed to ensure that the temperature control target of the greenhouse environment is achieved, that is, in every other cycle, that is, t=n×cycle, if K1≥VTmin, start the air conditioning to cool down, where n=[1,2,3,...]; Set conditions to prevent excessive energy consumption due to extreme weather in a short period of time. Do not change the air conditioning settings until the temperature difference ΔT reaches the temperature difference compensation threshold ΔTc; The setting conditions are as follows to prevent excessive energy consumption due to extreme weather in a short period of time and not to change the air conditioning settings before the temperature difference ΔT reaches the temperature difference compensation threshold ΔTc: Record the greenhouse temperature data Ts under the current air-conditioning operation state and the target set temperature Tr when the air-conditioning operation starts; Using the difference between the current ambient temperature Ts and the target set temperature Tr, the real-time temperature difference ΔT=Ts−Tr is calculated; Determine whether the real-time temperature difference reaches the preset temperature difference compensation threshold ΔTc, that is, determine (|ΔT|≤|ΔTc|). If the condition is not met, it means that there is no need to change the device settings. Otherwise, the device needs to be adjusted according to the current environmental conditions. The air conditioning working mode adjustment cycle C is set, and it is executed according to the above conditions. When the cycle C ends and |ΔT|>|ΔTc|) or the system determines that the external temperature has changed, the working state is adjusted to respond to the new demand.
4. A load heterogeneous control system for greenhouse planting according to claim 3, characterized in that: According to the judgment (|ΔT|≤|ΔTc|), if the condition is not met, it means that there is no need to change the device settings, otherwise the device needs to be adjusted according to the current environmental conditions, and further includes: Record the last adjustment time To and the current temperature Ts, and obtain the external reference temperature Te at this time; Environmental assessment, determining that when |Ts−Tr|>|ΔTc| and the time interval between the last adjustment at the current time t is greater than the minimum allowed adjustment period, the trigger condition is updated, indicating that the control strategy should be reset; Dynamically change the set temperature or equipment operation mode according to the update situation to maintain the internal environment stable, and set the update condition as |Ts−Tr|>|ΔTc|; Execute the above determination and make corresponding adjustments, record the latest status and send adjustment instructions to the control parameter setting module when necessary.
5. The load heterogeneous control system for greenhouse planting according to claim 1 is characterized by: The control parameter module automatically sets differentiated control parameters according to the crop types in each region to accurately meet the needs of the corresponding growth stage, including: Combine the classification data of crops in the planting area with geographic information technology to determine the location distribution information of each crop; The combined database searches for the range of suitable growing conditions required for each growth cycle of the crop; Automatically generate control parameter setting rule files according to the specific needs of the growth stage in each area; Implement differentiated irrigation and temperature regulation programs to simulate artificial climate environments that best suit the developmental needs of current plant species; Calibration checks are regularly performed for the specific needs of specific crops to ensure standards are met or strategies are updated to improve results.
6. A load heterogeneous control system for greenhouse planting according to claim 5, characterized in that: The control parameter module automatically sets differentiated control parameters according to the crop types in each region to accurately meet the needs of the corresponding growth stage. More details include: The classification data of different crops in the greenhouse are combined with geographic information technology to determine the specific location distribution of each crop. The formula is: Li = GIS (Xi, Yi, Zi), Among them, Li represents the spatial position of the i-th crop, Xi, Yi, Zi are geographical coordinates; By searching the database, we can obtain the suitable environmental conditions required by each crop at each growth stage. The condition data is stored in the form of a multidimensional matrix, which represents the various parameter requirements of the crop. The formula is: Ci,j=Retrieve(Di,Gj), Among them, Ci,j is the environmental condition required by crop i at growth stage j, Di is the crop data, and Gj is the growth stage; According to the growth requirements of crops, the control parameter setting rule file is automatically generated, and the lighting time and intensity are set using the formula: , Among them, Iij is the light intensity required by the i-th crop at growth stage j, Imax,j is the optimal light intensity, Tij,Hij are temperature and humidity respectively, Topt,j,Hopt,j are the optimal temperature and humidity; The temperature control setting adopts the formula: , Where Tset,i is the target temperature of the i-th crop, and ΔTi is the temperature deviation adjusted according to the current environmental conditions; According to the generated control parameter rule file, the system implements differentiated irrigation and temperature regulation for crops in different areas. The irrigation water volume is calculated using the formula: , Among them, Wi is the irrigation amount of the i-th crop, Wbase,i is the basic irrigation amount, ki is the adjustment coefficient, and Si is the real-time reading of the soil moisture sensor; The system adjusts the temperature based on the deviation between the real-time temperature data and the preset temperature target. The temperature adjustment adopts the formula: , Among them, ΔTadj,i is the temperature deviation that needs to be adjusted, and Tcurrent is the current ambient temperature; For the specific needs of each crop, the system will perform regular calibration checks to ensure that the control parameters are consistent with the actual needs of the crop. The calibration process is completed through the feedback signal adjustment module. Multi-sensor technology is used to monitor and feedback environmental changes in the greenhouse in real time, using the formula: , Among them, Fi is the comprehensive feedback signal, and Si,k is the kth sensor data of the i-th crop.
7. The load heterogeneous control system for greenhouse planting according to claim 1 is characterized by: The optimization and control module continuously optimizes the control logic through deep learning analysis of historical data to achieve dynamic matching and self-adaptation, including: Collect long-term accumulated operating parameters and output data sets as historical databases; Establish an environmental control model and continue to use newly added historical data to train and adjust the prediction accuracy; In-depth analysis of past environmental change trends and their inherent regularity in affecting production; Add an automated fault recovery function to ensure that the system can be quickly restarted and run automatically in the event of a sudden accident causing a system crash; Online monitoring of the deviation between actual performance and theoretical optimal configuration enables timely dynamic parameter adjustment to optimize control performance and reduce energy loss levels.
8. A load heterogeneous control system for greenhouse planting according to claim 7, characterized in that: The optimization and control module continuously optimizes the control logic through deep learning analysis of historical data to achieve dynamic matching and self-adaptation, further including: Collect the long-term accumulated operating parameters and output data of the greenhouse as the basis for subsequent modeling and optimization, using the formula: Dhist={(Ti,Hi,Ii,Ci,Wi,Yi)|i=1,2,…,n}, Among them, Dhist represents the data set of the historical database, Ti, Hi, Ii, Ci, Wi represent the temperature, humidity, light intensity, carbon dioxide concentration and irrigation amount collected for the i-th time, and Yi represents the corresponding crop yield or quality; The environmental control model is established using the historical database Dhist. The control model is in the form of: Y=f(T,H,I,C,W)+ϵ, Among them, Y is the expected yield or quality of the crop, f is the control model, ϵ is the model error, T, H, I, C, and W represent the collected temperature, humidity, light intensity, carbon dioxide concentration, and irrigation amount, respectively; During the model training process, the system continuously uses the newly added historical data to retrain the model and update the weights and parameters. The loss function in the training process uses the mean square error (MSE) to measure the deviation between the predicted value and the actual value. The specific formula is: , Where MSE is the mean square error, Yi is the actual value of the i-th sample, represents the predicted value of the i-th sample, and n represents the total number of samples; Through in-depth analysis of historical data, the system identifies the long-term impact of changes in environmental parameters on crop yield and quality, extracts the inherent regularity, and uses the formula: X(t)=ϕ1X(t−1)+ϕ2X(t−2)+⋯+θ0+ϵt, Among them, X(t) represents the environmental parameters at time t, ϕ and θ are the coefficients of the model respectively.
9. Based on the trend analysis results, the system predicts future environmental changes and adjusts control parameters in advance to optimize the climate conditions in the greenhouse; Monitor the working status of each module online. When an abnormality or fault is detected, the fault recovery mechanism is automatically triggered. The fault detection formula is: , Fault(t) represents the fault state at time t, X(t) represents the actual measured value of the system at time t, Xset is the desired control parameter, δ is the allowable deviation range, and when a fault occurs, it automatically switches to the backup mode, quickly restores key control functions, and restarts in the background to diagnose the cause of the fault; Real-time monitoring of the deviation between the environmental parameters in the greenhouse and the theoretical optimal configuration. By comparing the difference between the actual monitoring data Xactual and the optimal setting value Xopt, the control parameters are dynamically adjusted. The dynamic adjustment of the control parameters uses the formula: ΔX=Kp·(Xopt-Xactual)+Ki·∑(Xopt-Xactual)+Kd·(d(Xopt-Xactual) / dt), in, ΔX is the control parameter that needs to be adjusted, Xopt is the theoretical optimal setting value, Xactual is the actual monitored environmental parameter value, Kp is the proportional control coefficient, Ki is the integral control coefficient, and Kd is the differential control coefficient.
10. The load heterogeneous control system for greenhouse planting according to claim 1, characterized in that: The feedback signal adjustment module uses multi-sensor technology to integrate feedback signals, and the real-time adjustment execution mechanism includes: Set up information transmission interfaces between various types of sensing instruments to be compatible with various types of sensor input ports; Comprehensively and weigh the importance and weight of different indicator types to build a unified feedback evaluation standard; Independently detect and isolate sources of signal interference on a single router; Regularly calibrate the reading accuracy of all measuring tools; Equipped with disaster recovery switching backup circuit.
11. A load heterogeneous control system for greenhouse planting according to claim 9, characterized in that: The feedback signal adjustment module uses multi-sensor technology to integrate the feedback signal, and the real-time adjustment execution mechanism further includes: Set a unified sensor information transmission interface using the formula: Ij=f(Sj,Pj), Where Ij represents the information transmission interface of the jth sensor, Sj represents the model of the jth sensor, Pj represents the data format of the jth sensor, and f is the interface adaptation function; Taking into account the sensitivity and volatility of various environmental indicators, appropriate weights are assigned to different indicators. Based on these weights, a unified feedback evaluation standard is constructed. The formula used to construct the unified feedback evaluation standard is: , Among them, Feval is the unified feedback evaluation standard, m is the total number of environmental indicators, wk is the weight of the kth indicator, Xk is the current actual value of the kth indicator, Xset,k is the target setting value of the kth indicator, and σk is the volatility or standard deviation of the kth indicator; Independently detect and isolate the signal interference source on a single router. The signal interference detection judgment formula is as follows: , Where Dint(t) is the signal interference state at time t, 1 indicates interference is detected, 0 indicates no interference, R(t) is the signal transmission rate at time t, and δR is the threshold of signal interference; Regularly calibrate the reading accuracy of all measuring tools. The calibration formula for regular calibration is: Ck=Xk+Δk, Where Ck is the reading of the kth sensor after calibration, Xk is the actual measurement value before calibration, and Δk is the calibration deviation; Equipped with a disaster recovery switchover backup circuit, it will automatically switch to the backup circuit when a core component fails or the environment is bad. The judgment and triggering conditions for disaster recovery switching are as follows: , Wherein, Ssw(t) is the disaster recovery switching state at time t, 1 indicates triggering the backup circuit, 0 indicates normal operation, Fcrit(t) is the critical fault parameter at time t, and τ is the threshold of disaster recovery switching.
Citation Information
Patent Citations
Greenhouse automatic control method and system based on big data
CN108334139A
Greenhouse crop planting environment Internet of things intelligent regulation and control system and method
CN108874004A
Multi-path data fusion method and greenhouse monitoring system using multi-path data fusion method
CN112488193A
Temperature and humidity control method and system applied to planting greenhouse
CN117742423A
Automatic temperature control device and method for greenhouse
CN117859558A
Cited By
Photovoltaic greenhouse regulation and control system based on rule engine
CN119292377A
Method for screening japonica rice amphiphilic hybridization target gene plants based on high-throughput sequencing
CN119433091A
Method for screening plants of interest gene of japonica rice double parent cross based on high-throughput sequencing
CN119433091B
Greenhouse internal environment monitoring system based on Internet of Things
CN119647870A
Distributed digital agricultural park environment sensing system
CN119741142A
