Multi-source energy fusion agricultural greenhouse intelligent heat supply and regulation and control system

Abstract

The invention relates to the technical field of intelligent heat supply, in particular to a multi-source energy fusion agricultural greenhouse intelligent heat supply and regulation and control system, which comprises a multi-source energy acquisition module for acquiring energy output parameters of a solar heat collector, a geothermal well and a biomass boiler in real time and monitoring external meteorological data of a greenhouse; the energy dynamic matching module is used for generating an energy scheduling strategy through a dynamic priority algorithm and outputting a target energy type and supplied energy; the energy storage buffer module is used for storing or releasing the supplied energy and outputting the temperature and the residual capacity of an energy storage medium; the multi-parameter coupling regulation and control module is used for generating a regulation and control instruction through an environment parameter coupling model; the actuating mechanism driving module is used for converting the regulation and control instruction into control signals of a heater, a fan and a humidifier; the self-learning optimization module is used for dynamically correcting the dynamic priority algorithm and the environment parameter coupling model; according to the invention, through multi-parameter cooperative regulation and dynamic optimization, crops are ensured to be in the optimal environmental conditions in different growth stages.

Description

Technical Field

[0001] The present invention relates to the field of intelligent heating technology, and in particular to an intelligent heating and control system for agricultural greenhouses integrating multiple energy sources. Background Art

[0002] Agricultural greenhouse heating and control systems are an important part of modern agriculture. Their core goal is to provide a suitable growth environment for crops. Traditional greenhouse heating systems mostly rely on a single energy source (such as coal or electric heating), and have problems such as high energy consumption, large carbon emissions, and poor control flexibility. In recent years, multi-source energy heating technology has gradually been applied, but it still faces technical difficulties such as low energy synergy efficiency, mismatch between energy storage and energy consumption timing, separation of multi-parameter control, and low accuracy of cold and hot load prediction. Although existing technologies have proposed improvement solutions such as multi-source energy scheduling algorithms, phase change energy storage technology, and environmental parameter coupling models, there are still shortcomings such as rigid energy scheduling strategies, insufficient energy storage control accuracy, and poor adaptability of control models, which make it difficult to meet the needs of efficient and precise control of modern agricultural greenhouses.

[0003] In response to the above problems, the present invention proposes an intelligent heating and control system for agricultural greenhouses that integrates multiple energy sources. Through a modular progressive design, it realizes dynamic scheduling of multiple energy sources, precise control of phase change energy storage, and coordinated optimization of environmental parameters. The system combines crop growth models with self-learning optimization algorithms to dynamically adjust energy priorities and control strategies, thereby improving greenhouse energy utilization efficiency and environmental control accuracy, providing a highly efficient and intelligent solution for modern agricultural greenhouses. Summary of the Invention

[0004] Based on the above objectives, the present invention provides an intelligent heating and control system for agricultural greenhouses that integrates multiple energy sources.

[0005] An intelligent heating and control system for agricultural greenhouses that integrates multiple energy sources, including the following modules: Multi-source energy collection module: collects energy output parameters of solar collectors, geothermal wells and biomass boilers in real time, and monitors external greenhouse meteorological data; Energy dynamic matching module: Based on the energy output parameters and greenhouse external meteorological data, it generates an energy scheduling strategy through a dynamic priority algorithm and outputs the target energy type and supply amount; Energy storage buffer module: receives energy scheduling strategies, uses phase change energy storage materials to store or release energy, and outputs the temperature and remaining capacity of the energy storage medium; Multi-parameter coupling control module: Based on the energy storage medium temperature and greenhouse internal sensor data, it generates control instructions through the environmental parameter coupling model; Actuator drive module: converts the control instructions into control signals for the heater, fan, and humidifier, which are used to adjust the greenhouse temperature, ventilation, and humidity respectively; Self-learning optimization module: dynamically corrects the dynamic priority algorithm and environmental parameter coupling model based on greenhouse crop growth feedback data.

[0006] Furthermore, the multi-source energy collection module includes: Solar collector parameter collection: PV array temperature sensors and irradiance meters are used to obtain the collector surface temperature and light intensity in real time, and instantaneous output power is calculated based on the photothermal conversion efficiency formula. Geothermal well parameter collection: Use wellhead flowmeters and temperature difference sensors to monitor geothermal fluid flow and inlet and outlet temperature differences in real time, and calculate geothermal output power; Biomass boiler parameter collection: Use fuel mass flow meter and flue gas analyzer to detect biomass fuel consumption rate and low calorific value in real time and calculate boiler output power; Meteorological data fusion algorithm: The light intensity, wind speed and ambient temperature collected by the greenhouse external meteorological station are input into the meteorological influencing factor model, and the comprehensive meteorological correction coefficient is output.

[0007] Furthermore, the energy dynamic matching module includes: Priority index calculation: Calculate the dynamic priority index of solar energy, geothermal energy and biomass energy based on energy output parameters and meteorological data; Heat load demand matching: Combined with greenhouse heat load forecast and meteorological correction coefficient, the weight distribution of priority indicators is dynamically adjusted; Energy dispatch sequence generation: Sort by priority indicators from high to low, generate an energy call sequence, and allocate the energy supply of each energy source step by step based on the remaining energy supply demand.

[0008] Furthermore, in the heat load demand matching, a heat load prediction model is constructed to output the heat load prediction value of the greenhouse in the next hour, including: Basic heat load calculation: Calculate the basic heat load based on the thermal inertia parameters of the greenhouse enclosure structure and the real-time internal temperature; Meteorological influence correction: Dynamically correct the basic heat load based on the meteorological correction coefficient; Predict the heat load in the next hour: Use the time series prediction model to make a rolling prediction of the heat load in the next hour; Calibration of prediction results: Compare the predicted value with the real-time monitoring value.

[0009] Furthermore, the energy storage buffer module includes: Energy storage / release mode determination: Determine the operation mode based on the supply-demand gap and remaining capacity; Dynamic control of phase change energy storage: In heat storage mode, the heat storage rate is calculated based on the input power and heat storage efficiency; in heat release mode, the heat release power is calculated based on the real-time temperature of the phase change material and the heat release rate coefficient; Dynamic update of remaining capacity: Updates the remaining capacity according to the operation mode.

[0010] Furthermore, the dynamic regulation of phase change energy storage includes: Energy calculation in the heat storage stage: The heat storage rate is determined by the excess energy and the heat storage efficiency of the phase change material; Energy calculation in the heat release stage: The heat release power is determined by the difference between supply and demand and the remaining capacity.

[0011] Furthermore, the multi-parameter coupling control module includes: Dynamic coupling of environmental parameters: Build a multi-objective optimization model based on the crop growth stage, inputting the energy storage medium temperature, real-time temperature inside the greenhouse, relative humidity, and CO2 concentration; Control instruction generation algorithm: Generates control instructions, including heater duty cycle, fan speed and humidifier atomization particle size; Command constraint and output: The heating command, fan speed command and humidification command calculated by the control module are subjected to physical constraint processing and then output to the actuator drive module.

[0012] Furthermore, the construction of the multi-objective optimization model includes: Definition of multi-objective optimization model: Construct a multi-objective optimization function with the goal of minimizing greenhouse environmental parameter deviations; Parameter normalization processing: standardize each control parameter; Dynamic weight adjustment algorithm: A dynamic weight correction mechanism is introduced to adjust the weight of each target item in real time according to its deviation contribution; Model constraints: Determine the optimal solution under the premise of satisfying the constraints.

[0013] Furthermore, the actuator driving module includes: Heater control signal generation: converting the generated heater duty cycle into a pulse width modulation signal for heater driving; Fan control signal generation: convert the generated fan target speed into actual drive voltage; Humidifier control signal generation: converting the generated atomization particle size into the driving frequency of the ultrasonic humidifier; Signal constraint and output: The control signal is subjected to physical limit constraints and then output to the respective drive modules.

[0014] Furthermore, the self-learning optimization module includes: Feedback data collection and preprocessing: Collect crop growth feedback data, including crop growth rate, energy consumption cost and environmental parameter deviation integral; Dynamic priority algorithm modification: Use deep reinforcement learning algorithm to update weight coefficients.

[0015] Beneficial effects of the present invention: The present invention provides an intelligent heating and control system for agricultural greenhouses that integrates multiple energy sources. It realizes on-demand scheduling of multiple energy sources (solar energy, geothermal energy, and biomass energy) through a dynamic priority algorithm, and combines phase change energy storage technology to solve the supply and demand lag problem, significantly improving the utilization rate of intermittent energy and improving the overall energy utilization efficiency. At the same time, it gives priority to calling on clean energy such as solar energy and geothermal energy to reduce biomass fuel consumption, and reduces the overall carbon emissions of the system, which is in line with the development trend of green agriculture. In addition, based on the environmental parameter coupling model, it realizes the coordinated control of temperature, humidity, and CO2 concentration, avoiding the temperature and humidity conflict problem caused by traditional independent control, improving the control accuracy, and providing a more stable and suitable environment for crop growth.

[0016] The present invention dynamically corrects the energy scheduling strategy and the environmental parameter coupling model through a self-learning optimization module, and realizes adaptive optimization of the control strategy in combination with crop growth feedback data, further improving the intelligence level and adaptability of the system; through multi-parameter coordinated control and dynamic optimization, it ensures that crops are in the optimal environmental conditions at different growth stages, and the growth rate is improved, which has good promotion value. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 Schematic diagram of a module according to an embodiment of the present invention; Figure 2 This is an energy collection diagram of an embodiment of the present invention. DETAILED DESCRIPTION

[0019] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to specific embodiments.

[0020] It should be noted that, unless otherwise defined, the technical or scientific terms used in the present invention should have the usual meanings understood by people with ordinary skills in the field to which the present invention belongs. The "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0021] like Figure 1-Figure 2 As shown in the figure, a multi-source energy integrated agricultural greenhouse intelligent heating and control system includes the following modules: Multi-source energy collection module: collects energy output parameters of solar collectors, geothermal wells and biomass boilers in real time, and monitors external greenhouse meteorological data; Energy dynamic matching module: Based on energy output parameters and greenhouse external meteorological data, it generates energy scheduling strategies through dynamic priority algorithms and outputs target energy types and supply amounts; Energy storage buffer module: receives energy scheduling strategies, uses phase change energy storage materials to store or release energy, and outputs the temperature and remaining capacity of the energy storage medium; Multi-parameter coupling control module: Based on the energy storage medium temperature and greenhouse internal sensor data, it generates control instructions through the environmental parameter coupling model; Actuator drive module: converts control instructions into control signals for heaters, fans, and humidifiers, which are used to adjust greenhouse temperature, ventilation, and humidity respectively; Self-learning optimization module: Dynamically corrects the dynamic priority algorithm and environmental parameter coupling model based on greenhouse crop growth feedback data.

[0022] The multi-source energy harvesting module includes: Solar collector parameter collection: Real-time acquisition of collector surface temperature through photovoltaic array temperature sensors and irradiance meters and light intensity , and calculate the instantaneous output power based on the photothermal conversion efficiency formula , expressed as: ; in, is the calibrated conversion efficiency of the solar collector , is the effective lighting area of the collector , is the temperature attenuation coefficient , Is the standard test temperature ; Geothermal well parameter collection: Real-time monitoring of geothermal fluid flow through wellhead flowmeters and temperature difference sensors and inlet and outlet temperature difference , calculate the geothermal output power , expressed as: ; in, is the specific heat capacity of water , is the density of water ; Biomass boiler parameter collection: real-time detection of biomass fuel consumption rate through fuel mass flow meter and flue gas analyzer and low calorific value , calculate the boiler output power , expressed as: ; in, Boiler combustion efficiency ; Meteorological data fusion algorithm: The light intensity collected by the greenhouse external weather station , wind speed and ambient temperature Input meteorological impact factor model and output comprehensive meteorological correction coefficient , expressed as: ; in, is the weight coefficient ( ), determined by fitting the correlation between historical meteorological data and heating demand, It is the highest sunlight intensity and wind speed in local history. is the greenhouse set temperature, Is the allowable fluctuation range of temperature control .

[0023] The energy dynamic matching module includes: Priority index calculation: Based on energy output parameters and meteorological data, the dynamic priority index of solar energy, geothermal energy, and biomass energy is calculated and expressed as: ; in, It is Dynamic priority indicators of energy types are used to quantify the scheduling priorities of different energy sources at the current moment. It is Real-time output power of energy sources, Energy Corresponding to solar energy, geothermal energy and biomass energy respectively, For the The maximum historical output power of the energy source, is the output stability coefficient, , For the The carbon emission intensity of the energy type is preset to be 0 for solar energy, 0.05 for geothermal energy, and 0.15 for biomass energy. is the carbon emission baseline value ( ), is the weight coefficient , the initial value is set to , is the meteorological correction factor; Heat load demand matching: Combined with the greenhouse heat load forecast value and meteorological correction coefficient, dynamically adjust the weight distribution of priority indicators, according to the greenhouse heat load forecast value in the next hour and the current total energy supply The difference , the weight dynamic adjustment rule is expressed as: when (Insufficient energy supply), increase Weight to 0.5, reduce to 0.1; when (Excess energy supply), increase Weight to 0.3, reduce to 0.3; in, is the heat load tolerance threshold (take the greenhouse rated load ); Energy dispatch sequence generation: Sort by priority index from high to low, generate energy call sequence, and allocate energy supply of each energy source step by step based on the remaining energy supply demand, expressed as: ; in, is the scheduling period (10 minutes), is the predicted value of heat load, For the Energy supply of type energy, For the The amount of energy that has been allocated by this type of energy in this scheduling cycle .

[0024] During heat load demand matching, a heat load prediction model is constructed to output the heat load forecast value of the greenhouse in the next hour, including: Basic heat load calculation: Calculate the basic heat load based on the thermal inertia parameters of the greenhouse enclosure and the real-time internal temperature , expressed as: ; in, is the thermal inertia coefficient of the greenhouse enclosure structure , calculated by the thermal conductivity and surface area of building materials, is the greenhouse set temperature , preset according to crop growth stage, Is the real-time temperature inside the greenhouse , is the crop transpiration heat load , , is the crop transpiration coefficient , the value range is 0.01~0.1, and it is calibrated according to the crop type and growth stage experiment. is the crop planting area, To set the relative humidity, The real-time relative humidity inside the greenhouse; Weather correction: Based on weather correction factor , dynamically correct the basic heat load, expressed as: ; in, is the corrected base heat load, is the meteorological impact weight factor , according to the correlation fitting between historical meteorological data and heat load; Predicting the heat load for the next hour: A time series forecasting model (ARIMA) is used to make a rolling forecast of the heat load for the next hour, expressed as: ; in, is the predicted heat load value for the next hour, is the autoregressive coefficient, obtained through training of historical heat load data, is the forecast error term; Forecast result calibration: the predicted value With real-time monitoring value Compare, if the relative error Exceed , triggering the model update of the self-learning optimization module, expressed as: .

[0025] The energy storage buffer module includes: Energy storage / release mode judgment: based on the difference between supply and demand and remaining capacity , determine the operation mode, including: Heat storage mode : Excess energy is stored in phase change materials; Heat release mode : Release stored energy; Standby mode : Maintain the current state; Dynamic regulation of phase-change energy storage: In heat storage mode, the heat storage rate is calculated based on the input power and heat storage efficiency to ensure that energy storage does not exceed the maximum capacity of the system and is limited by the thermophysical parameters of the phase-change material. In heat release mode, the heat release power is calculated based on the real-time temperature of the phase-change material and the heat release rate coefficient, while ensuring that the heat release temperature does not fall below the set threshold. Ultimately, the charging and discharging process of the energy storage system is dynamically adjusted. Dynamic update of remaining capacity: Update remaining capacity according to operation mode , expressed as: ; in, The remaining energy for the next moment, is the remaining energy storage capacity at the current moment, is the heat storage power in heat storage mode, is the heat release power in heat release mode, is the scheduling period, is the total capacity of the phase change energy storage unit.

[0026] Dynamic regulation of phase change energy storage includes: Energy calculation in the heat storage stage: heat storage rate From excess energy Phase change material heat storage efficiency Decision, expressed as: ; in, is the heat storage power in heat storage mode, is the maximum energy storage capacity, is the remaining energy storage capacity at the current moment, is the total capacity of the phase change energy storage unit, is the scheduling period; Energy calculation in the heat release stage: heat release power By the difference between supply and demand and the remaining capacity, expressed as: ; in, is the heating power in heating mode.

[0027] The multi-parameter coupling control module includes: Dynamic coupling of environmental parameters: Build a multi-objective optimization model based on the crop growth stage, inputting the energy storage medium temperature, real-time temperature inside the greenhouse, relative humidity, and CO2 concentration; Control instruction generation algorithm: Generates control instructions, which include heater duty cycle, fan speed and humidifier atomization particle size, expressed as: (1) Heater duty cycle : ; in, is the current indoor temperature, is the target set temperature, is the current temperature of the energy storage medium, is the lower limit of the effective heat release temperature of the energy storage medium, the default value is , is the current indoor relative humidity, is the target humidity setting, is the control weight coefficient, satisfying , dynamically adjusted according to the crop growth stage; (2) Fan speed : ; in, is the fan speed command value, is the current indoor carbon dioxide concentration, Set goals Concentration, range , is the adjustment factor of temperature error on fan speed, the recommended value is 0.05, for The deviation is the adjustment factor for the fan speed, and the recommended value is 0.1; (3) Humidifier atomization particle size : ; in, is the humidifier atomization particle size instruction value, The humidity fluctuation range is defined as the allowable deviation of the set humidity. The default value is , is the particle size adjustment coefficient, and its value range is , calibrated according to actual measurement of humidifier performance; Instruction constraints and output: The heating instructions calculated by the control module , fan speed command and humidification instructions After physical constraint processing, it is output to the actuator drive module. The constraint rules are expressed as: ; in, It's time The heating instruction value, It's time The fan speed command value, It's time Humidification amount command value, is the maximum speed allowed by the fan, It is the minimum effective working flow of the humidifier. When it is lower than this value, the equipment will not start or the efficiency will drop significantly. It is the maximum safe operating flow rate of the humidifier. Exceeding this value may cause overload or safety hazards.

[0028] The construction of the multi-objective optimization model includes: Definition of multi-objective optimization model: Construct a multi-objective optimization function with the goal of minimizing the deviation of greenhouse environmental parameters, which is expressed as: ; in, is the current indoor temperature, is the current indoor relative humidity, For the current indoor concentration, is the current temperature of the energy storage medium, Set target values for environmental parameters, The optimal heat release temperature of phase change material , is the environmental control weight coefficient, satisfying , dynamically set according to the crop growth stage: Seedling stage: ; Flowering period: ; is the allowable fluctuation range of the corresponding parameter, for , for , for , for ; Parameter normalization: To eliminate the influence of dimension, each control parameter is normalized and expressed as: ; in, is the normalized value of the real-time temperature inside the greenhouse, is the normalized value of the real-time relative humidity inside the greenhouse, is the normalized value of the real-time CO2 concentration inside the greenhouse, is the normalized value of the energy storage medium temperature; Dynamic weight adjustment algorithm: A dynamic weight correction mechanism is introduced. The weight of each target item is corrected in real time according to its deviation contribution, which is expressed as: ; ; in, is the updated weight coefficient, is the initial weight setting, is the sensitivity adjustment coefficient, and its value range is , based on historical data and control strategy calibration, It is The normalized deviation value of the environmental parameters, , is the normalized environmental parameter value, and the corresponding order is expressed as: ; ; ; ; Model constraints: Determine the optimal solution under the premise of satisfying the constraints. The constraints are expressed as: .

[0029] The actuator drive module includes: Heater control signal generation: Generates the heater duty cycle Converted into a pulse width modulation (PWM) signal for heater driving, with a duty cycle of Expressed as: ; in, is the heater control duty cycle (range ), yes Actual duty cycle of the signal (range 0~95%), is the heater power response coefficient, with a range of , calibrated experimentally based on the dynamic power response characteristics of the heater, is the duty cycle offset, the value range is , used to compensate for the heater's startup threshold; Fan control signal generation: Generate the fan target speed Convert to actual driving voltage , expressed as: ; in, is the target fan speed, is the fan drive voltage, Is the speed-voltage proportional coefficient, the value range is , needs to be calibrated according to the fan model and voltage characteristics, is the speed change rate damping coefficient, the value range is , used to suppress voltage mutations and protect the fan circuit; Humidifier control signal generation: the generated atomization particle size Converted to the driving frequency of the ultrasonic humidifier , the conversion relationship is as follows: ; in, is the humidifier atomization particle size, is the ultrasonic driving frequency, is the frequency-size conversion coefficient, and its value range is , obtained based on experimental calibration of the atomizer; Signal constraints and output: To avoid system overload and actuator over-limit, the control signal is subjected to physical limit constraints and then output to the respective drive modules. The constraint rules are expressed as follows: ; in, is the minimum operating voltage of the fan, is the maximum safe operating voltage of the fan, is the minimum driving frequency of the humidifier, It is the maximum safe driving frequency of the humidifier.

[0030] The self-learning optimization module includes: Feedback data collection and preprocessing: Collect crop growth feedback data, including crop growth rate (Real-time monitoring via stem diameter sensor or leaf area index meter), energy consumption cost (the sum of the actual energy supply of biomass energy, geothermal energy and solar energy and the unit energy cost) and the integral of the environmental parameter deviation (Normalized deviation time integral of ); Dynamic priority algorithm modification: using deep reinforcement learning algorithm to update weight coefficients , whose reward function Expressed as: ; in, To optimize weight , the initial value is set to , is the base growth rate of the crop, preset according to the variety, The energy cost benchmark.

[0031] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present invention is limited to these examples. Within the scope of the present invention, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the present invention as described above, which are not provided in detail for the sake of simplicity.

Claims

1. An intelligent heating and control system for agricultural greenhouses integrating multiple energy sources, characterized in that: Includes the following modules: Multi-source energy collection module: collects energy output parameters of solar collectors, geothermal wells and biomass boilers in real time, and monitors external greenhouse meteorological data; Energy dynamic matching module: Based on the energy output parameters and greenhouse external meteorological data, it generates an energy scheduling strategy through a dynamic priority algorithm and outputs the target energy type and supply amount; Energy storage buffer module: receives energy scheduling strategies, uses phase change energy storage materials to store or release energy, and outputs the temperature and remaining capacity of the energy storage medium; Multi-parameter coupling control module: Based on the energy storage medium temperature and greenhouse internal sensor data, it generates control instructions through the environmental parameter coupling model; Actuator drive module: converts the control instructions into control signals for the heater, fan, and humidifier, which are used to adjust the greenhouse temperature, ventilation, and humidity respectively; Self-learning optimization module: dynamically corrects the dynamic priority algorithm and environmental parameter coupling model based on greenhouse crop growth feedback data.

2. The multi-source energy fusion agricultural greenhouse intelligent heating and control system according to claim 1 is characterized in that: The multi-source energy collection module includes: Solar collector parameter collection: PV array temperature sensors and irradiance meters are used to obtain the collector surface temperature and light intensity in real time, and instantaneous output power is calculated based on the photothermal conversion efficiency formula. Geothermal well parameter collection: Use wellhead flowmeters and temperature difference sensors to monitor geothermal fluid flow and inlet and outlet temperature differences in real time, and calculate geothermal output power; Biomass boiler parameter collection: Use fuel mass flow meter and flue gas analyzer to detect biomass fuel consumption rate and low calorific value in real time and calculate boiler output power; Meteorological data fusion algorithm: The light intensity, wind speed and ambient temperature collected by the greenhouse external meteorological station are input into the meteorological influencing factor model, and the comprehensive meteorological correction coefficient is output.

3. The multi-source energy fusion agricultural greenhouse intelligent heating and control system according to claim 2 is characterized in that: The energy dynamic matching module includes: Priority index calculation: Calculate dynamic priority indexes for solar energy, geothermal energy, and biomass energy based on energy output parameters and meteorological data; Heat load demand matching: Combined with greenhouse heat load forecast and meteorological correction coefficient, the weight distribution of priority indicators is dynamically adjusted; Energy dispatch sequence generation: Sort by priority indicators from high to low, generate an energy call sequence, and allocate the energy supply of each energy source step by step based on the remaining energy supply demand.

4. The multi-source energy fusion agricultural greenhouse intelligent heating and control system according to claim 3 is characterized in that: In the heat load demand matching, a heat load prediction model is constructed to output the heat load prediction value of the greenhouse in the next hour, including: Basic heat load calculation: Calculate the basic heat load based on the thermal inertia parameters of the greenhouse enclosure structure and the real-time internal temperature; Meteorological influence correction: Dynamically correct the basic heat load based on the meteorological correction coefficient; Predict the heat load in the next hour: Use the time series prediction model to make a rolling prediction of the heat load in the next hour; Calibration of prediction results: Compare the predicted value with the real-time monitoring value.

5. The multi-source energy fusion agricultural greenhouse intelligent heating and control system according to claim 4 is characterized in that: The energy storage buffer module includes: Energy storage / release mode determination: Determine the operation mode based on the supply-demand gap and remaining capacity; Dynamic control of phase change energy storage: In heat storage mode, the heat storage rate is calculated based on the input power and heat storage efficiency; in heat release mode, the heat release power is calculated based on the real-time temperature of the phase change material and the heat release rate coefficient; Dynamic update of remaining capacity: Updates the remaining capacity according to the operation mode.

6. The multi-source energy fusion agricultural greenhouse intelligent heating and control system according to claim 5 is characterized in that: The phase change energy storage dynamic regulation includes: Energy calculation in the heat storage stage: The heat storage rate is determined by the excess energy and the heat storage efficiency of the phase change material; Energy calculation in the heat release stage: The heat release power is determined by the difference between supply and demand and the remaining capacity.

7. The multi-source energy fusion agricultural greenhouse intelligent heating and control system according to claim 6 is characterized in that: The multi-parameter coupling control module includes: Dynamic coupling of environmental parameters: Build a multi-objective optimization model based on the crop growth stage, inputting the energy storage medium temperature, real-time temperature inside the greenhouse, relative humidity, and CO2 concentration; Control instruction generation algorithm: Generates control instructions, including heater duty cycle, fan speed and humidifier atomization particle size; Command constraint and output: The heating command, fan speed command and humidification command calculated by the control module are subjected to physical constraint processing and then output to the actuator drive module.

8. The multi-source energy fusion agricultural greenhouse intelligent heating and control system according to claim 7 is characterized in that: The construction of the multi-objective optimization model includes: Definition of multi-objective optimization model: Construct a multi-objective optimization function with the goal of minimizing greenhouse environmental parameter deviations; Parameter normalization processing: standardize each control parameter; Dynamic weight adjustment algorithm: A dynamic weight correction mechanism is introduced to adjust the weight of each target item in real time according to its deviation contribution; Model constraints: Determine the optimal solution under the premise of satisfying the constraints.

9. The multi-source energy fusion agricultural greenhouse intelligent heating and control system according to claim 8 is characterized in that: The actuator drive module includes: Heater control signal generation: converting the generated heater duty cycle into a pulse width modulation signal for heater driving; Fan control signal generation: convert the generated fan target speed into actual drive voltage; Humidifier control signal generation: converting the generated atomization particle size into the driving frequency of the ultrasonic humidifier; Signal constraint and output: The control signal is subjected to physical limit constraints and then output to the respective drive modules.

10. The multi-source energy fusion agricultural greenhouse intelligent heating and control system according to claim 8 is characterized in that: The self-learning optimization module includes: Feedback data collection and preprocessing: Collect crop growth feedback data, including crop growth rate, energy consumption cost and environmental parameter deviation integral; Dynamic priority algorithm modification: Use deep reinforcement learning algorithm to update weight coefficients.

Images