Temperature control method and device for nursery stock greenhouse cultivation environment and storage medium

Abstract

The invention relates to the technical field of temperature control, in particular to a temperature control method and device for a nursery stock greenhouse cultivation environment and a storage medium. The method comprises the following steps that an in-greenhouse temperature influence model is established, the in-greenhouse temperature influence model can predict the in-greenhouse air temperature according to the in-greenhouse soil temperature, and optimization is carried out by considering the influence of the out-greenhouse air temperature on the in-greenhouse air temperature; acquiring a seedling target soil temperature range and a target air temperature range at the current seedling growth stage, starting an air temperature adjusting strategy when monitoring that the real-time in-greenhouse air temperature is not within the target in-greenhouse air temperature range, and judging whether the in-greenhouse soil temperature is within the target in-greenhouse soil temperature range or not; and if the soil temperature in the greenhouse is not within the range of the target soil temperature, adjusting the soil temperature. According to the method, the response speed and adaptability to environmental changes are greatly improved, and more stable and suitable growth conditions are provided for nursery stocks.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of temperature control, in particular to a temperature control method and device for a seedling greenhouse cultivation environment and a storage medium. BACKGROUND

[0002] In modern horticulture and agricultural cultivation, temperature control of the seedling greenhouse cultivation environment is one of the key factors to ensure the healthy growth of crops. The growth of seedlings not only depends on the appropriate air temperature, but also has strict requirements for the soil temperature where the roots are located. Different growth stages have different temperature requirements. For example, a higher soil temperature is required during the seed germination period to promote germination, while a more stable temperature condition is required during the seedling stage to support the healthy development of roots and photosynthesis. However, in actual operation, it is extremely challenging to maintain such an ideal temperature distribution. Due to the different heat conduction efficiencies between soil and air, combined with the changes in external climate conditions, it is difficult for a single overall temperature control strategy to meet the specific needs of different parts of the seedlings. In particular, under large greenhouses or continuous adverse weather conditions, the limitations of traditional temperature control systems are more obvious. These systems usually lack the ability to finely regulate the soil deep temperature and the crown microclimate, resulting in problems such as soil temperature reaching the ideal state during heating but the crown temperature being too high, causing energy waste, or soil temperature dropping too fast during ventilation and cooling, affecting the healthy development of roots. Therefore, it is necessary to provide a temperature control method and device for a seedling greenhouse cultivation environment and a storage medium. SUMMARY

[0003] The present application aims to provide a temperature control method and device for a seedling greenhouse cultivation environment and a storage medium to solve the problem that traditional temperature control systems often uniformly adjust the temperature of the entire greenhouse, resulting in overheating of the crown during soil heating, energy waste, and sudden drop of soil temperature during ventilation and cooling, affecting the growth of roots.

[0004] To achieve the above-mentioned purpose, the present application aims to provide a temperature control method for a seedling greenhouse cultivation environment, comprising the following steps: S1, respectively burying distributed sensors at different depths of the soil to collect the soil temperature in the greenhouse in real time, and deploying distributed sensors at the height of the plant canopy to measure the air temperature in the greenhouse; S2, establishing a greenhouse temperature influence model according to the real-time collected soil temperature in the greenhouse and the air temperature in the greenhouse, combining the historical soil temperature in the greenhouse and the air temperature in the greenhouse, the greenhouse temperature influence model can predict the air temperature in the greenhouse according to the soil temperature in the greenhouse, and the influence of the outside air temperature on the air temperature in the greenhouse is considered for optimization when establishing the greenhouse temperature influence model; S3, determine the target soil temperature range and the target air temperature range of the seedling based on the growth stage of the seedling, determine whether the real-time greenhouse air temperature is within the target greenhouse air temperature range by monitoring the real-time greenhouse air temperature, determine the air temperature error between the greenhouse air temperature and the target greenhouse air temperature, predict the air temperature adjustment completion time based on the air temperature adjustment strategy and the greenhouse temperature influence model ; S4, in the process of temperature adjustment, monitor the real-time greenhouse soil temperature, predict the greenhouse soil temperature after time based on the greenhouse temperature influence model, and determine whether the greenhouse soil temperature is within the target greenhouse soil temperature range; if the greenhouse soil temperature is not within the target greenhouse soil temperature range, adjust the soil temperature.

[0005] As a further improvement of the technical solution, the specific steps of establishing the greenhouse temperature influence model in S2 are as follows: S21, establish the dynamic relationship between soil temperature and greenhouse air temperature , and consider the nonlinear adjustment effect of soil humidity ; S22, calculate the cross-correlation function through historical data to determine the lag time , and introduce the lag term in the dynamic relationship between soil temperature and greenhouse air temperature ; S23, finally, add the outdoor temperature as a linear term to the dynamic relationship between soil temperature and greenhouse air temperature , and consider the noise term of light fluctuation and human disturbance, and finally generate the greenhouse temperature influence model.

[0006] As a further improvement of the technical solution, when establishing the greenhouse temperature influence model in S2, the specific steps of considering the influence of outdoor air temperature on indoor air temperature for optimization are as follows: S24, use an exponential function to quantify the nonlinear effect of ventilation intensity on indoor and outdoor heat exchange, and generate a heat leakage coefficient; S25, capture the temperature lag effect caused by the heat storage or release of the greenhouse by weighting the indoor and outdoor temperature difference in the past time period, and control the decay rate of historical influence through a decay factor ; S26, based on the direct effect of the current outdoor temperature and the cumulative effect of the historical temperature lag effect, combine the heat leakage coefficient to generate the outdoor temperature influence coefficient ; S27, according to the outdoor temperature influence coefficient , an optimized indoor temperature influence model is generated.

[0007] As a further improvement of the technical solution, in S3, the target soil temperature range and the target air temperature range are determined based on the growth stage of the seedling, specifically: real-time collection of seedling growth state data through sensors installed in the greenhouse, determination of the current growth stage of the seedling based on the collected seedling growth state data, construction of an experience module of growth stage and temperature demand based on historical seedling growth state data, the experience module records the target soil temperature and target air temperature range corresponding to each growth stage of the seedling, and finally the target soil temperature range and target air temperature range are determined by fine-tuning the range of the target soil temperature and target air temperature according to the current environment.

[0008] As a further improvement of the technical solution, in S3, the specific steps of the air temperature adjustment strategy are: S31, compare the real-time data of the indoor air temperature at the current time point with the target indoor air temperature range, and calculate the air temperature error S32, map the air temperature error to the preliminary control strength based on a nonlinear mapping function, and combine the output of the nonlinear mapping function with proportional, integral, and differential control effects using a PID controller to finally generate a control signal containing heating power and heating time .

[0009] As a further improvement of the technical solution, in S3, the specific steps of predicting the air temperature adjustment completion time based on the air temperature adjustment strategy and the indoor temperature influence model are as follows: S33, input the control variable containing heating power into the indoor temperature influence model to predict the indoor air temperature at the next time step; S34, determine whether the indoor air temperature at the next time step is within the target indoor air temperature range, if not, iteratively update the air temperature error and the control signal until the predicted indoor air temperature enters the target range; S35, use the golden section search method to quickly solve the minimum adjustment time , and adjust the prediction time based on the compensation factor of historical prediction error.

[0010] As a further improvement of the technical solution, in S4, the specific steps of predicting the indoor soil temperature after time based on the indoor temperature influence model are as follows: S41, obtain the heat transfer coupling coefficient​ with heat loss rate further obtain the soil temperature response time constant and steady state temperature ; S42, based on the data of S41, consider the inherent time lag attenuation factor , and adopt a first-order inertial system model to predict the dynamic response of the soil temperature in the greenhouse, and predict the soil temperature in the greenhouse after .

[0011] In another aspect, the present application provides a temperature control device for a seedling greenhouse cultivation environment, comprising a sensor, a storage, a processor and a computer program stored in the storage and executable on the processor, wherein the processor executes the computer program to realize the steps of the temperature control method for the seedling greenhouse cultivation environment according to any one of the above.

[0012] As a further improvement of the technical solution, the sensor at least includes a soil temperature sensor, an air temperature sensor, a soil humidity sensor, a high-definition camera and an outdoor air temperature sensor.

[0013] In another aspect, the present application provides a storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to realize the steps of the method according to any one of the above.

[0014] Compared with the prior art, the present application has the following beneficial effects: In the temperature control method, device and storage medium for the seedling greenhouse cultivation environment, the soil and air temperature in the greenhouse is accurately collected in real time, and a dynamic temperature influence model in the greenhouse is established combined with historical data, fully considering the influence of soil humidity, outdoor temperature and light fluctuation, which not only effectively avoids energy waste and adverse effects on root system, but also optimizes the control signal through PID control and nonlinear mapping, realizes accurate energy input, greatly improves the response speed and adaptability to environmental changes, and provides more stable and suitable growth conditions for seedlings. BRIEF DESCRIPTION OF DRAWINGS

[0015] Figure 1 The overall method flowchart of the present application. DETAILED DESCRIPTION

[0016] The technical solutions in the embodiments of the present application will be described clearly and completely in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0017] Embodiment 1: Please refer to Figure 1 The embodiment provides a temperature control method for a seedling greenhouse cultivation environment, which comprises the following steps: S1, distributed sensors are buried at different depths of the soil to collect the soil temperature in the greenhouse in real time, and distributed sensors are arranged at the height of the plant canopy to measure the air temperature in the greenhouse; specifically, a temperature measuring instrument is installed on the column at both sides of the planting area, the temperature measuring instrument can always keep flush with the top of the canopy by adjusting the height of the support, and the infrared temperature measuring instrument is installed above the gap between the plant rows to ensure that the infrared rays are not blocked by the plant leaves; the soil temperature in the greenhouse represents the temperature of the seedling root system, and the air temperature represents the canopy temperature of the seedling; the root system temperature and the canopy temperature are adjusted to reach the temperature required for the growth of the seedling, so as to promote the yield and efficiency of the seedling.

[0018] S2, a greenhouse temperature influence model is established according to the real-time collected soil temperature in the greenhouse and the air temperature in the greenhouse, and the historical soil temperature in the greenhouse and the air temperature in the greenhouse; the greenhouse temperature influence model can predict the air temperature in the greenhouse according to the soil temperature in the greenhouse, and the influence of the air temperature outside the greenhouse on the air temperature in the greenhouse is considered to optimize the establishment of the greenhouse temperature influence model; The specific steps of establishing the greenhouse temperature influence model in S2 are as follows: S21, the dynamic relationship between the soil temperature and the air temperature in the greenhouse is established, and the nonlinear adjustment effect of soil humidity is considered; the adjustment effect of soil humidity on heat conduction is described by an exponential function , avoiding the idealized assumption of the traditional linear model. When the soil humidity is low , the adjustment term tends to 0, and the heat exchange between the soil and the air is weak; after the humidity increases , the adjustment term increases significantly, for example , reflecting the enhanced heat conduction of the humid soil. Especially in the scene of sudden humidity increase after irrigation, the model can more accurately predict the rapid response of the air temperature.

[0019] At the same time, the temperature difference driving term reflects the instantaneous heat balance between the air and the soil, and the humidity adjustment coefficient ensures that the model conforms to the physical law of energy transfer.

[0020] S22, the cross-correlation function is calculated through historical data to determine the lag time , and the soil temperature and the air temperature in the greenhouse The lag term is introduced in the dynamic relationship between soil and air temperature; The cross-correlation function is used to analyze historical data to determine the lag time of soil temperature on air temperature (As an example, the soil temperature is 20°C at 8:00, and the air temperature is 25°C at 8:00. The soil absorbs heat during the day, and the heat needs to be conducted to the surface and affect the air temperature for several hours. The lag term accurately reflects this process. The introduction of the lag term avoids regarding soil and air temperature as instantaneous synchronous changes, reducing the sensitivity of the model to instantaneous noise. Especially in environments with large diurnal temperature differences, the model can distinguish between different stages of heat accumulation during the day and heat release at night, avoiding large fluctuations in predicted values.

[0021] The cross-correlation function is calculated by historical data to determine the lag time Specifically: In the formula, is the cross-correlation function at ; is the average value of soil temperature; is the number of sampling time points; is the lag time; is the measured value of the indoor air temperature at time ; is the average value of air temperature; ; The specific process is: standardize and , calculate the correlation coefficient under different , generate the CCF curve, find the lag time corresponding to the CCF peak value, that is , which is the lag time . If the CCF reaches the peak value at hours (such as 0.85), then hours, that is, the soil temperature change needs 2 hours to significantly affect the air temperature.

[0022] S23, finally, the outdoor temperature is added to the dynamic relationship between soil temperature and indoor air temperature , considering the noise term of light fluctuation and human disturbance , and finally generating the indoor temperature influence model; In the formula, is the indoor air temperature at time; is the soil temperature at time; is the influence weight of soil on air temperature; ​Soil temperature lag time; For timestamps; This is the soil moisture regulation coefficient; In order to be in Soil moisture over time; It is the heat exchange intensity coefficient; In order to be in The temperature of the air inside the shed over time; In order to be in Soil temperature over time; In order to be in The temperature outside the shed during the time; The penetration intensity of outside temperature into the greenhouse; In order to be in Noise term in time; In S2, the specific steps for optimizing the greenhouse temperature influence model by considering the impact of outside air temperature on inside air temperature are as follows: S24. An exponential function is used to quantify the nonlinear effect of ventilation intensity on heat exchange between the inside and outside of the shed, generating a heat leakage coefficient; when ventilation is closed ( When heat leakage approaches zero, and with enhanced ventilation, heat exchange efficiency exhibits saturated growth, avoiding distortion of the linear model. (Covering material coefficient) Further adjustments to the heat leakage intensity are made; for example, double-layer membranes, due to their superior insulation properties, have a lower value. This design precisely characterizes the synergistic effect of ventilation and materials on heat exchange; the heat leakage coefficient is: ; S25. By weighting the temperature difference between inside and outside the greenhouse over past time periods, the temperature lag effect caused by heat storage or release in the greenhouse is captured, and the attenuation factor is used to... The decay rate of historical effects is controlled because the heat storage capacity of the greenhouse structure causes temperature changes to lag behind those of the external environment. For example, during the day when the outside temperature is high, heat is absorbed by the soil; at night, as the outside temperature drops, the stored heat is gradually released, slowing down the temperature drop inside the greenhouse. Therefore, the temperature lag effect of the greenhouse is introduced, i.e., a weighted cumulative term of historical temperature differences: ; S26, Based on the current outdoor temperature The direct effect of heat leakage and the cumulative effect of historical temperature lag are combined with the heat leakage coefficient to generate the external temperature influence coefficient. ; In the formula, In time The influence of the outside temperature of the greenhouse; The thermal resistivity of the covering material; In order to be in Ventilation intensity over time; To fit the parameters, the nonlinear response speed of the ventilation intensity is controlled; is a scaling factor for the historical temperature difference accumulation term; is a decay factor; is the outdoor temperature at the past time step; is the indoor air temperature at the past time step; is the historical window length, considering the influence of how many time steps in the past; ; In winter night, the outdoor temperature drops sharply to , the greenhouse is in semi-ventilation state , the covering material is double membrane ; Heat leakage coefficient: Heat inertia correction term (take , , , the temperature difference of the past 3 hours is 2℃, 1℃, 0℃): Total outdoor temperature influence: S27, according to the outdoor temperature influence coefficient , the optimized indoor temperature influence model is generated; In the formula, is the optimized indoor air temperature at time; S3, based on the growth stage of seedlings, determine the target soil temperature range and target air temperature range of seedlings, judge whether the real-time indoor air temperature is in the target indoor air temperature range by monitoring, determine the air temperature error between the indoor air temperature and the target indoor air temperature, and predict the air temperature adjustment completion time based on the air temperature adjustment strategy and the indoor temperature influence model ; The specific steps of determining the target soil temperature range and target air temperature range of seedlings based on the growth stage of seedlings in S3 are as follows: real-time collection of seedling growth state data through sensors installed in the greenhouse, judgment of the growth stage to which the current seedlings belong based on the collected seedling growth state data, construction of an experience module of growth stage and temperature demand according to historical seedling growth state data, recording of the target soil temperature and target air temperature range corresponding to each growth stage of seedlings in the experience module, and finally determining the target soil temperature range and target air temperature range by fine-tuning the range of target soil temperature and target air temperature according to the current environment, target soil temperature range: ; target air temperature range: .

[0023] In S3, the specific steps of determining the air temperature error and adjusting the air temperature by adopting the air temperature adjustment strategy are as follows: S31, comparing the current time point's indoor air temperature real-time data with the target indoor air temperature range to calculate the air temperature error ; Wherein, is the average value of the seedling target air temperature range; S32, mapping the air temperature error to the preliminary control strength based on a nonlinear mapping function, and combining the nonlinear mapping function output with the proportional, integral and differential control effects by using a PID controller to finally generate the control signal containing the heating power and heating time ; In the formula, is the temperature difference mapping value; is a sign function, which ensures correct positive and negative instructions; is the control nonlinear degree; is a normalization parameter, which ensures that the output tends to saturation at large errors to avoid excessive adjustment strength; In the formula, is the time control signal; is the proportional control gain; is the integral control gain; is the differential control gain; In S33, the specific steps of predicting the air temperature adjustment completion time based on the air temperature adjustment strategy and the indoor temperature influence model are as follows: S33, inputting the control variable containing the heating power into the indoor temperature influence model to predict the indoor air temperature at the next time step; In the formula, is the air temperature at time; is the control efficiency coefficient, which is determined by a conventional method (such as the least square method) according to historical operation data, and the historical operation data includes but is not limited to the control signal applied at different times ​​The slope of the regression model obtained by fitting the input and output data using a linear regression method such as least squares is the regulation efficiency coefficient ; S34, determining whether the indoor air temperature at the next time step is within the target indoor air temperature range, and if not, iteratively updating the air temperature error and the regulation signal until the predicted indoor air temperature enters the target range; S35, using the golden section search method to quickly solve the minimum adjustment time , and adjusting the prediction time based on the compensation factor of the historical prediction error.

[0024] Define the target function: Where, and are the lower and upper limits of the target air temperature range, respectively.

[0025] Iteration process: Initialize the search interval ; Calculate the midpoint ; Predict by model , update the search interval; When , terminate and output ; Specifically: Iteratively narrow the search range within a preset time interval: each time select 61.8% (golden section point) of the interval length as the candidate time , use the prediction model to calculate the indoor air temperature at time , and update the search boundary according to the deviation direction of the predicted temperature from the target interval. For example, if the predicted temperature is lower than the target lower limit, discard the left half interval; otherwise, adjust the right boundary. Iterate until the error between the predicted temperature and the target median is less than a threshold , output ; First, calculate the average absolute error of the predicted indoor air temperature and the actual indoor air temperature at the last N time points, and normalize it with the span of the target indoor air temperature range ΔTrange to obtain the relative error ratio. Multiply this ratio by the compensation intensity coefficient (default 0.2) as a dynamic correction coefficient to adjust the prediction time For example, if the average prediction error over the past 5 minutes accounts for 10% of the target interval width, the final adjustment time will be extended to 1.02 times the original prediction value (1 + 0.2 × 0.1). This mechanism significantly improves the robustness of time prediction under different environmental conditions by learning the characteristics of system errors online.

[0026] S4. During temperature regulation, the soil temperature inside the greenhouse is monitored in real time, and the time required is predicted based on the greenhouse temperature influence model. The soil temperature inside the greenhouse is then measured, and it is determined whether the soil temperature inside the greenhouse is within the range of the target soil temperature inside the greenhouse. If the soil temperature inside the greenhouse is not within the range of the target soil temperature inside the greenhouse, the soil temperature is adjusted. In this embodiment, temperature adjustment is achieved through underground hot water pipes.

[0027] In S4, the time is predicted based on the greenhouse temperature influence model. The specific steps for controlling the soil temperature inside the greenhouse are as follows: S41. Obtain the heat transfer coupling coefficient based on online fitting. With heat loss rate This leads to the soil temperature response time constant. and steady-state temperature ; In the formula, The baseline temperature inside the greenhouse (the temperature that the soil will eventually tend to when there is no active heating or cooling of the soil). S42. Based on the data from S41, consider the inherent time lag decay factor. A first-order inertial system model was used to predict the dynamic response of soil temperature inside the greenhouse, with a prediction time of [time value missing]. The soil temperature inside the greenhouse afterwards; The model for the first-order inertial system is as follows: In the formula, for Soil temperature inside the shed after a certain time; To regulate the initial soil temperature inside the greenhouse; The inherent time lag of the system is the response delay required for temperature to transfer from the air to the soil; when When the value is small, the exponent term is close to 1, and the predicted temperature is close to the initial soil temperature. ; when As the exponential term approaches a larger value, the system temperature approaches a steady-state value. ; This model can utilize real-time detection. and online adaptive determined parameters, more accurately predict the soil temperature after the regulation time , thereby providing a basis for the next step of assisted regulation.

[0028] Embodiment 2: The embodiment provides a temperature control device for seedling greenhouse cultivation environment, comprising a sensor, a storage, a processor and a computer program stored in the storage and executable on the processor, wherein the processor implements the steps of the temperature control method for seedling greenhouse cultivation environment according to any one of the above embodiments when executing the computer program.

[0029] The sensor at least comprises: a soil temperature sensor, which is used for real-time monitoring of soil temperature, driving model establishment and soil temperature regulation, ensuring a suitable root environment and optimizing temperature prediction accuracy; an air temperature sensor, which is used for real-time monitoring of canopy air temperature, verifying the regulation effect and predicting future temperature, and ensuring stable air temperature; a soil humidity sensor, which is used for providing soil humidity data, optimizing the greenhouse temperature influence model of the relationship between soil and air temperature, reducing water disturbance, and improving the synergy of irrigation and temperature regulation; a high-definition camera, which is used for identifying seedling species and growth stages, triggering knowledge base query, and accurately adapting to the environmental needs of different growth stages; an outdoor air temperature sensor, which is used for monitoring external temperature, optimizing modeling of heat exchange and temperature difference hysteresis effect, improving the adaptability of the model to external environmental changes, and reducing prediction errors.

[0030] The embodiment also provides a storage medium having a computer program stored thereon, wherein the computer program implements the steps of the method according to any one of the above embodiments when executed by a processor.

[0031] The basic principles, main features and advantages of the present application are shown and described above. It should be understood by those skilled in the art that the present application is not limited by the above embodiments, and the above embodiments and descriptions in the specification are only preferred examples of the present application and are not intended to limit the present application. Without departing from the spirit and scope of the present application, various changes and improvements can be made to the present application, and these changes and improvements all fall within the scope of the claimed present application.

Claims

1. A method of temperature control of a seedling greenhouse cultivation environment, characterized by, The method comprises the following steps: S1, respectively burying distributed sensors at different depths of the soil to collect the soil temperature in the greenhouse in real time, and deploying distributed sensors at the height of the plant canopy to measure the air temperature in the greenhouse; S2, establishing a greenhouse temperature influence model according to the real-time collected soil temperature in the greenhouse and the air temperature in the greenhouse combined with the historical soil temperature in the greenhouse and the air temperature in the greenhouse, the greenhouse temperature influence model can predict the air temperature in the greenhouse according to the soil temperature in the greenhouse, and the influence of the outdoor air temperature on the air temperature in the greenhouse is considered for optimization when the greenhouse temperature influence model is established; S3, determining a target soil temperature range and a target air temperature range based on the growth stage of the seedling, determining whether the real-time indoor air temperature is within the target indoor air temperature range by monitoring the real-time indoor air temperature, determining an air temperature error between the indoor air temperature and the target indoor air temperature, and predicting an air temperature adjustment completion time based on an air temperature adjustment strategy and an indoor temperature influence model ; S4. During temperature regulation, the soil temperature inside the greenhouse is monitored in real time, and the time required is predicted based on the greenhouse temperature influence model. The soil temperature inside the greenhouse is then measured, and it is determined whether the soil temperature inside the greenhouse is within the range of the target soil temperature inside the greenhouse; if the soil temperature inside the greenhouse is not within the range of the target soil temperature inside the greenhouse, the soil temperature is adjusted.

2. The method of temperature control of a nursery greenhouse growing environment according to claim 1, wherein: The specific steps of establishing the greenhouse temperature influence model in S2 are as follows: S21, establishing soil temperature the dynamic relationship between the air temperature in the greenhouse and the soil temperature, taking into account the non-linear regulating action of the soil humidity ; S22, calculate cross-correlation function by historical data to determine lag time and introduce lag term in dynamic relationship between soil temperature and greenhouse air temperature ​ S23, finally the outside temperature as a linear term to the soil temperature between the inside air temperature with the dynamic relationship, while considering the noise term of light fluctuation and human disturbance , finally generate the inside temperature influence model.

3. The method of temperature control of a nursery greenhouse growing environment according to claim 2, wherein: The specific steps of considering the influence of the outdoor air temperature on the air temperature in the greenhouse for optimization when the greenhouse temperature influence model is established in S2 are as follows: S24, using an exponential function to quantify the non-linear influence of ventilation intensity on heat exchange between the inside and outside of the greenhouse to generate a heat leakage coefficient; S25, capturing the temperature hysteresis effect caused by the heat storage or release of the greenhouse by weighting the temperature difference between inside and outside of the greenhouse in the past time period, and through the decay factor controlling the decay rate of the history influence; S26, based on the current outdoor temperature The direct effect and the cumulative effect of historical temperature hysteresis effect, combined with the heat leakage coefficient to generate the outdoor temperature influence coefficient And then generate the optimized indoor temperature influence model.

4. The method of temperature control of a nursery greenhouse growing environment according to claim 3, wherein: In S3, the specific steps of determining the target soil temperature range and the target air temperature range based on the growth stage of the seedling are as follows: collecting the seedling growth state data in real time through the sensors installed in the greenhouse, determining the growth stage to which the current seedling belongs based on the collected seedling growth state data, and determining the target soil temperature and target air temperature range corresponding to each growth stage of the seedling, adjusting the range of the target soil temperature and target air temperature according to the current environment, and finally determining the target soil temperature range and target air temperature range.

5. The method of temperature control of a nursery greenhouse growing environment according to claim 4, wherein: In S3, the specific steps of the air temperature regulation strategy are as follows: S31, compare the current time point's real-time data of the indoor air temperature with the target indoor air temperature range, and calculate the air temperature error ; S32, mapping the air temperature error to a preliminary control effort based on a non-linear mapping function, while using a PID controller to combine proportional, integral, and derivative control actions with the non-linear mapping function output to ultimately generate a control signal comprising heating power and heating time .​ 6. The method of temperature control of a nursery greenhouse growing environment according to claim 5, wherein: In the S3, the air temperature adjustment completion time is predicted based on the air temperature adjustment strategy and the indoor temperature influence model The specific steps are as follows: S33, the control variable comprising heating power is input into the indoor temperature influence model to predict the indoor air temperature at the next time step; S34, determining whether the air temperature in the greenhouse at the next time step is within the range of the target air temperature in the greenhouse, if not, iteratively updating the air temperature error and the control signal until the predicted air temperature in the greenhouse enters the target range; S35, golden section search method is used to quickly solve the minimum adjustment time , and the prediction time is adjusted based on the compensation factor of historical prediction error.

7. The method of temperature control of a nursery greenhouse growing environment according to claim 6, wherein: In step S4, the time is predicted based on the greenhouse temperature influence model. The specific steps for controlling the soil temperature inside the greenhouse are as follows: S41、According to the online fitting, the heat transfer coupling coefficient is obtained With the heat loss rate Further, the soil temperature response time constant is obtained And the steady-state temperature ; S42, attenuate factor based on data of S41 considering inherent time lag and a first-order inertial system model is used to predict the dynamic response of the soil temperature in the greenhouse, and the soil temperature in the greenhouse after the prediction time is predicted.

8. A temperature control device for an intelligent nursery greenhouse cultivation environment, comprising a sensor, a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: The processor executes the computer program to realize the steps of the temperature control method of the seedling greenhouse cultivation environment in any one of claims 1 to 7.

9. The temperature control device for a nursery greenhouse growing environment according to claim 8, wherein: The sensor at least includes a soil temperature sensor, an air temperature sensor, a soil humidity sensor, a high-definition camera, and an outdoor air temperature sensor.

10. A storage medium having stored thereon a computer program, characterized in that: The computer program is executed by the processor to realize the steps of the method of any one of claims 1 to 7. The computer program is executed by the processor to realize the steps of the method of any one of claims 1 to 7.

Images