Intelligent greenhouse accurate regulation and control method and system based on artificial intelligence, and storage medium

Abstract

The invention relates to the technical field of artificial intelligence, and discloses an intelligent greenhouse accurate regulation and control method and system based on artificial intelligence, and a storage medium. And target environment parameters needing to be regulated and controlled are locked according to the difference between the current environment and the parameter optimal range. And formulating a target power supply strategy containing a dual-voltage power supply parameter matrix for the sensor corresponding to the target environment parameter, dynamically adjusting the power supply voltage, and accurately obtaining environment monitoring data, thereby realizing accurate regulation and control of the greenhouse environment. According to the scheme, the accuracy and stability of environmental parameter monitoring can be effectively improved, and data deviation caused by unreasonable power supply of the sensor is avoided; meanwhile, the regulation and control strategy is dynamically optimized based on the crop growth requirements, the environmental requirements of the crops in different growth stages can be better met, the fine management of the crop growth environment in the intelligent greenhouse is finally realized, and the improvement of the crop yield and quality is facilitated.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an artificial intelligence-based smart greenhouse precise control method, system and storage medium. Background Art

[0002] With the development of agricultural modernization, smart greenhouses have gradually become an important means to improve crop yield and quality. Traditional greenhouse environmental control mostly relies on manual experience or fixed threshold control, which makes it difficult to accurately match the environmental needs of crops at different growth stages. For example, the control of parameters such as ambient temperature, humidity, light intensity and trace element supply lacks dynamicity, resulting in waste of resources or restricted crop growth. At the same time, the power supply method of environmental monitoring sensors usually uses a fixed voltage, without considering the impact of environmental factors on sensor performance. When environmental parameters such as ambient temperature changes and humidity fluctuate, the accuracy and stability of sensor monitoring data are difficult to guarantee, which in turn affects the scientific nature of control decisions. Therefore, there is an urgent need for a precise control method based on artificial intelligence that can combine crop growth characteristics with environmental changes to achieve dynamic optimization of environmental parameters and adaptive adjustment of sensor power supply strategies to improve the management efficiency and economic benefits of smart greenhouses. Summary of the Invention

[0003] The main purpose of the present invention is to provide a method, system and storage medium for precise control of smart greenhouses based on artificial intelligence.

[0004] To achieve the above objectives, in a first aspect, an embodiment of the present application provides a method for precise control of a smart greenhouse based on artificial intelligence, which is applied to a control system. The method includes: Obtain the full growth cycle demand model of the target crops in the greenhouse; Determining candidate environmental parameters that need to be regulated during the current growth phase based on the full growth cycle demand model and historical supply data; When the number of the candidate environmental parameters is greater than or equal to two, determining the target environmental parameter that needs to be precisely controlled according to the difference between the current environmental conditions in the greenhouse and the optimal range of the candidate environmental parameters; Determine the target power supply parameters of the environmental monitoring sensor corresponding to the target environmental parameter according to the current environmental conditions in the greenhouse, wherein the target power supply parameters include a dual-voltage power supply parameter matrix; Acquire environmental monitoring data of the environmental monitoring sensor under the target power supply parameters, and perform precise regulation based on the environmental monitoring data so that the environmental monitoring data is dynamically within the optimal range of the target environmental parameters.

[0005] In one possible implementation, the full growth cycle demand model includes a temperature demand sub-model, a humidity demand sub-model, a light demand sub-model, and a trace element demand sub-model. Determining the candidate environmental parameters that need to be regulated in the current growth stage based on the full growth cycle demand model and historical supply data includes: Determining a historical supply matching degree of each environmental parameter of the target crop according to the historical supply data of each environmental parameter of the target crop and the corresponding demand sub-model; An environmental parameter whose historical supply matching degree is less than or equal to the matching degree threshold is determined as a candidate environmental parameter.

[0006] In a possible implementation, determining the historical supply matching degree of each environmental parameter of the target crop based on the historical supply data of each environmental parameter of the target crop and the corresponding demand sub-model includes: For each environmental parameter, a time series historical supply data matrix is ​​constructed, where the matrix elements include supply values ​​sampled at fixed time intervals within a preset historical period; Input the historical supply data matrix into the corresponding demand sub-model to generate a theoretical demand value sequence at each time point; Calculate the difference between the historical supply value and the theoretical demand value at each time point to obtain the supply deviation sequence; Perform a sliding window analysis on the supply deviation sequence to calculate the average supply deviation rate within each window, where the average supply deviation rate is the average value of the ratio of the supply deviation value to the theoretical demand value at each time point within the window; The historical supply matching degree of each environmental parameter of the target crop is determined according to the average supply deviation rate.

[0007] In one possible implementation, determining the target environmental parameter that needs to be precisely controlled based on the difference between the current environmental condition in the greenhouse and the optimal range of the candidate environmental parameters includes: For each candidate environmental parameter, the actual supply data is calculated to determine the deviation between the actual supply data and the optimal range of the candidate environmental parameter. The candidate environmental parameters whose deviation degree is greater than or equal to the deviation degree threshold are determined as target environmental parameters.

[0008] In one possible implementation, the target environmental parameter includes an ambient temperature, the environmental monitoring sensor includes a temperature sensor, and determining, based on the current environmental conditions in the greenhouse, a target power supply parameter corresponding to the environmental monitoring sensor of the target environmental parameter includes: The current ambient temperature value in the greenhouse is input into the pre-established correlation model between the power supply voltage and the sensor monitoring accuracy to obtain the main frequency power supply voltage value and the secondary frequency power supply voltage value; The dual-voltage power supply parameter matrix is ​​generated according to the primary frequency power supply voltage value, the secondary frequency power supply voltage value, and a preset voltage switching frequency.

[0009] In one possible implementation, the current ambient temperature value in the greenhouse is input into a pre-established correlation model between the power supply voltage and the sensor monitoring accuracy to obtain the primary frequency power supply voltage value and the secondary frequency power supply voltage value, including: When the current ambient temperature of the greenhouse is greater than or equal to the temperature threshold, the temperature sensor is powered by a first power supply voltage at a primary frequency, and the temperature sensor is powered by a second power supply voltage at a secondary frequency, wherein the second power supply voltage is greater than the first power supply voltage; When the current ambient temperature of the greenhouse is lower than the temperature threshold, the temperature sensor is powered by the second power supply voltage at the primary frequency, and the temperature sensor is powered by the first power supply voltage at the secondary frequency.

[0010] In a possible implementation, the method further includes: Correcting the preset voltage switching frequency according to the rate of change of the ambient temperature value to obtain a target voltage switching frequency; wherein, when the rate of change of the ambient temperature value is greater than or equal to the rate of change threshold, increasing the duty cycle of the main frequency power supply voltage; Regenerate the dual voltage power supply parameter matrix according to the main frequency power supply voltage value, the secondary frequency power supply voltage value and the target voltage switching frequency; In one possible implementation, the control system includes a power supply circuit and a voltage switching circuit, wherein the voltage switching circuit includes an interlock switch component. After determining the target power supply parameter of the environmental monitoring sensor corresponding to the target environmental parameter according to the current environmental conditions in the greenhouse, the control system further includes: generating mutually exclusive driving signals according to the dual voltage power supply parameter matrix; One of the electronic switches in the interlock switch assembly is controlled to be turned on according to the driving signal so that the power supply circuit supplies power to the temperature sensor according to the target power supply parameter.

[0011] In a second aspect, an embodiment of the present application further provides a control system, comprising: a memory and a processor, wherein the memory is used to store program code; the processor is used to call the program code to execute the method described in the first aspect.

[0012] In a third aspect, an embodiment of the present application further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the method described in the first aspect are implemented.

[0013] Different from the existing technology, the embodiment of the present application provides an artificial intelligence-based precise control method for smart greenhouses. By constructing a full growth cycle demand model for target crops, candidate environmental parameters are screened out in combination with historical supply data, and then the target environmental parameters that need to be controlled are locked based on the difference between the current environment and the optimal range of the parameters. On this basis, a target power supply strategy containing a dual-voltage power supply parameter matrix is ​​formulated for the sensors corresponding to the target environmental parameters, and the power supply voltage is dynamically adjusted to accurately obtain environmental monitoring data, thereby achieving precise control of the greenhouse environment. This solution can effectively improve the accuracy and stability of environmental parameter monitoring and avoid data deviations caused by unreasonable sensor power supply. At the same time, the dynamic optimization of the control strategy based on crop growth needs can better meet the environmental requirements of crops at different growth stages, improve resource utilization efficiency, reduce energy waste, and ultimately achieve refined management of the crop growth environment in the smart greenhouse, helping to improve crop yield and quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in 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 some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying any creative work.

[0015] Figure 1 This is a flow chart of a method for precise control of a smart greenhouse based on artificial intelligence in some embodiments of the present application; Figure 2 This is a flow chart of step S200 of the method for precise control of smart greenhouses based on artificial intelligence in some embodiments of the present application; Figure 3 This is a flow chart of step S300 of the method for precise control of smart greenhouses based on artificial intelligence in some embodiments of the present application; Figure 4 This is a schematic diagram of a power supply circuit of a control system in one embodiment of the present application; Figure 5 This is a schematic diagram of a voltage switching circuit of a control system in one embodiment of the present application; Figure 6 This is a schematic diagram of the hardware structure of the control system in some embodiments of the present application.

[0016] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0017] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0018] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative position relationship, movement status, etc. between the various components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0019] In addition, the descriptions of "first", "second", etc. in the present invention are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, "and / or" in the full text includes three solutions. Taking A and / or B as an example, it includes technical solution A, technical solution B, and technical solution that satisfies both A and B. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in this field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0020] Traditional greenhouse environmental control relies heavily on manual experience or fixed threshold control, making it difficult to accurately match the environmental needs of crops at different growth stages. For example, the control of parameters such as ambient temperature, humidity, light intensity, and trace element supply lacks dynamism, resulting in waste of resources or restricted crop growth. At the same time, environmental monitoring sensors are usually powered by a fixed voltage, without considering the impact of environmental factors on sensor performance. When the ambient temperature changes or the humidity fluctuates, the accuracy and stability of the sensor monitoring data are difficult to guarantee, which in turn affects the scientific nature of the control decision. Therefore, there is an urgent need for a precise control method based on artificial intelligence that can combine crop growth characteristics with environmental changes to achieve dynamic optimization of environmental parameters and adaptive adjustment of sensor power supply strategies to improve the management efficiency and economic benefits of smart greenhouses.

[0021] like Figure 1-Figure 5 As shown, the following takes the control system executing the intelligent greenhouse precise control method based on artificial intelligence as an example to illustrate. It should be noted that although the logical order is shown in the flow chart, in some cases, the steps shown or described can be executed in a different order than here. Figure 1The method includes the following steps S100 to S500: Step S100: obtaining a full growth cycle demand model of target crops in the greenhouse; The full growth cycle demand model is based on the principles of crop physiology, ecology and environmental science, combined with historical data, experimental observations and machine learning algorithms, to dynamically simulate the crop's demand for environmental factors such as light, temperature, humidity, CO2 concentration, water, and nutrients (such as nitrogen, phosphorus, and potassium) at different growth stages (such as germination, vegetative growth, reproductive growth, and maturity).

[0022] The full growth cycle demand model can include different segmented demand models, such as light demand sub-model, temperature demand sub-model, humidity demand sub-model, CO2 concentration demand sub-model, water demand sub-model, and nutrient (such as nitrogen, phosphorus, and potassium) demand sub-model. Different segmented demand models provide accurate data basis for growth.

[0023] Step S200: determining candidate environmental parameters that need to be regulated in the current growth stage based on the full growth cycle demand model and historical supply data; It is understood that environmental parameters may include different parameters such as light, temperature, humidity, CO2 concentration, water, nutrients (such as nitrogen, phosphorus, potassium), etc. Candidate environmental parameters refer to environmental parameters that are initially determined to need to be regulated.

[0024] Candidate environmental parameters can be pre-defined, for example, key parameters strongly correlated with crop physiological needs based on crop growth models, variety characteristic databases, or historical planting experience. Alternatively, they can be derived based on changes in environmental parameters. For example, by monitoring the changing trends of environmental parameters in real time (e.g., a sudden increase in humidity at night may increase the risk of downy mildew), combined with threshold triggering mechanisms or machine learning anomaly detection algorithms, parameters requiring dynamic control can be identified.

[0025] In one embodiment, the full growth cycle demand model includes a temperature demand sub-model, a humidity demand sub-model, a light demand sub-model, and a trace element demand sub-model. Step S200 of determining candidate environmental parameters that need to be regulated in the current growth stage based on the full growth cycle demand model and historical supply data includes: S210, determining a historical supply matching degree of each environmental parameter of the target crop according to the historical supply data of each environmental parameter of the target crop and a corresponding demand sub-model; S220: Determine the environmental parameters whose historical supply matching degree is less than or equal to the deviation threshold as candidate environmental parameters.

[0026] The temperature requirement sub-model represents the temperature requirements of crops at various growth stages (e.g., optimal temperature, upper and lower temperature tolerance limits). The humidity requirement sub-model represents the thresholds of air or soil humidity requirements of crops (e.g., suitable humidity ranges at different growth stages). The light requirement sub-model represents the requirements of crops for light intensity, duration, or quality (e.g., photoperiod, photosynthetically active radiation). The trace element requirement sub-model represents the ratios and concentration thresholds of the crops' requirements for macronutrients such as nitrogen, phosphorus, and potassium, as well as trace elements such as iron, zinc, and boron.

[0027] The supply matching degree represents the degree of matching between historical supply data and crop demand. In one embodiment, the step S210: determining the historical supply matching degree of each environmental parameter of the target crop based on the historical supply data of each environmental parameter of the target crop and the corresponding demand sub-model, includes: constructing a historical supply data matrix of a time series for each environmental parameter, wherein the matrix elements include supply values ​​sampled at fixed time intervals within a preset historical time period; inputting the historical supply data matrix into the corresponding demand sub-model to generate a theoretical demand value sequence for each time point; calculating the difference between the historical supply value and the theoretical demand value at each time point to obtain a supply deviation sequence; performing a sliding window analysis on the supply deviation sequence to calculate the average supply deviation rate within each window, wherein the average supply deviation rate is the average value of the ratio of the supply deviation value to the theoretical demand value at each time point within the window; and determining the historical supply matching degree of each environmental parameter of the target crop based on the average supply deviation rate.

[0028] Specifically, the historical supply matching degree can be calculated by the following formula:

[0029] Where, e k,i is the supply deviation value at the i-th time point in window k, r k,i is the theoretical demand value at the i-th time point in window k, w is the sliding window size, and F is the historical supply matching degree.

[0030] For example, the target crop is tomato, the preset historical time period is the past 30 days, and the fixed time interval is 1 hour. That is, the temperature in the greenhouse is sampled once every hour, and a total of 720 temperature supply values ​​are obtained. Construct the historical supply data matrix S of the time series. S is a 1×720 matrix (this is a simplified representation and may have different dimensions depending on the situation). The matrix element s i(1, 2, ...720), which is the temperature supply value at each time point, for example, S1 = 20°C, S2 = 20.5°C, etc. The tomato temperature demand sub-model is pre-established. Its input is time (corresponding to different growth stages) and its output is the theoretical required temperature value. Inputting the historical supply data matrix S into the tomato temperature demand sub-model, we obtain the theoretical demand value sequence R at each time point. R is also a 1×720 matrix, with element r i (1, 2, ...720) are the theoretical required temperatures at the corresponding time points. For example, at a certain moment in the early growth period of tomatoes, the theoretical required temperatures are r1 = 20°C and r2 = 18.2°C. Calculate the difference between the historical supply value and the theoretical demand value at each time point to obtain the supply deviation sequence E. For each time point i, e i =s i −r i For example, at the first time point, e1=s1−r1=20-18=2°C, and at the second time point, e2=s2−r2=20.5-18.2=2.3°C. Set the sliding window size w = 24 (i.e., the window covers 1 day of time data). Perform a sliding window analysis on the supply deviation sequence E. In the first window k = 1 (corresponding to the 1st to 24th time points), the historical supply matching degree corresponding to window k = 1 is finally obtained according to the above formula. .

[0031] As the window slides (each time a window is slid), the historical supply matching degree corresponding to each window can be calculated sequentially, providing a comprehensive understanding of the degree of match between tomato temperature supply and demand at different time periods over the past 30 days. If the average F value calculated over the 30 windows is closer to 1, the temperature matching degree is higher, indicating that the historical temperature supply more effectively meets the growing needs of tomatoes. If the average F value calculated over the 30 windows deviates from 1, the temperature matching degree is lower, and the temperature control strategy may need to be adjusted.

[0032] In the embodiment of the present application, an environmental parameter whose historical supply matching degree is less than or equal to a matching degree threshold (such as 0.98) is determined as a candidate environmental parameter, indicating that the parameter has deviated from the crop requirements for a long time in history (such as the temperature supply is continuously higher or lower than the theoretical value) and may become a limiting factor in the current growth stage. Therefore, the environmental parameter is preliminarily determined as a candidate environmental parameter that needs to be regulated.

[0033] Step S300: When the number of the candidate environmental parameters is greater than or equal to two, determine the target environmental parameter that needs to be precisely controlled based on the difference between the current environmental condition in the greenhouse and the optimal range of the candidate environmental parameters; If the number of candidate environmental parameters is one, the candidate environmental parameter is used as the target environmental parameter. If the number of candidate environmental parameters is greater than or equal to two, the target environmental parameter needs to be determined from multiple candidate environmental parameters.

[0034] Specifically, the degree of deviation between the current actual data and the required value for each candidate environmental parameter can be evaluated. If the current actual data for a candidate environmental parameter is close to the required value, that is, within a reasonable fluctuation range, then no adjustment is made to it. If the current actual data deviates from the required value, exceeding the reasonable fluctuation range, then that candidate environmental parameter is determined to be the target environmental parameter and requires precise control.

[0035] In one embodiment, step S300: determining the target environmental parameter that needs to be precisely controlled based on the difference between the current environmental condition in the greenhouse and the optimal range of the candidate environmental parameters, includes: S310, for each candidate environmental parameter, calculating the degree of deviation between the current actual supply data and the optimal range of the candidate environmental parameter; S320: Determine the candidate environmental parameters whose deviation degree is greater than or equal to the deviation degree threshold as target environmental parameters.

[0036] Specifically, the current actual supply data of each candidate environmental parameter can be preliminarily monitored by sensors, and the degree of deviation between the current actual supply data and the optimal range of the candidate environmental parameter can be calculated, and then the candidate environmental parameter with a deviation degree greater than or equal to a deviation degree threshold can be determined as the target environmental parameter.

[0037] For example, to measure the degree of deviation between the current actual supply data and the optimal range of the candidate environmental parameters, the embodiment of the present application uses the difference between the current actual supply data and the midpoint of the optimal range of the candidate environmental parameters as the numerator; at the same time, the midpoint of the optimal range of the candidate environmental parameters is used as the denominator. By calculating the ratio of the numerator and denominator, a value that can reflect the degree of deviation can be obtained.

[0038] For example, among multiple candidate environmental parameters such as temperature supply, humidity supply, and oxygen supply, if it is determined that the current temperature supply seriously deviates from the optimal range required, and other candidate environmental parameters are close to the optimal range required, the ambient temperature will be used as the target environmental parameter for precise control.

[0039] Step S400: determining target power supply parameters of the environmental monitoring sensor corresponding to the target environmental parameters according to the current environmental conditions in the greenhouse, wherein the target power supply parameters include a dual-voltage power supply parameter matrix; Understandably, the ambient humidity and temperature in a greenhouse can have a certain impact on sensor stability and accuracy. For example, the core component characteristics of most sensors (especially those based on semiconductor or resistor principles, such as thermistors, humidity sensors, pressure sensors, and temperature sensors) vary with temperature. Rising temperature can cause changes in resistance, semiconductor carrier concentration, and reference voltage offset, directly causing the output signal to deviate from its true value (zero drift and sensitivity drift). In high humidity environments, moisture can be absorbed by the sensor housing, packaging materials, or the sensitive element itself. This can cause a decrease in insulation resistance, a change in dielectric constant, material expansion, or hydrolysis, resulting in measurement drift or distortion (particularly affecting capacitive humidity sensors, certain pressure sensors, and resistive sensors).

[0040] Based on the impact of environmental factors on sensor performance, this application proposes setting different supply voltages for the sensor under different environmental conditions. By adjusting the supply voltage in this targeted manner, the adverse effects of environmental factors on sensor performance can be compensated to a certain extent, reducing the probability of sensor instability or inaccuracy due to environmental changes. For example, in environments with high temperature or high humidity, appropriately adjusting the supply voltage can enable the sensor to operate more stably and reduce output signal deviation.

[0041] Furthermore, this application provides a dual-voltage power supply mode, combining high and low voltage, to further increase the flexibility of sensor power control. Depending on the specific conditions within the greenhouse, the sensor can be flexibly powered using either high or low voltage. This dual-voltage power supply mode can better adapt to different environmental conditions, ensuring that the sensor maintains stable and accurate performance in a variety of complex environments.

[0042] In one embodiment, the target environmental parameter includes the ambient temperature, and the environmental monitoring sensor includes a temperature sensor. Step S400: determining the target power supply parameter of the environmental monitoring sensor corresponding to the target environmental parameter according to the current environmental conditions in the greenhouse, including: inputting the current ambient temperature value in the greenhouse into a pre-established correlation model of the power supply voltage and the sensor monitoring accuracy to obtain the main frequency power supply voltage value and the secondary frequency power supply voltage value; generating the dual voltage power supply parameter matrix according to the main frequency power supply voltage value, the secondary frequency power supply voltage value and the preset voltage switching frequency.

[0043] The primary frequency power supply voltage value refers to the voltage value that is used as the primary power supply voltage during a power supply cycle and its power supply duration accounts for the dominant proportion of the overall power supply process. The secondary frequency power supply voltage value refers to the voltage value that is used as the secondary power supply voltage during a power supply cycle and its power supply duration accounts for a secondary proportion of the overall power supply process.

[0044] The supply voltage-sensor accuracy correlation model characterizes the relationship between supply voltage and sensor accuracy at different temperatures. This model was developed through analysis and fitting of extensive experimental data. During the experiment, the accuracy indicators (such as measurement error and precision) of the sensor output were recorded when different supply voltages were applied to the sensor at different temperatures.

[0045] For example, the correlation model may be set to output two power supply voltages, such as 5.0V or 3.3V, to provide a basis for the power supply strategy of the sensor.

[0046] In an embodiment of the present application, for a greenhouse environmental monitoring scenario, the current ambient temperature value in the greenhouse, acquired in real time, is used as a key input parameter and imported into a pre-built model associating power supply voltage with sensor monitoring accuracy. Through the model's computational processing, it is possible to derive a primary frequency power supply voltage value that ensures high accuracy in sensor monitoring results at the current ambient temperature. At the same time, based on two pre-set power supply voltage schemes, once the primary frequency power supply voltage value is determined, the corresponding secondary frequency power supply voltage value can be quickly determined through simple numerical relationships or logical deductions.

[0047] For example, if the current ambient temperature value in the greenhouse is input and the main frequency supply voltage value is 5.0V, the secondary frequency supply voltage value is determined to be 3.3V; if the current ambient temperature value in the greenhouse is input and the main frequency supply voltage value is 3.3V, the secondary frequency supply voltage value is determined to be 5.0V.

[0048] After obtaining the main frequency power supply voltage value and the secondary frequency power supply voltage value based on the current ambient temperature in the greenhouse, the three key parameters of the main frequency power supply voltage value, the secondary frequency power supply voltage value and the preset voltage switching frequency can be integrated; based on the integrated parameters, a dual voltage power supply parameter matrix is ​​constructed according to certain rules and formats.

[0049] The dual-voltage power supply parameter matrix is ​​a computer-readable collection of key parameters for the sensor power supply process. These parameters are presented in matrix form, clarifying the supply voltage that the sensor should use at different time periods and the rules for voltage switching, providing precise guidance for the sensor's dual-voltage power supply operation.

[0050] In one embodiment, the current ambient temperature value in the greenhouse is input into a pre-established correlation model between the supply voltage and the sensor monitoring accuracy to obtain the primary frequency supply voltage value and the secondary frequency supply voltage value, including: When the current ambient temperature of the greenhouse is greater than or equal to the temperature threshold, the temperature sensor is powered by a first power supply voltage at a primary frequency, and the temperature sensor is powered by a second power supply voltage at a secondary frequency, wherein the second power supply voltage is greater than the first power supply voltage; When the current ambient temperature of the greenhouse is lower than the temperature threshold, the temperature sensor is powered by the second power supply voltage at the primary frequency, and the temperature sensor is powered by the first power supply voltage at the secondary frequency.

[0051] Specifically, when the greenhouse's current ambient temperature is greater than or equal to the temperature threshold (high temperature environment), the embodiment of the present application uses a first supply voltage (3.3V) for primary power to the temperature sensor and a second supply voltage (5.0V) for secondary power to the temperature sensor. In high-temperature environments, using a low voltage for primary power can prevent the characteristic drift of sensor sensitive components (such as bridges and oscillators) caused by high temperature and self-heating, thereby ensuring monitoring accuracy. Using a high temperature for secondary power can ensure the anti-interference ability of communication interfaces (such as RS-485 and CAN) during long-distance transmission, thereby maintaining data transmission stability.

[0052] When the greenhouse's current ambient temperature is below the temperature threshold (low-temperature environment), the embodiment of the present application uses the second supply voltage (5.0V) for primary power to supply the temperature sensor, and the first supply voltage (3.3V) for secondary power to supply the temperature sensor. In low-temperature environments, using high voltage for primary power can increase transistor switching speed and saturation current, avoid circuit response lag, and thus improve monitoring accuracy. Using low voltage for secondary power can avoid the effects of high temperatures caused by prolonged high-voltage power supply, which can affect monitoring stability.

[0053] Thus, this application adopts different dual-voltage power supply strategies for different greenhouse ambient temperatures, enabling the sensor to better adapt to various complex environmental conditions. Whether in high or low temperature environments, the sensor can maintain optimal operating conditions by adjusting the supply voltage, improving the adaptability and flexibility of the sensor in the greenhouse environmental monitoring system. Furthermore, this power supply strategy can be adjusted and optimized according to actual needs, facilitating subsequent system upgrades and expansions.

[0054] In one embodiment, the precise control method of a smart greenhouse based on artificial intelligence also includes: correcting the preset voltage switching frequency according to the rate of change of the ambient temperature value to obtain a target voltage switching frequency; wherein, when the rate of change of the ambient temperature value is greater than or equal to the rate of change threshold, increasing the duty cycle of the main frequency power supply voltage; and regenerating the dual voltage power supply parameter matrix according to the main frequency power supply voltage value, the secondary frequency power supply voltage value and the target voltage switching frequency.

[0055] The ambient temperature rate of change reflects how quickly the temperature changes over a given period of time. The preset voltage switching frequency is based on general conditions, but when the ambient temperature fluctuates rapidly, the original switching frequency may not be able to meet the sensor's supply voltage needs in a timely manner. By adjusting the preset voltage switching frequency based on the ambient temperature rate of change, a target voltage switching frequency that better meets actual environmental requirements can be obtained.

[0056] Specifically, when the rate of change of the ambient temperature value reaches or exceeds a pre-set rate of change threshold, this indicates that the ambient temperature is fluctuating violently. Such rapid and drastic environmental changes can have an adverse effect on the sensor's monitoring accuracy, as the sensor may not have enough time to fully adapt to the sudden temperature change, resulting in deviations in the monitoring data. The main frequency supply voltage has been carefully designed and verified to have the ability to ensure the sensor's monitoring accuracy under corresponding environmental conditions. Based on this, when the ambient temperature changes violently, a strategy is adopted to increase the duty cycle of the main frequency supply voltage. The increase in the duty cycle means that the sensor can use the main frequency supply voltage to work for a longer period of time per unit time. In this way, the sensor can be more stably and continuously in a power supply state suitable for the current ambient temperature, thereby giving full play to the advantages of the main frequency supply voltage in ensuring monitoring accuracy, effectively reducing the adverse interference of rapid changes in ambient temperature on the monitoring results, and further improving the accuracy of ambient temperature monitoring.

[0057] For example, the duty cycle adjustment amount is proportional to the portion of the ambient temperature change rate that exceeds the threshold. Assuming the adjustment coefficient is k, the duty cycle adjustment amount D=k×(R−R th ), R is the rate of change of ambient temperature, R th is the preset change rate threshold.

[0058] After adjusting the duty cycle of the main frequency supply voltage, the switching frequency of the target voltage can be obtained; in this way, the dual voltage supply parameter matrix can be regenerated based on the main frequency supply voltage value, the secondary frequency supply voltage value and the target voltage switching frequency, thereby providing the latest data basis for the adjustment strategy.

[0059] In one embodiment, the control system includes a power supply circuit and a voltage switching circuit, and the voltage switching circuit includes an interlock switch component. Figure 4 As shown, Figure 4 This is a schematic diagram of the power supply circuit of the control system in one embodiment of the present application. The solar panel provides 12V voltage, and then the DC-DC converter shown in the figure performs voltage conversion between 5.0V and 3.3V. Figure 5 As shown, Figure 5This is a schematic diagram of the voltage switching circuit of the control system in one embodiment of the present application. By turning one electronic switch on, the other electronic switch can be turned off. When switch K1 is closed and K2 is open, the temperature sensor DS18B20 is powered by a +5V power supply. When switch K2 is closed and K1 is open, the temperature sensor DS18B20 is powered by a +3.3V power supply.

[0060] In one embodiment, after determining the target power supply parameters of the environmental monitoring sensor corresponding to the target environmental parameters according to the current environmental conditions in the greenhouse, it also includes: generating mutually exclusive drive signals according to the dual-voltage power supply parameter matrix; controlling one of the electronic switches in the interlock switch assembly to turn on according to the drive signal so that the power supply circuit supplies power to the temperature sensor according to the target power supply parameters.

[0061] After determining the target power supply parameters for an environmental monitoring sensor (for example, a temperature sensor) corresponding to the target environmental parameters within the greenhouse, this embodiment of the application further generates mutually exclusive drive signals using a dual-voltage power supply parameter matrix. These signals are used to control the conduction of electronic switches in an interlock switch assembly, ensuring that the power supply circuit supplies power to the temperature sensor according to the target power supply parameters. This solution precisely controls the sensor's power supply, ensuring stable and accurate operation in the complex and changing environment of the greenhouse.

[0062] Step S500: Acquire environmental monitoring data of the environmental monitoring sensor under the target power supply parameters, and perform precise control based on the environmental monitoring data so that the environmental monitoring data is dynamically within the optimal range of the target environmental parameters.

[0063] Under target power supply parameters, environmental monitoring sensors (such as temperature sensors) are powered according to a preset power supply strategy, improving the accuracy and stability of environmental parameter monitoring. The environmental monitoring data is then compared with the pre-set target environmental parameter range to assess whether the current environmental conditions meet the requirements. Based on the data analysis results, combined with the actual application scenario and needs, a corresponding control strategy is formulated. For example, when the temperature exceeds the upper limit of the target range, cooling devices (such as fans and air conditioners) are activated; when the humidity falls below the lower limit of the target range, humidification devices (such as humidifiers) are activated. After executing the control operation, changes in the environmental monitoring data are monitored in real time. Based on the feedback, the control strategy and device parameters are adjusted promptly until the environmental monitoring data dynamically falls within the optimal range of the target environmental parameters. In this way, adaptive control of environmental parameters based on precise monitoring ensures accurate and efficient control.

[0064] Based on this, the embodiment of the present application provides an artificial intelligence-based precise control method for smart greenhouses. By constructing a full growth cycle demand model for target crops, candidate environmental parameters are screened out in combination with historical supply data, and then the target environmental parameters that need to be controlled are locked based on the difference between the current environment and the optimal range of the parameters. On this basis, a target power supply strategy containing a dual-voltage power supply parameter matrix is ​​formulated for the sensors corresponding to the target environmental parameters, the power supply voltage is dynamically adjusted, and the environmental monitoring data is accurately obtained, thereby achieving precise control of the greenhouse environment. This solution can effectively improve the accuracy and stability of environmental parameter monitoring and avoid data deviations caused by unreasonable sensor power supply. At the same time, the dynamic optimization control strategy based on crop growth needs can better meet the environmental requirements of crops at different growth stages, improve resource utilization efficiency, reduce energy waste, and ultimately achieve refined management of the crop growth environment in smart greenhouses, helping to improve crop yield and quality.

[0065] like Figure 6 As shown, Figure 6 This is a schematic diagram of the hardware structure of the control system in some embodiments of the present application. The control system provided in the embodiments of the present application includes a memory 1000 and a processor 2000, wherein the memory 1000 is used to store computer-readable instructions, and the processor 2000 is used to call the computer-readable instructions to execute the artificial intelligence-based smart greenhouse precision control method as described above.

[0066] Among them, the processor 2000 is used to provide computing and control capabilities to control the control system to perform corresponding tasks. For example, the control system is controlled to perform the artificial intelligence-based smart greenhouse precision control method in any of the above-mentioned method embodiments, and the method includes: obtaining a full growth cycle demand model of the target crop in the greenhouse; determining the candidate environmental parameters that need to be regulated in the current growth stage based on the full growth cycle demand model and historical supply data; when the number of the candidate environmental parameters is greater than or equal to two, determining the target environmental parameters that need to be precisely regulated based on the difference between the current environmental conditions in the greenhouse and the optimal range of the candidate environmental parameters; determining the target power supply parameters of the environmental monitoring sensor corresponding to the target environmental parameters based on the current environmental conditions in the greenhouse, the target power supply parameters include a dual-voltage power supply parameter matrix; obtaining the environmental monitoring data of the environmental monitoring sensor under the target power supply parameters, and performing precise control based on the environmental monitoring data so that the environmental monitoring data is dynamically within the optimal range of the target environmental parameters.

[0067] Processor 2000 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), a hardware chip, or any combination thereof; it may also be a digital signal processing (DSP), an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or any combination thereof. The PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0068] Memory 1000, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as the program instructions / modules corresponding to the AI-based smart greenhouse precision control method in the embodiments of the present application. Processor 2000 can implement the AI-based smart greenhouse precision control method in any of the aforementioned method embodiments by executing the non-transitory software programs, instructions, and modules stored in memory 1000.

[0069] Specifically, the memory 1000 may include a volatile memory (VM), such as a random access memory (RAM); the memory 1000 may also include a non-volatile memory (NVM), such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD) or other non-transitory solid-state storage device; the memory 1000 may also include a combination of the above types of memory.

[0070] To sum up, the control system of the present application adopts the technical solution of any one of the above-mentioned embodiments of the intelligent greenhouse precision control method based on artificial intelligence. Therefore, it has at least the beneficial effects brought by the technical solution of the above-mentioned embodiments, which will not be described one by one here.

[0071] The present application also provides a computer-readable storage medium, such as a memory device including program code. The program code can be executed by a processor to implement the artificial intelligence-based smart greenhouse precision control method described in the above embodiment. For example, the computer-readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CDROM), a magnetic tape, a floppy disk, or an optical data storage device.

[0072] The present application also provides a computer program product comprising one or more program codes stored in a computer-readable storage medium. A processor of the early warning system reads the program code from the computer-readable storage medium and executes the program code to perform the steps of the artificial intelligence-based smart greenhouse precision control method provided in the above embodiment.

[0073] Those skilled in the art will understand that all or part of the steps of implementing the above embodiments can be completed by hardware, or by hardware related to program code, and the program can be stored in a computer-readable storage medium. The above-mentioned storage medium can be a read-only memory, a disk or an optical disk, etc.

[0074] It should be noted that the device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of this embodiment.

[0075] Through the description of the above embodiments, it is clear to those skilled in the art that each embodiment can be implemented by means of software plus a general hardware platform, or of course by hardware. It is understood by those skilled in the art that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0076] The above description is only a preferred embodiment of the present invention and does not limit the patent scope of the present invention. All equivalent structural transformations made by using the contents of the present invention description and drawings under the inventive concept of the present invention, or direct / indirect application in other related technical fields are included in the patent protection scope of the present invention.

Claims

1. A smart greenhouse precision control method based on artificial intelligence, characterized in that: Applied to a control system, the method comprises: Obtain the full growth cycle demand model of the target crops in the greenhouse; Determining candidate environmental parameters that need to be regulated during the current growth phase based on the full growth cycle demand model and historical supply data; When the number of the candidate environmental parameters is greater than or equal to two, determining the target environmental parameter that needs to be precisely controlled according to the difference between the current environmental conditions in the greenhouse and the optimal range of the candidate environmental parameters; Determine the target power supply parameters of the environmental monitoring sensor corresponding to the target environmental parameter according to the current environmental conditions in the greenhouse, wherein the target power supply parameters include a dual-voltage power supply parameter matrix; Acquire environmental monitoring data of the environmental monitoring sensor under the target power supply parameters, and perform precise regulation based on the environmental monitoring data so that the environmental monitoring data is dynamically within the optimal range of the target environmental parameters.

2. The method for precise control of smart greenhouses based on artificial intelligence according to claim 1, characterized in that: The full growth cycle demand model includes a temperature demand sub-model, a humidity demand sub-model, a light demand sub-model, and a trace element demand sub-model. The candidate environmental parameters that need to be regulated in the current growth stage are determined based on the full growth cycle demand model and historical supply data, including: Determining a historical supply matching degree of each environmental parameter of the target crop according to the historical supply data of each environmental parameter of the target crop and the corresponding demand sub-model; An environmental parameter whose historical supply matching degree is less than or equal to the matching degree threshold is determined as a candidate environmental parameter.

3. The method for precise control of smart greenhouses based on artificial intelligence according to claim 2, characterized in that: The determining the historical supply matching degree of each environmental parameter of the target crop according to the historical supply data of each environmental parameter of the target crop and the corresponding demand sub-model includes: For each environmental parameter, a time series historical supply data matrix is ​​constructed, where the matrix elements include supply values ​​sampled at fixed time intervals within a preset historical period; Input the historical supply data matrix into the corresponding demand sub-model to generate a theoretical demand value sequence at each time point; Calculate the difference between the historical supply value and the theoretical demand value at each time point to obtain the supply deviation sequence; Perform a sliding window analysis on the supply deviation sequence to calculate the average supply deviation rate within each window, where the average supply deviation rate is the average value of the ratio of the supply deviation value to the theoretical demand value at each time point within the window; The historical supply matching degree of each environmental parameter of the target crop is determined according to the average supply deviation rate.

4. The method for precise control of smart greenhouses based on artificial intelligence according to claim 1, characterized in that: The method of determining the target environmental parameters that need to be precisely controlled based on the difference between the current environmental conditions in the greenhouse and the optimal range of the candidate environmental parameters includes: For each candidate environmental parameter, the actual supply data is calculated to determine the deviation between the actual supply data and the optimal range of the candidate environmental parameter. The candidate environmental parameters whose deviation degree is greater than or equal to the deviation degree threshold are determined as target environmental parameters.

5. The method for precise control of smart greenhouses based on artificial intelligence according to claim 1, characterized in that: The target environmental parameter includes an ambient temperature, the environmental monitoring sensor includes a temperature sensor, and determining the target power supply parameter of the environmental monitoring sensor corresponding to the target environmental parameter according to the current environmental conditions in the greenhouse includes: The current ambient temperature value in the greenhouse is input into the pre-established correlation model between the power supply voltage and the sensor monitoring accuracy to obtain the main frequency power supply voltage value and the secondary frequency power supply voltage value; The dual-voltage power supply parameter matrix is ​​generated according to the primary frequency power supply voltage value, the secondary frequency power supply voltage value, and a preset voltage switching frequency.

6. The method for precise control of smart greenhouses based on artificial intelligence according to claim 5, characterized in that: Input the current ambient temperature value in the greenhouse into the pre-established correlation model between the power supply voltage and the sensor monitoring accuracy to obtain the main frequency power supply voltage value and the secondary frequency power supply voltage value, including: When the current ambient temperature of the greenhouse is greater than or equal to the temperature threshold, the temperature sensor is powered by a first power supply voltage at a primary frequency, and the temperature sensor is powered by a second power supply voltage at a secondary frequency, wherein the second power supply voltage is greater than the first power supply voltage; When the current ambient temperature of the greenhouse is lower than the temperature threshold, the temperature sensor is powered by the second power supply voltage at a primary frequency, and the temperature sensor is powered by the first power supply voltage at a secondary frequency.

7. The method for precise control of smart greenhouses based on artificial intelligence according to claim 5, characterized in that: The method further comprises: Correcting the preset voltage switching frequency according to the rate of change of the ambient temperature value to obtain a target voltage switching frequency; wherein, when the rate of change of the ambient temperature value is greater than or equal to the rate of change threshold, increasing the duty cycle of the main frequency power supply voltage; The dual-voltage power supply parameter matrix is ​​regenerated according to the primary frequency power supply voltage value, the secondary frequency power supply voltage value and the target voltage switching frequency.

8. The method for precise control of smart greenhouses based on artificial intelligence according to claim 1, characterized in that: The control system includes a power supply circuit and a voltage switching circuit. The voltage switching circuit includes an interlock switch component. After determining the target power supply parameter of the environmental monitoring sensor corresponding to the target environmental parameter according to the current environmental conditions in the greenhouse, the control system further includes: generating mutually exclusive driving signals according to the dual voltage power supply parameter matrix; One of the electronic switches in the interlock switch assembly is controlled to be turned on according to the driving signal so that the power supply circuit supplies power to the temperature sensor according to the target power supply parameter.

9. A control system, characterized in that: include: A memory and a processor, wherein the memory is used to store program codes; The processor is configured to call the program code to execute the method according to any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images