A temperature and light control method for intelligent plant cultivation device

Abstract

The application relates to the technical field of plant culture, and discloses a temperature and illumination control method for an intelligent plant culture device, which comprises the following steps: S1, inputting plant variety information and presetting basic maintenance information of an environment in each stage; S2, regularly sampling rhizosphere soil and non-rhizosphere soil, comparing sampling results with plant standard information, and performing nutrient management information; S3, generating illumination information according to the basic maintenance information; S4, generating temperature information according to the basic maintenance information; and S5, generating feedback adjustment information according to the nutrient management information, wherein the feedback adjustment information comprises temperature adjustment information and illumination adjustment information. Based on intelligent optimization of plant variety characteristics and growth stages, the application realizes whole-process, fine management and self-adaptive adjustment of a plant growth environment through monitoring of rhizosphere soil and non-rhizosphere soil and combination of illumination and temperature control.

Description

Technical Field

[0001] This invention relates to the field of plant cultivation technology, and more specifically, to a method for temperature and light control in intelligent plant cultivation devices. Background Technology

[0002] As modern agriculture develops towards intelligence and precision, the regulation of plant growth environment is gradually shifting from traditional experience-based management to data-driven intelligent control. In actual production, environmental factors such as light, temperature, and soil nutrients have a decisive impact on plant growth and development. Real-time perception and dynamic adjustment of these factors are key to improving crop yield and quality.

[0003] Currently, some systems collect soil and environmental parameters through sensors and combine them with automatic control equipment for simple environmental regulation. However, they lack personalized regulation mechanisms for different plant varieties and growth stages. Most systems adopt a uniform control strategy, failing to fully consider the specific needs of different crops and their growth stages for light, temperature, and nutrients, resulting in low regulation accuracy. Soil nutrient management is extensive and lacks a closed-loop feedback mechanism. Traditional fertilization methods rely heavily on manual experience, lacking quantitative assessment and dynamic adjustment of key nutrients such as nitrogen (N), phosphorus (P), and potassium (K), easily leading to fertilizer waste or insufficient supply, affecting crop absorption efficiency.

[0004] Furthermore, the rhizosphere is the core zone for nutrient absorption, and its nutrient status differs significantly from that of non-rhizosphere soil. Current technologies often treat the entire soil as a homogeneous body, failing to achieve differentiated monitoring and regulation of the two soil types, thus limiting further improvements in nutrient utilization efficiency.

[0005] Furthermore, environmental regulation and soil nutrient regulation are disconnected and lack a synergistic mechanism. Most systems separate light and temperature control from soil management, lack a unified data integration platform and feedback regulation mechanism, making it difficult to achieve dynamic matching between the external environment and internal nutrient supply.

[0006] Therefore, there is an urgent need for a temperature and light control method for intelligent plant cultivation devices that can comprehensively consider plant variety characteristics, growth stages, rhizosphere and non-rhizosphere soil conditions, and environmental parameters, in order to achieve precise perception and closed-loop optimization of the entire plant growth process, thereby improving resource utilization efficiency and promoting the development of agricultural production towards intelligence and greening. Summary of the Invention

[0007] In view of this, the present invention proposes a temperature and light control method for intelligent plant cultivation devices, aiming to solve the technical problems of the current disconnect between environmental regulation and soil nutrient regulation, the lack of a synergistic mechanism, the separation of light and temperature control from soil management in most systems, and the lack of a unified data integration platform and feedback regulation mechanism.

[0008] In one aspect, the present invention proposes a method for temperature and light control in an intelligent plant cultivation device, comprising:

[0009] Step S1: Input the plant variety information and preset the basic environmental maintenance information for each stage;

[0010] Step S2: Regularly sample the rhizosphere soil and non-rhizosphere soil, compare the sampling results with the plant standard information, and provide nutrient management information.

[0011] Step S3: Generate illumination information based on the basic maintenance information;

[0012] Step S4: Generate temperature information based on the basic maintenance information;

[0013] Step S5: Generate feedback adjustment information based on the nutrient management information, including temperature adjustment information and light adjustment information.

[0014] Preferably, step S1 includes: storing plant variety data, with each plant variety corresponding to multiple growth stages including budding period, growth period, flowering period, and fruiting period;

[0015] For each stage, optimal light intensity, temperature range, humidity, and rhizosphere soil nutrient standards are preset.

[0016] Preferably, step S2 includes acquiring root images at each sampling time and determining rhizosphere soil and non-rhizosphere soil, including:

[0017] The root system image is captured by a camera, and denoising, grayscale conversion and edge detection are performed. Each independent branch is marked and feature extraction is performed based on connected component analysis. The features include the number of branches, the coverage ratio and the root system length. The coverage ratio is obtained by comparing the number of root system pixels with the total number of pixels, and the root system length is calculated by the path integral of edge detection.

[0018] The endpoint of each branch is critically located to determine the boundary between rhizosphere and non-rhizosphere soil. By applying a distance transform to the binarized root image, the distance from the endpoint of each branch to the nearest background pixel is found and calculated using the following formula:

[0019] D(p) = min q∈B pq2

[0020] Where D(p) represents the distance from p to set B; p is the root pixel; B is the set of background pixels; q∈B: represents an element q in set B, where q is also a point in space; ||pq||2 represents the Euclidean distance between point p and point q, where:

[0021]

[0022] Where p1 and q1 are coordinates in the first dimension, p2 and q2 are coordinates in the second dimension, and p3 and q3 are coordinates in the third dimension;

[0023] A marginal threshold d is preset based on the influence gradient of the coverage area ratio. rhizo Using the marginal threshold d rhizo Thresholding is performed on the distance-transformed image to create a mask. Pixels that meet the condition that the distance is less than or equal to the threshold are marked as foreground (root zone soil), and the rest are marked as background (non-root zone soil). For the generated binary image mask, a contour detection algorithm is used to find the contours of all connected regions.

[0024] Preferably, step S2 includes setting a marginal threshold d based on the influence gradient of the coverage area ratio. rhizo It also includes:

[0025] The RCR root coverage ratio is calculated using the following formula:

[0026]

[0027] Where RCR∈[0,1]; A root It is the area of ​​the root system pixels identified per unit area in the image; A grid It is the total area of ​​the grid cells;

[0028] As the root system coverage area increases, the range of influence of the rhizosphere effect also expands accordingly, therefore d rhizo It varies with the coverage ratio;

[0029] d rhizo Including a maximum threshold d max and a minimum threshold d min , where the maximum threshold d max The minimum threshold d represents the rhizosphere influence range of the densely rooted area. min To determine the rhizosphere influence range in the sparse root zone, the RCR is mapped to [d]. min d max The function setting d in the interval rhizo It is obtained by calculation using the following formula:

[0030]

[0031] Here, β controls the steepness of the curve, and θ is the RCR value corresponding to the midpoint of the curve.

[0032] Preferably, step S5 includes comparing the detection results in the rhizosphere soil with the standard values ​​in the plant database to generate a nutrient deviation vector, including:

[0033] ΔN=N measured -N target ;

[0034] ΔP=P measured -P target ;

[0035] ΔK=K measured -K target ;

[0036] Where, N measured The nitrogen content (N) in the soil is obtained from actual measurements. target It is a target nitrogen content preset in a plant information database based on plant species, growth stage, and environmental conditions; P measured This refers to the actual measured phosphorus content in the soil, P. target It is a target phosphorus content preset in a plant information database based on plant species, growth stage, and environmental conditions; K measured The potassium content (K) in the soil is obtained through actual measurement. target It is a target potassium content preset in the plant information database based on plant species, growth stage and environmental conditions.

[0037] Preferably, step S5 further includes a nutrient and light response model, comprising:

[0038] I opt =I base +u N ·ΔN+u P ·ΔP+u K ·ΔK;

[0039] Among them, I opt It is the optimal light intensity; I base This is the base light intensity, set according to the plant species and stage; u N u P u K It is the light experience coefficient, which represents the weight of each nutrient's influence on temperature requirements.

[0040] Preferably, step S5 further includes a nutrient and temperature response model, comprising:

[0041] T opt =T base +m N ·ΔN+m P ·ΔP+m K ·ΔK;

[0042] Among them, T opt It is the optimal cultivation temperature; T base This is the base temperature, set according to the plant species and stage; mN m P m K It is a temperature empirical coefficient, representing the weight of each nutrient's influence on temperature requirements.

[0043] Preferably, step S5 further includes using a PID controller to construct a feedback system for light intensity and temperature to achieve plant control.

[0044] Compared with existing technologies, the beneficial effects of this invention are that, through the collaborative work of multiple modules, it achieves precise perception, dynamic regulation, and closed-loop optimization of the plant growth environment, significantly improving crop growth efficiency and resource utilization. Specifically, relying on a plant information database, it presets standard environmental parameters and nutrient requirements for different varieties and growth stages, providing a basis for subsequent control. By sampling and analyzing rhizosphere and non-rhizosphere soil separately, and comparing them with standard values ​​to generate a nutrient deviation vector, it achieves quantitative assessment and environmental feedback regulation of key nutrients such as nitrogen, phosphorus, and potassium. This establishes a dynamic synergistic relationship between external environmental regulation and soil nutrient supply, thereby maintaining the optimal nutrient balance required for plant growth and ensuring full utilization of soil nutrients. Attached Figure Description

[0045] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0046] Figure 1 A flowchart of a temperature and light control method for intelligent plant cultivation provided in an embodiment of the present invention. Detailed Implementation

[0047] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the disclosure to those skilled in the art. It should be noted that, unless otherwise specified, embodiments and features in the embodiments of the present invention can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0048] In some embodiments of this application, see Figure 1 As shown, a method for temperature and light control in an intelligent plant cultivation device includes:

[0049] Step S1: Input the plant variety information and preset the basic environmental maintenance information for each stage;

[0050] Step S2: Regularly sample the rhizosphere soil and non-rhizosphere soil, compare the sampling results with the plant standard information, and provide nutrient management information.

[0051] Step S3: Generate lighting information based on basic maintenance information;

[0052] Step S4: Generate temperature information based on basic maintenance information;

[0053] Step S5 includes generating feedback adjustment information based on nutrient management information, including temperature adjustment information and light adjustment information.

[0054] In some embodiments of this application, step S1 includes: storing plant variety data, with each plant variety corresponding to multiple growth stages including budding period, growth period, flowering period, and fruiting period;

[0055] For each stage, presets are made for optimal light intensity, temperature range, humidity, and rhizosphere soil nutrient standards based on plant type and growth stage.

[0056] In some embodiments of this application, step S2 includes acquiring root images at each sampling time and determining rhizosphere soil and non-rhizosphere soil, including:

[0057] The root system images are captured by a camera, and then denoised, grayscaled, and edge detected. Each independent branch is labeled and its features are extracted based on connected component analysis. The features include the number of branches, the coverage ratio, and the root system length. The coverage ratio is obtained by comparing the number of root system pixels with the total number of pixels, and the root system length is calculated by the path integral of the edge detection.

[0058] The endpoint of each branch is critically located to determine the boundary between rhizosphere and non-rhizosphere soil. By applying a distance transform to the binarized root image, the distance from the endpoint of each branch to the nearest background pixel is found and calculated using the following formula:

[0059] D(p) = min q∈B pq2

[0060] Where D(p) represents the distance from p to set B; p is the root pixel; B is the set of background pixels; q∈B: represents an element q in set B, where q is also a point in space; ||pq||2 represents the Euclidean distance between point p and point q, where:

[0061]

[0062] Where p1 and q1 are coordinates in the first dimension, p2 and q2 are coordinates in the second dimension, and p3 and q3 are coordinates in the third dimension;

[0063] A marginal threshold d is preset based on the influence gradient of the coverage area ratio. rhizo Using the marginal threshold d rhizo Thresholding is performed on the distance-transformed image to create a mask. Pixels that meet the condition that the distance is less than or equal to the threshold are marked as foreground (root zone soil), and the rest are marked as background (non-root zone soil). For the generated binary image mask, a contour detection algorithm is used to find the contours of all connected regions.

[0064] In some embodiments of this application, step S2 includes setting a marginal threshold d based on the influence gradient of the coverage area ratio. rhizo It also includes:

[0065] The RCR root coverage ratio is calculated using the following formula:

[0066]

[0067] Where RCR∈[0,1]; A root It is the area of ​​the root system pixels identified per unit area in the image; A grid It is the total area of ​​the grid cells;

[0068] As the root system coverage area increases, the range of influence of the rhizosphere effect also expands accordingly, therefore d rhizo It varies with the coverage ratio;

[0069] d rhizo Including a maximum threshold d max and a minimum threshold d min , where the maximum threshold d max The minimum threshold d represents the rhizosphere influence range of the densely rooted area. min To determine the rhizosphere influence range in the sparse root zone, the RCR is mapped to [d]. min d max The function setting d in the interval rhizo It is obtained by calculation using the following formula:

[0070]

[0071] Here, β controls the steepness of the curve, and θ is the RCR value corresponding to the midpoint of the curve.

[0072] In some embodiments of this application, step S5, which includes comparing the detection results in the rhizosphere soil with standard values ​​in a plant database to generate a nutrient deviation vector, includes:

[0073] ΔN=N measured -N target ;

[0074] ΔP=Pmeasured -P target ;

[0075] ΔK=K measured -K target ;

[0076] Where, N measured The nitrogen content (N) in the soil is obtained from actual measurements. target It is a target nitrogen content preset in a plant information database based on plant species, growth stage, and environmental conditions; P measured This refers to the actual measured phosphorus content in the soil, P. target It is a target phosphorus content preset in a plant information database based on plant species, growth stage, and environmental conditions; K measured The potassium content (K) in the soil is obtained through actual measurement. target It is a target potassium content preset in the plant information database based on plant species, growth stage and environmental conditions.

[0077] In some embodiments of this application, step S5 further includes a nutrient and light response model, comprising:

[0078] I opt =I base +u N ·ΔN+u P ·ΔP+u K ·ΔK;

[0079] Among them, I opt It is the optimal light intensity; I base This is the base light intensity, set according to the plant species and stage; u N u P u K It is the light experience coefficient, which represents the weight of each nutrient's influence on temperature requirements.

[0080] In some embodiments of this application, step S5 further includes a nutrient and temperature response model, comprising:

[0081] T opt =T base +m N ·ΔN+m P ·ΔP+m K ·ΔK;

[0082] Among them, T opt It is the optimal cultivation temperature; T base This is the base temperature, set according to the plant species and stage; m N m P m K It is a temperature empirical coefficient, representing the weight of each nutrient's influence on temperature requirements.

[0083] Specifically, an example is given in the practical application case of this application:

[0084] Light and temperature control during tomato flowering period

[0085] Plant variety: Tomato

[0086] Growth stage: Flowering period

[0087] Nutrient test results:

[0088] N = 0.25 g / kg (standard value is 0.3 g / kg) → Nitrogen deficiency

[0089] P = 0.1 g / kg (standard value is 0.12 g / kg) → Phosphorus deficiency

[0090] K = 0.2 g / kg (standard value is 0.2 g / kg) → Normal

[0091] It is understandable that in a tomato growing environment, the detected nitrogen content in the current soil is 0.25 g / kg, while according to the plant information database, the ideal nitrogen content for tomatoes at this growth stage should be 0.3 g / kg. Therefore:

[0092] ΔN = 0.25 - 0.3 = -0.05

[0093] This means that the current nitrogen content in the soil is lower than the target value, which is then calculated using optimal cultivation methods:

[0094] Optimization and regulation strategies:

[0095] Increase the light intensity to Iopt = 30000 lux.

[0096] It is understandable that increasing light intensity is necessary because sufficient nitrogen helps photosynthesis, and increasing light intensity promotes the plant's utilization of existing nitrogen.

[0097] Increase the root zone temperature to Topt = 23.5℃.

[0098] Understandably, adjusting the temperature, based on the nitrogen-temperature response model, increases the root zone temperature to enhance the plant's ability to absorb nitrogen.

[0099] In some embodiments of this application, step S5 includes using a PID controller to construct a feedback system for light intensity and temperature to achieve plant control.

[0100] Specifically, the following is a code example of control flow implementation using light intensity as an example:

[0101] #Illumination PID Control

[0102] while True:measured_light=read_light_sensor()

[0103] error=target_light-measured_light

[0104] #PID calculation proportional = Kp * error

[0105] integral+=Ki*error*dt derivative=Kd*(error-last_error) / dt

[0106] output=proportional+integral+derivative

[0107] # Output to an actuator (e.g., PWM driving an LED)

[0108] set_light_intensity(output)

[0109] last_error = error sleep(dt)

[0110] Compared with existing technologies, the beneficial effects of this invention are that, through the collaborative work of multiple modules, it achieves precise perception, dynamic regulation, and closed-loop optimization of the plant growth environment, significantly improving crop growth efficiency and resource utilization. Specifically, relying on a plant information database, it presets standard environmental parameters and nutrient requirements for different varieties and growth stages, providing a basis for subsequent control.

[0111] By sampling and analyzing rhizosphere and non-rhizosphere soils separately and comparing them with standard values ​​to generate nutrient deviation vectors, quantitative assessment of key nutrients such as nitrogen, phosphorus, and potassium and feedback regulation of the environment are achieved. This enables a dynamic synergistic relationship between external environmental regulation and soil nutrient supply, thereby maintaining the optimal nutrient balance required for plant growth and ensuring full utilization of soil nutrients.

[0112] Specifically, the light sensor in this application can be either BH1750 or TSL2561 for real-time detection of the current light intensity. The temperature sensor can be either DS18B20 or PT100 for detecting the root zone and canopy temperature. The main control unit can be a microcontroller or an embedded system STM32 or Raspberry Pi running a PID control algorithm. The actuator can be an LED dimmable lighting system: adjusting brightness and color temperature according to the PID output signal. A Peltier temperature control module, heating film, or cooling fan: adjusting temperature according to PID instructions. The communication interface uses protocols such as CAN bus, I2C, and Modbus to support data interaction between the sensor and the actuator. It is understood that the above-described temperature and light control methods for intelligent plant cultivation devices have the same beneficial effects, and will not be elaborated further here.

[0113] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program goods. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program goods embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0114] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program goods according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0115] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0116] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0117] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the protection scope of the claims of the present invention.

Claims

1. A method for temperature and light control in an intelligent plant cultivation device, characterized in that, include: Step S1: Input the plant variety information and preset the basic environmental maintenance information for each stage; Step S2: Regularly sample the rhizosphere soil and non-rhizosphere soil, compare the sampling results with the plant standard information, and provide nutrient management information; Step S3: Generate illumination information based on the basic maintenance information; Step S4: Generate temperature information based on the basic maintenance information; Step S5: Generate feedback adjustment information based on the nutrient management information, the feedback adjustment information including temperature adjustment information and light adjustment information; Step S2 includes acquiring root images at each sampling time and determining rhizosphere soil and non-rhizosphere soil, including: The root system image is captured by a camera, and denoising, grayscale conversion and edge detection are performed. Each independent branch is marked and feature extraction is performed based on connected component analysis. The features include the number of branches, the coverage ratio and the root system length. The coverage ratio is obtained by comparing the number of root system pixels with the total number of pixels, and the root system length is calculated by the path integral of edge detection. The endpoint of each branch is critically located to determine the boundary between rhizosphere and non-rhizosphere soil. By applying a distance transform to the binarized root image, the distance from the endpoint of each branch to the nearest background pixel is found and calculated using the following formula: ； in, This represents the distance from p to set B; p is the root pixel; B is the set of background pixels; q∈B: represents an element q in set B, where q is also a point in space; Let p represent the Euclidean distance between points p and q, where: ； in, and These are the coordinates in the first dimension. and These are the coordinates in the second dimension. and These are the coordinates in the third dimension; A marginal threshold d is preset based on the influence gradient of the coverage area ratio. rhizo Using the marginal threshold d rhizo Thresholding is performed on the distance-transformed image to create a mask. Pixels that meet the condition that the distance is less than or equal to the threshold are marked as foreground (root zone soil), and the rest are marked as background (non-root zone soil). For the generated binary image mask, a contour detection algorithm is used to find the contours of all connected regions.

2. The temperature and light control method for an intelligent plant cultivation device according to claim 1, characterized in that, Step S1 includes: storing plant variety data, with each plant variety corresponding to multiple growth stages including budding period, growth period, flowering period, and fruiting period; For each stage, optimal light intensity, temperature range, humidity, and rhizosphere soil nutrient standards are preset.

3. The temperature and light control method for an intelligent plant cultivation device according to claim 1, characterized in that, Step S2, This includes setting a marginal threshold d based on the influence gradient of the coverage area ratio. rhizo It also includes: The RCR root coverage ratio is calculated using the following formula: ； Where RCR∈[0,1]; It is the area of ​​the root system pixels identified per unit area in the image; It is the total area of ​​the grid cells; As the root system coverage area increases, the range of influence of the rhizosphere effect also expands accordingly, therefore d rhizo It varies with the coverage ratio; d rhizo Including a maximum threshold d max and a minimum threshold d min , where the maximum threshold d max The minimum threshold d represents the rhizosphere influence range of the densely rooted area. min To determine the rhizosphere influence range in the sparse root zone, the RCR is mapped to [d]. min d max The function setting d in the interval rhizo It is obtained by calculation using the following formula: ； Here, β controls the steepness of the curve, and θ is the RCR value corresponding to the midpoint of the curve.

4. The temperature and light control method for an intelligent plant cultivation device according to claim 1, characterized in that, Step S5 further includes comparing the detection results in the rhizosphere soil with the standard values ​​in the plant information database to generate a nutrient deviation vector, including: ΔN=N measured −N target ; ΔP=P measured −P target ; ΔK=K measured −K target； Where, N measured The nitrogen content (N) in the soil is obtained from actual measurements. target It is a target nitrogen content preset in a plant information database based on plant species, growth stage, and environmental conditions; P measured This refers to the actual measured phosphorus content in the soil, P. target It is a target phosphorus content preset in a plant information database based on plant species, growth stage, and environmental conditions; K measured The potassium content (K) in the soil is obtained through actual measurement. target It is a target potassium content preset in the plant information database based on plant species, growth stage and environmental conditions.

5. The temperature and light control method for an intelligent plant cultivation device according to claim 4, characterized in that, Step S5 further includes a nutrient and light response model, comprising: ； in, It is the optimal light intensity; This is the basic light intensity, set according to the plant species and stage; , , It is the light experience coefficient, which represents the weight of each nutrient's influence on temperature requirements.

6. The temperature and light control method for an intelligent plant cultivation device according to claim 4, characterized in that, Step S5 further includes a nutrient and temperature response model, including: ； in, It is the optimal cultivation temperature; This is the base temperature, set according to the plant species and stage; , , It is a temperature empirical coefficient, representing the weight of each nutrient's influence on temperature requirements.

7. The temperature and light control method for an intelligent plant cultivation device according to claim 1, characterized in that, Step S5 further includes using a PID controller to construct a feedback system for light intensity and temperature to achieve plant control.

Images