Intelligent drip irrigation method and system for growing dendrobium seedlings in greenhouse

Abstract

The present invention provides a method and system for intelligent drip irrigation of dendrobium seedlings in a greenhouse, which relates to the field of intelligent drip irrigation technology. The method comprises the following steps: collecting multiple sets of historical data from the dendrobium seedling greenhouse; using temperature, wind speed, and dendrobium growth stage data as a training set and corresponding water requirements as labels, and establishing a dendrobium water demand prediction model based on a deep learning algorithm; collecting temperature, wind speed, and dendrobium growth stage data in the greenhouse in real time, inputting the data into the model to obtain a predicted dendrobium water demand, and correcting the predicted dendrobium water demand using soil moisture data and light intensity data to obtain a comprehensive water demand index; calculating the drip irrigation interval and automatically adjusting the drip irrigation time, and increasing the drip irrigation amount when the comprehensive water demand index exceeds a preset threshold. The present invention dynamically adjusts the drip irrigation interval and drip irrigation amount to ensure that the dendrobium obtains an appropriate water supply under different growth stages and environmental changes, thereby improving water use efficiency and reducing manual management costs and labor intensity.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent drip irrigation, and in particular to an intelligent drip irrigation method and system for growing dendrobium seedlings in a greenhouse. Background Art

[0002] In modern agriculture and horticulture, Dendrobium officinale, a highly valuable herbal and ornamental plant, requires very strict water management during its cultivation and seedling raising. Traditional drip irrigation methods often rely on manual experience to adjust irrigation frequency and water volume. This method is not only time-consuming and labor-intensive, but also leads to water waste and uneven irrigation. In a greenhouse environment, multiple factors such as temperature, humidity, and light can affect the growth of Dendrobium officinale, and simple manual adjustments are difficult to meet its changing growth needs. In addition, the water requirements of Dendrobium officinale vary at different growth stages, making it difficult to accurately determine the optimal irrigation timing and water volume, resulting in uneven growth and even affecting its quality.

[0003] Although some existing smart drip irrigation systems have begun to use sensors to monitor environmental parameters and soil moisture, these systems are usually based on simple threshold control and lack the ability to comprehensively consider and dynamically adjust multiple growth factors. For example, these systems may decide whether to start irrigation based on data from soil moisture sensors, but they cannot accurately adjust based on multiple variables such as real-time temperature, wind speed, and the growth stage of Dendrobium. This single-factor adjustment method is still difficult to meet the complex growth needs of Dendrobium, and may lead to over-irrigation or under-irrigation, affecting the growth health and final yield of Dendrobium. Therefore, there is an urgent need for an intelligent drip irrigation system that can comprehensively consider multiple environmental factors and plant growth status to more accurately meet the water needs of Dendrobium at different growth stages.

[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art. Summary of the Invention

[0005] The object of the present invention is to provide a method and system for intelligent drip irrigation of dendrobium greenhouse seedlings to solve the problems raised in the above background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] An intelligent drip irrigation method for growing dendrobium seedlings in a greenhouse, comprising the following steps:

[0008] Step 1: Use soil moisture sensors, temperature sensors, light intensity sensors, wind speed sensors, and plant growth status sensors to collect multiple sets of historical data from the Dendrobium seedling greenhouse. Each set of historical data includes temperature, wind speed, Dendrobium growth stage data, and the corresponding Dendrobium water requirement.

[0009] Step 2: Using greenhouse temperature, wind speed, and Dendrobium growth stage data as a training set and the corresponding water requirements as labels, a Dendrobium water requirement prediction model was established based on a deep learning algorithm. The model was trained to obtain a trained Dendrobium water requirement prediction model.

[0010] Step 3: Use sensors to collect real-time data on greenhouse temperature, wind speed, and Dendrobium growth stage, and input them into the water demand prediction model to obtain the model's output of the predicted Dendrobium water demand. The predicted plant water demand is then corrected using the collected soil moisture and light intensity data to obtain a comprehensive water demand index.

[0011] Step 4: Based on the obtained comprehensive water demand index, the drip irrigation interval is calculated using a dynamic adjustment formula. According to the calculated drip irrigation interval, the system automatically adjusts the drip irrigation time, and when the comprehensive water demand index is higher than the preset water demand threshold, the system will increase the drip irrigation water volume.

[0012] Furthermore, soil moisture sensors, temperature sensors, light intensity sensors, wind speed sensors, and plant growth status sensors are installed in different areas of the greenhouse, specifically including:

[0013] In the greenhouse, sensors are installed according to the dendrobium planting layout and environmental characteristics. The soil moisture sensor is installed near the plant roots, the temperature sensor is installed in the center of the greenhouse to avoid the influence of local heat sources, the light intensity sensor is installed in a position that can represent the lighting conditions of the entire greenhouse, and the wind speed sensor is installed at the ventilation position in the greenhouse.

[0014] The water requirement of Dendrobium officinale should be obtained based on historical irrigation data;

[0015] The growth stages of Dendrobium are mainly divided into: seed stage, seedling stage, growth period, flowering stage, fruiting stage and aging stage.

[0016] Furthermore, for the sensor data, ensure that the data format of all sensor outputs is unified, and the data format includes timestamp, sensor type, and reading value, and establish a data storage and backup mechanism in the system to ensure that the collected data will not be lost due to system failure, and the data is regularly backed up to a secure storage medium.

[0017] Furthermore, the data from each sensor is pre-processed to ensure data quality, specifically including:

[0018] Remove data outliers: Calculate the standard deviation of the data and set 3 times the standard deviation as the threshold. Data points outside this range are considered outliers.

[0019] The formula for calculating the standard deviation of the data is:

[0020]

[0021] Where σ is the standard deviation, μ is the total number of data points, and x i is the i-th data point, μ is the mean of the data;

[0022] The formula for calculating the mean of the data is:

[0023]

[0024] Where μ is the mean of the data, H is the total number of data points, and x i is the i-th data point;

[0025] Data interpolation: For time series data, use linear interpolation to fill missing values: Assuming that the data changes linearly between two known points, the missing values are estimated by calculating the linear relationship between the two points.

[0026] Furthermore, the process of establishing a dendrobium water demand prediction model based on a deep learning algorithm specifically includes:

[0027] A Dendrobium water demand prediction model was established based on the deep learning algorithm. The model consists of an input layer, a hidden layer, an activation layer, and an output layer. The temperature, wind speed, and Dendrobium growth stage data in the greenhouse were used as training sets, and the corresponding water demand was used as a label to train the model and obtain a trained Dendrobium water demand prediction model.

[0028] Furthermore, the predicted water requirement H of Dendrobium officinale was corrected using the collected soil moisture data and light intensity data, and the formula for the comprehensive water requirement index was obtained as follows:

[0029]

[0030] Among them, M is the comprehensive water demand index, S is soil moisture, L is light intensity, H is the predicted water demand of Dendrobium, α is the preset proportional coefficient of soil moisture S, β is the preset proportional coefficient of light intensity L, γ is the preset proportional coefficient of the predicted water demand of Dendrobium H, α, β, and γ are all greater than zero, and α>β>γ, and C1 is the constant correction index.

[0031] Furthermore, based on the obtained comprehensive water demand index, the drip irrigation interval I(t) is calculated using a dynamic adjustment formula, and the formula is as follows:

[0032] I(t)=I0*e -k*M

[0033] Where I(t) is the calculated drip irrigation interval, I0 is the initial drip irrigation interval in hours, M is the comprehensive water demand index, and k is the preset adjustment coefficient, and k is greater than zero.

[0034] Furthermore, based on the calculated drip irrigation interval, the system automatically adjusts the drip irrigation water volume, specifically including:

[0035] When the comprehensive water demand index M is higher than the preset water demand threshold M x , that is, M>M x When , the system will increase the drip irrigation water volume. The calculation formula of the drip irrigation water volume Q is as follows:

[0036] Q=Q base *(1+δ*M)

[0037] Where Q is the irrigation water volume, Q base is the basic irrigation amount in liters, M is the comprehensive water demand index, δ is the preset proportional coefficient of the comprehensive water demand index M, and δ is greater than zero.

[0038] The present invention further provides a dendrobium greenhouse seedling cultivation intelligent drip irrigation system, which is used to implement the above-mentioned dendrobium greenhouse seedling cultivation intelligent drip irrigation method, including:

[0039] The data acquisition module uses soil moisture sensors, temperature sensors, light intensity sensors, wind speed sensors, and plant growth status sensors to collect multiple sets of historical data from the greenhouse. Each set of historical data includes temperature, wind speed, Dendrobium growth stage data, and the corresponding plant water demand;

[0040] The model building module uses greenhouse temperature, wind speed, and Dendrobium growth stage data as a training set and the corresponding water demand as a label. It builds a Dendrobium water demand prediction model based on a deep learning algorithm, trains the model, and obtains a trained Dendrobium water demand prediction model.

[0041] The model correction module uses sensors to collect real-time data on temperature, wind speed, and dendrobium growth stage in the greenhouse, and inputs these data into the water demand prediction model to obtain the predicted water demand of dendrobium as output. The predicted water demand of dendrobium is corrected using the collected soil moisture data and light intensity data to obtain a comprehensive water demand index.

[0042] The comprehensive analysis module calculates the drip irrigation interval based on the obtained comprehensive water demand index using a dynamic adjustment formula. According to the calculated drip irrigation interval, the system automatically adjusts the drip irrigation time, and when the comprehensive water demand index is higher than the preset water demand threshold, the system will increase the drip irrigation water volume.

[0043] Compared with the prior art, the present invention has the following beneficial effects:

[0044] The present invention integrates multiple sensors and deep learning algorithms to build an intelligent greenhouse plant water demand prediction and management system. The system can collect environmental data and plant growth status in the greenhouse in real time, accurately calculate the plant's water demand through a trained prediction model, and correct it in combination with soil moisture data and light intensity data to obtain a more accurate comprehensive water demand index. Based on this index, the system can dynamically adjust the drip irrigation interval and drip irrigation water volume to ensure that plants can obtain an appropriate water supply at different growth stages and under environmental changes. This intelligent management method not only improves water use efficiency and reduces water waste, but also helps to improve crop growth quality and yield, reduces the cost and labor intensity of manual management, and provides technical support for the sustainable development of greenhouse agriculture. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 Schematic diagram of the overall method flow of the present invention;

[0046] Figure 2 It is a schematic diagram of the overall system module of the present invention. DETAILED DESCRIPTION

[0047] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to specific embodiments.

[0048] It should be noted that, unless otherwise defined, the technical or scientific terms used in the present invention should have the usual meanings understood by people with ordinary skills in the field to which the present invention belongs. The "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative position relationships. When the absolute position of the object being described changes, the relative position relationship may also change accordingly.

[0049] Example:

[0050] See also Figure 1 , the present invention provides a technical solution:

[0051] An intelligent drip irrigation method for growing dendrobium seedlings in a greenhouse, comprising the following steps:

[0052] Step 1: Use soil moisture sensors, temperature sensors, light intensity sensors, wind speed sensors, and plant growth status sensors to collect multiple sets of historical data from the Dendrobium seedling greenhouse. Each set of historical data includes temperature, wind speed, Dendrobium growth stage data, and the corresponding Dendrobium water requirement.

[0053] In this embodiment, soil moisture sensors, temperature sensors, light intensity sensors, wind speed sensors, and plant growth status sensors are installed in different areas of the greenhouse, specifically including:

[0054] In the greenhouse, sensors should be installed according to the planting layout and environmental characteristics of the dendrobium. The soil moisture sensor should be installed near the roots of the dendrobium. The temperature sensor should be installed in the center of the greenhouse to avoid the influence of local heat sources. The light intensity sensor should be installed in a position that can represent the lighting conditions of the entire greenhouse. The wind speed sensor should be installed at the ventilation position in the greenhouse.

[0055] The water requirement of Dendrobium officinale should be obtained based on historical irrigation data;

[0056] By installing a variety of sensors, comprehensive data on greenhouse environmental parameters and plant growth status can be collected. This data includes but is not limited to soil moisture, temperature, light intensity, wind speed, and plant growth stage. Comprehensive analysis of these parameters can more accurately reflect the plant's water needs. The collected historical data provides rich training material for the deep learning model, enabling it to learn the complex patterns and dynamic changes in Dendrobium's water needs. This data-driven decision-making process is more scientific and reliable than traditional methods that rely on experience and intuition.

[0057] The growth stages of Dendrobium are mainly divided into: seed stage, seedling stage, growth stage, flowering stage, fruiting stage and aging stage;

[0058] For the sensor data, ensure that the data format of all sensor outputs is unified, including timestamp, sensor type, and reading value, and establish a data storage and backup mechanism in the system to ensure that the collected data will not be lost due to system failures, and the data is regularly backed up to a secure storage medium;

[0059] Pre-process the data from each sensor to ensure data quality, including:

[0060] Remove data outliers: Calculate the standard deviation of the data and set 3 times the standard deviation as the threshold. Data points outside this range are considered outliers.

[0061] The formula for calculating the standard deviation of the data is:

[0062]

[0063] Where σ is the standard deviation, N is the total number of data points, and x i is the i-th data point, μ is the mean of the data;

[0064] The formula for calculating the mean of the data is:

[0065]

[0066] Where μ is the mean of the data, N is the total number of data points, and x i is the i-th data point;

[0067] Data interpolation: For time series data, use linear interpolation to fill missing values: Assuming that the data changes linearly between two known points, the missing values are estimated by calculating the linear relationship between the two points.

[0068] Step 2: Using greenhouse temperature, wind speed, and Dendrobium growth stage data as a training set and the corresponding water requirements as labels, a Dendrobium water requirement prediction model was established based on a deep learning algorithm. The model was trained to obtain a trained Dendrobium water requirement prediction model.

[0069] In this embodiment, the process of establishing a dendrobium water demand prediction model based on a deep learning algorithm specifically includes:

[0070] A Dendrobium water demand prediction model was established based on the deep learning algorithm. The model consists of an input layer, a hidden layer, an activation layer, and an output layer. The temperature, wind speed, and Dendrobium growth stage data in the greenhouse were used as training sets, and the corresponding water demand was used as a label to train the model and obtain a trained Dendrobium water demand prediction model.

[0071] A Dendrobium water requirement prediction model based on a deep learning algorithm can automatically predict the plant's water needs. This level of automation is unmatched by traditional rule-based or empirical methods. It can dynamically adjust predictions based on real-time data, enabling more intelligent water management. Deep learning models can learn complex nonlinear relationships from large amounts of data, enabling them to capture subtle correlations between temperature, wind speed, plant growth stage, and water requirements. This high-precision prediction capability allows the model to adapt to different environmental conditions and plant growth stages, providing more personalized water management recommendations. Through the model's automated learning and prediction, the impact of human factors on water management decisions can be reduced, mitigating the problems of insufficient or excessive water supply caused by human misjudgment.

[0072] Step 3: Use sensors to collect real-time data on greenhouse temperature, wind speed, and Dendrobium growth stage, and input them into the water demand prediction model to obtain the model's output of the predicted Dendrobium water demand. The predicted plant water demand is then corrected using the collected soil moisture and light intensity data to obtain a comprehensive water demand index.

[0073] In this embodiment, the predicted water demand H of Dendrobium officinale is corrected using the collected soil moisture data and light intensity data, and the formula for obtaining the comprehensive water demand index is as follows:

[0074]

[0075] Where M is the comprehensive water demand index, S is soil moisture, L is light intensity, and H is the predicted water demand of Dendrobium. α is the preset proportional coefficient for soil moisture S, β is the preset proportional coefficient for light intensity L, and γ is the preset proportional coefficient for the predicted water demand H. α, β, and γ are all greater than zero, with α>β>γ. C1 is a constant correction exponent. Soil moisture is a key factor directly affecting water absorption by Dendrobium and holds a significant weight in the model. Low soil moisture limits plant water acquisition, while high soil moisture can cause root hypoxia. Soil moisture S typically accounts for 40-60% of the weight. Light intensity L affects plant photosynthesis and transpiration, thereby indirectly affecting plant water demand. High light levels enhance plant transpiration and increase water demand. Light intensity usually accounts for 20-40% of the weight; the predicted plant water demand H is obtained through historical water demand, which reflects the water demand of plants under past environmental conditions and can provide some prediction basis for current water demand. Historical water demand usually accounts for 10-30% of the weight, so α>β>γ; when soil moisture S increases, plants will reduce their absorption of water to avoid oversaturation, so the comprehensive water demand index M decreases; when light intensity L increases, the stomata on plant leaves will open wider to absorb more carbon dioxide for photosynthesis. At the same time, this also causes more water to evaporate from the leaf surface into the atmosphere through transpiration. The increase in transpiration means that plants need more water to replenish the water lost due to evaporation, so the comprehensive water demand index M will increase; when the predicted plant water demand H increases, the comprehensive water demand index M will increase accordingly; that is, the light intensity L, the predicted plant water demand H and the comprehensive water demand index M are positively correlated, and the soil moisture S is negatively correlated with the comprehensive water demand index M;

[0076] By collecting real-time greenhouse environmental data and Dendrobium growth status data and inputting them into a water demand prediction model, real-time prediction of Dendrobium water requirements can be achieved. This real-time nature enables the system to dynamically adjust water supply based on current environmental conditions and plant status, more accurately meeting plant needs. In addition to temperature, wind speed, and Dendrobium growth stage data, soil moisture and light intensity data are also incorporated to refine the predicted water requirements. This comprehensive consideration of multiple factors provides a more comprehensive reflection of Dendrobium water requirements and improves prediction accuracy. Soil moisture directly reflects the water status of plant roots, while light intensity influences plant transpiration and water use efficiency. Incorporating these key data into the prediction model's refinement process significantly improves prediction accuracy and reliability. The calculation of the comprehensive water demand index takes into account multiple environmental factors and plant growth status, enabling the system to better adapt to different climate conditions and plant growth stages, enhancing its adaptability and robustness.

[0077] Step 4: Based on the obtained comprehensive water demand index, the drip irrigation interval is calculated using a dynamic adjustment formula. According to the calculated drip irrigation interval, the system automatically adjusts the drip irrigation time. When the comprehensive water demand index is higher than the preset water demand threshold, the system will increase the drip irrigation water volume.

[0078] In this embodiment, the drip irrigation interval I(t) is calculated using a dynamic adjustment formula based on the obtained comprehensive water demand index, and the formula is as follows:

[0079] I(t)=I0*e -k*M

[0080] Where I(t) is the calculated drip irrigation interval, I0 is the initial drip irrigation interval in hours, M is the comprehensive water demand index, and k is the preset adjustment coefficient. The value range of k is usually [0.5, 1.5]. When the comprehensive water demand index M increases, the plant's demand for water increases, and the drip irrigation interval shortens accordingly. This indicates that the comprehensive water demand index M is negatively correlated with the drip irrigation interval, I(t).

[0081] Based on the calculated drip irrigation interval, the system automatically adjusts the drip irrigation water volume, including:

[0082] When the comprehensive water demand index M is higher than the preset water demand threshold M x , that is, M>M x When , the system will increase the drip irrigation water volume. The calculation formula of the drip irrigation water volume Q is as follows:

[0083] Q=Q base *(1+δ*M)

[0084] Where Q is the irrigation water volume, Q baseis the basic irrigation amount, in liters, M is the comprehensive water demand index, δ is the preset proportional coefficient of the comprehensive water demand index M, and the value range of δ is usually [0.85, 0.95]. When the comprehensive water demand index M increases, the plant's demand for water increases. If M is higher than the preset water demand threshold M x , the drip irrigation water volume Q will be increased, which means that the comprehensive water demand index M is positively correlated with the drip irrigation water volume Q.

[0085] See also Figure 2 The present invention also provides a dendrobium greenhouse seedling intelligent drip irrigation system, comprising:

[0086] The data acquisition module uses soil moisture sensors, temperature sensors, light intensity sensors, wind speed sensors, and plant growth status sensors to collect multiple sets of historical data from the greenhouse. Each set of historical data includes temperature, wind speed, Dendrobium growth stage data, and the corresponding plant water demand;

[0087] The model building module uses greenhouse temperature, wind speed, and Dendrobium growth stage data as a training set and the corresponding water demand as a label. It builds a Dendrobium water demand prediction model based on a deep learning algorithm, trains the model, and obtains a trained Dendrobium water demand prediction model.

[0088] The model correction module uses sensors to collect real-time data on temperature, wind speed, and dendrobium growth stage in the greenhouse, and inputs these data into the water demand prediction model to obtain the predicted water demand of dendrobium as output. The predicted water demand of dendrobium is corrected using the collected soil moisture data and light intensity data to obtain a comprehensive water demand index.

[0089] The comprehensive analysis module calculates the drip irrigation interval based on the obtained comprehensive water demand index using a dynamic adjustment formula. According to the calculated drip irrigation interval, the system automatically adjusts the drip irrigation time, and when the comprehensive water demand index is higher than the preset water demand threshold, the system will increase the drip irrigation water volume.

[0090] The specific values of α, β and γ in the formula are generally determined by technical personnel in this field based on actual conditions. The technical personnel in this field collect multiple groups of sample data and set corresponding preset proportional coefficients for each group of sample data. The set preset proportional coefficients and the collected sample data are substituted into the formula. Through repeated experiments and parameter adjustments, the accuracy of the model output and the rationality of the results are observed, and these factor coefficients are gradually adjusted. The performance and effect of the model under different parameter settings are compared to find the optimal coefficient combination. The calculated factor coefficients are screened and averaged to obtain the values of α, β and γ.

[0091] In addition, the size of the preset factor coefficient is a specific numerical value obtained by quantizing each parameter. In order to facilitate subsequent comparison, the size of the coefficient depends on the amount of sample data and the preliminary setting of the corresponding preset proportional coefficient for each set of sample data by technical personnel in this field. It is not unique, as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0092] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0093] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software depends on the specific application and design constraints of the technical solution.

[0094] 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, and may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment as needed.

[0095] The above is only a specific implementation method of the present application, but the scope of protection of the present application is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed in this application, which should be covered by the scope of protection of the present application.

Claims

1. An intelligent drip irrigation method for growing dendrobium seedlings in a greenhouse, characterized in that: The specific steps include: Step 1: Use soil moisture sensors, temperature sensors, light intensity sensors, wind speed sensors, and plant growth status sensors to collect multiple sets of historical data from the Dendrobium seedling greenhouse. Each set of historical data includes temperature, wind speed, Dendrobium growth stage data, and the corresponding Dendrobium water requirement. Step 2: Using greenhouse temperature, wind speed, and Dendrobium growth stage data as a training set and the corresponding water requirements as labels, a Dendrobium water requirement prediction model was established based on a deep learning algorithm. The model was trained to obtain a trained Dendrobium water requirement prediction model. Step 3: Use sensors to collect real-time data on greenhouse temperature, wind speed, and Dendrobium growth stage, and input them into the water demand prediction model to obtain the model's output of the predicted Dendrobium water demand. The predicted plant water demand is then corrected using the collected soil moisture and light intensity data to obtain a comprehensive water demand index. Step 4: Based on the obtained comprehensive water demand index, the drip irrigation interval is calculated using a dynamic adjustment formula. According to the calculated drip irrigation interval, the system automatically adjusts the drip irrigation time. When the comprehensive water demand index is higher than the preset water demand threshold, the system will increase the drip irrigation water volume. The process of establishing a dendrobium water demand prediction model based on a deep learning algorithm specifically includes: A Dendrobium water demand prediction model was established based on a deep learning algorithm. The model consists of an input layer, a hidden layer, an activation layer, and an output layer. The greenhouse temperature, wind speed, and Dendrobium growth stage data were used as training sets, and the corresponding water demand was used as a label. The model was trained to obtain a trained Dendrobium water demand prediction model. The predicted water requirement H of Dendrobium officinale was corrected using the collected soil moisture data and light intensity data. The formula for the comprehensive water requirement index was as follows: Wherein, M is the comprehensive water demand index, S is soil moisture, L is light intensity, H is the predicted water demand of Dendrobium, α is the preset proportional coefficient of soil moisture S, β is the preset proportional coefficient of light intensity L, γ is the preset proportional coefficient of predicted water demand H of Dendrobium, α, β, and γ are all greater than zero, and α>β>γ, and C1 is a constant correction index; Based on the obtained comprehensive water demand index, the drip irrigation interval I(t) is calculated using a dynamic adjustment formula, which is based on the following formula: I(t)=I0*e -k*M Where I(t) is the calculated drip irrigation interval, I0 is the initial drip irrigation interval in hours, M is the comprehensive water demand index, k is the preset adjustment coefficient, and k is greater than zero; Soil moisture sensors, temperature sensors, light intensity sensors, wind speed sensors, and plant growth status sensors are installed in different areas of the greenhouse, including: In the greenhouse, sensors are installed according to the dendrobium planting layout and environmental characteristics. The soil moisture sensor is installed near the plant roots, the temperature sensor is installed in the center of the greenhouse to avoid the influence of local heat sources, the light intensity sensor is installed in a position that can represent the lighting conditions of the entire greenhouse, and the wind speed sensor is installed at the ventilation position in the greenhouse. The water requirement of Dendrobium officinale should be obtained based on historical irrigation data; The growth stages of Dendrobium are mainly divided into: seed stage, seedling stage, growth stage, flowering stage, fruiting stage and aging stage; Based on the calculated drip irrigation interval, the system automatically adjusts the drip irrigation water volume, including: When the comprehensive water demand index M is higher than the preset water demand threshold M x , that is, M>M x When , the system will increase the drip irrigation water volume. The calculation formula of the drip irrigation water volume Q is as follows: Q=Q base *(1+δ*M) Where Q is the irrigation water volume, Q base is the basic irrigation amount in liters, M is the comprehensive water demand index, δ is the preset proportional coefficient of the comprehensive water demand index M, and δ is greater than zero.

2. The intelligent drip irrigation method for growing dendrobium seedlings in a greenhouse according to claim 1, characterized in that: For the sensor data, ensure that the data format of all sensor outputs is unified, and the data format includes timestamp, sensor type, and reading value. Establish a data storage and backup mechanism in the system to ensure that the collected data will not be lost due to system failure, and the data is regularly backed up to a secure storage medium.

3. The intelligent drip irrigation method for growing dendrobium seedlings in a greenhouse according to claim 2, characterized in that: Pre-process the data from each sensor to ensure data quality, including: Remove data outliers: Calculate the standard deviation of the data and set 3 times the standard deviation as the threshold. Data points outside this range are considered outliers. The formula for calculating the standard deviation of the data is: Where σ is the standard deviation, N is the total number of data points, and x i is the i-th data point, μ is the mean of the data; The formula for calculating the mean of the data is: Where μ is the mean of the data, N is the total number of data points, and x i is the i-th data point; Data interpolation: For time series data, use linear interpolation to fill missing values: Assuming that the data changes linearly between two known points, the missing values are estimated by calculating the linear relationship between the two points.

4. An intelligent drip irrigation system for growing dendrobium seedlings in a greenhouse, characterized by: The intelligent drip irrigation system for growing dendrobium seedlings in a greenhouse is used to implement the intelligent drip irrigation method for growing dendrobium seedlings in a greenhouse according to any one of claims 1 to 3, comprising: The data acquisition module uses soil moisture sensors, temperature sensors, light intensity sensors, wind speed sensors, and plant growth status sensors to collect multiple sets of historical data from the Dendrobium seedling greenhouse. Each set of historical data includes temperature, wind speed, Dendrobium growth stage data, and the corresponding plant water demand; The model building module uses greenhouse temperature, wind speed, and Dendrobium growth stage data as a training set and the corresponding water demand as a label. It builds a Dendrobium water demand prediction model based on a deep learning algorithm, trains the model, and obtains a trained Dendrobium water demand prediction model. The model correction module uses sensors to collect real-time data on temperature, wind speed, and dendrobium growth stage in the greenhouse, and inputs these data into the water demand prediction model to obtain the predicted water demand of dendrobium as output. The predicted water demand of dendrobium is corrected using the collected soil moisture data and light intensity data to obtain a comprehensive water demand index. The comprehensive analysis module calculates the drip irrigation interval based on the obtained comprehensive water demand index using a dynamic adjustment formula. According to the calculated drip irrigation interval, the system automatically adjusts the drip irrigation time, and when the comprehensive water demand index is higher than the preset water demand threshold, the system will increase the drip irrigation water volume.

Images