Growth monitoring method based on greenhouse wheat seedlings

Abstract

The present invention relates to the technical field of wheat growth monitoring, and in particular to a growth monitoring method based on greenhouse wheat seedling cultivation, comprising the following steps: deploying a sensor network in the greenhouse; constructing a multi-parameter coupling model, and determining the dynamic interaction between multiple parameters by introducing a coupling coefficient. The multi-parameter coupling model adopts a multiple regression analysis method, combines historical data with real-time data, dynamically adjusts the coupling coefficient, constructs a multi-parameter coupling model, and analyzes the influence of the coupling changes of various environmental parameters on the growth of wheat seedling cultivation; and sets an environmental control unit to adjust the temperature, humidity, light and carbon dioxide concentration parameters in the greenhouse in real time. The present invention ensures that the environmental parameters in the greenhouse can be adaptively maintained in an optimal state, thereby effectively improving the overall growth efficiency and quality of wheat seedling cultivation.

Description

Technical Field

[0001] The invention relates to the technical field of wheat growth monitoring, and in particular to a growth monitoring method based on greenhouse wheat seedling cultivation. Background Art

[0002] During the wheat seedling raising process, the environmental conditions in the greenhouse have a crucial impact on the growth rate and quality of the seedlings. Temperature, humidity, light intensity and carbon dioxide concentration are the main environmental parameters affecting wheat growth. Traditional greenhouse environmental control methods are usually based on simple feedback adjustments of a single parameter, relying on manual experience to adjust temperature, humidity, light, etc. It is difficult to accurately balance the complex relationship between different environmental parameters, and it is impossible to make real-time adaptive adjustments, resulting in large environmental fluctuations and insufficient control accuracy, which affects the seedling raising effect.

[0003] Most of the existing seedling environment control systems rely on fixed set values ​​for adjustment and lack real-time dynamic analysis of environmental parameters. In particular, in different wheat growth stages, there are large differences in the optimal combination of parameters such as temperature and humidity. A single parameter adjustment method is difficult to meet the needs of the entire seedling cycle. In addition, traditional methods find it difficult to consider the mutual coupling effects between environmental parameters, such as the relationship between temperature and humidity, the interaction between light intensity and carbon dioxide concentration, etc. These factors make it difficult to achieve refinement and intelligence in greenhouse environmental control systems in practical applications, and the seedling process is inefficient and of unstable quality. Summary of the invention

[0004] The invention provides a growth monitoring method based on greenhouse wheat seedling cultivation.

[0005] The growth monitoring method based on greenhouse wheat seedling cultivation includes the following steps:

[0006] S1, deploys a sensor network in the greenhouse to collect temperature, humidity, light intensity, and carbon dioxide concentration;

[0007] S2, based on the collected data, a multi-parameter coupling model is constructed, and the dynamic interaction between multiple parameters is determined by introducing the coupling coefficient. The multi-parameter coupling model uses a multiple regression analysis method, combines historical data with real-time data, and dynamically adjusts the coupling coefficient to ensure that the model can accurately reflect the complex linkage effects between environmental parameters in the greenhouse. The multi-parameter coupling model is constructed to analyze the impact of the coupling changes of various environmental parameters on the growth of wheat seedlings;

[0008] S3, based on the multi-parameter coupling model, sets up the environmental control unit, and adjusts the temperature, humidity, light and carbon dioxide concentration parameters in the greenhouse in real time according to the analysis results of the multi-parameter coupling model to ensure that the environment is always in the optimal state during the wheat seedling cultivation process. The feedback mechanism of environmental control can detect abnormal situations in real-time monitoring and send out an alarm signal when the environmental parameters exceed the ideal range set by the model, prompting the operator to make necessary adjustments.

[0009] Optionally, S1 includes designing a sensor network layout according to the structure and spatial layout inside the greenhouse; the sensor network includes a temperature sensor, a humidity sensor, a light sensor and a carbon dioxide concentration sensor.

[0010] Optionally, the S2 specifically includes:

[0011] S21, preprocessing the temperature, humidity, light intensity and carbon dioxide concentration data collected from the sensor network, including feature extraction of historical data and real-time data through the sliding window method, extracting the feature vector of the input parameters , Including temperature ,humidity , light intensity and carbon dioxide concentration ; The feature vector set is expressed as:

[0012] ,in, For the The temperature value at the moment, For the The humidity value at the moment, For the The light intensity at the time, For the The carbon dioxide concentration at the time;

[0013] S22, using the multivariate regression analysis method, based on the preprocessed input variable feature vector, constructs an integrated multi-parameter coupling model. The multi-parameter coupling model introduces multiple coupling coefficients to quantify the dynamic interaction between the four parameters, describe the nonlinear coupling effect between temperature, humidity, light intensity and carbon dioxide concentration, and determine the common impact on the wheat growth environment;

[0014] S23, the coupling coefficient is dynamically adjusted according to the changes in historical data and real-time monitoring data to ensure the adaptability of the model. An online learning algorithm is used to continuously update the coupling coefficient to ensure that the model continuously reflects the real-time dynamic changes in the internal environment of the greenhouse, thereby optimizing the environmental conditions in the greenhouse in real time.

[0015] Optionally, the sliding window method specifically includes:

[0016] Set the length of the sliding window: Select the length of the sliding window , can be set to 5 minutes. The window length mainly depends on the data collection frequency and actual application requirements. The moving step of the sliding window Indicates the distance the window slides each time. The step size is set to 1 minute. Each sensor collects data once a minute, and the sliding window length is 5 minutes. , the step length is 1 minute, that is , each sliding window contains 5 data points;

[0017] Calculate features within the window: For each sliding window , respectively, from the temperature ,humidity , light intensity , CO2 concentration Extract statistical features from the time series of data, including mean, standard deviation, maximum and minimum values;

[0018] For each sliding window Combine the features extracted from .

[0019] Optionally, the multi-parameter coupling model is expressed as:

[0020] ；

[0021] in, It represents the growth state (growth rate) of the wheat seedling growth environment and is the output of the model; , , , Respectively represent temperature, humidity, light intensity and carbon dioxide concentration, which are the input variables of the model. is the individual influence coefficient of each parameter, is the coupling coefficient between parameters, which quantifies the coupling effects between temperature and humidity, temperature and light intensity, temperature and carbon dioxide concentration, humidity and light intensity, humidity and carbon dioxide concentration, and light intensity and carbon dioxide concentration. is the error term;

[0022] The online learning algorithm is adopted in S23, and the coupling coefficient is continuously updated, specifically including:

[0023] Initialization: Based on historical data, the coupling coefficient β0 is determined using the initial regression model;

[0024] Data input: The sensor network monitors environmental data in real time and inputs X(k);

[0025] Recursive least squares method is used as the online learning algorithm to dynamically adjust the coupling coefficient according to the new data and the prediction results of the current model.

[0026] Optionally, the update rule of the recursive least squares method includes:

[0027] Set the initial coupling coefficient vector and the covariance matrix , the coupling coefficient update rule is as follows:

[0028] ,in, is the updated coupling coefficient vector, that is, the current time step The coupling coefficient at the moment is based on the coupling coefficient of the previous step. and the gain matrix Adjusted, Indicated in The coupling coefficient for each time step is The coupling coefficient is transposed, is the target output at the current moment (the monitoring result of the wheat growth environment at the current moment, i.e., the growth rate), is the input feature vector at the current moment, including various parameters and their interaction terms; is the gain matrix, which is used to control the weight of the model on historical data. The gain matrix controls the update step size of the model;

[0029] Covariance matrix The update is expressed as: ,in, It is The covariance matrix of the step, is the transpose of the current input feature vector.

[0030] Optionally, the S3 specifically includes:

[0031] S31, collects real-time data on temperature, humidity, light intensity and carbon dioxide concentration in the greenhouse through a sensor network, and inputs the real-time data into a multi-parameter coupling model to analyze the difference between current environmental parameters and wheat growth requirements;

[0032] S32, based on the multi-parameter coupling model, analyzing the current temperature, humidity, light intensity and carbon dioxide concentration and the mutual coupling relationship to predict the growth state of wheat, and adjusting the environmental parameter combination according to the prediction results until the optimal environmental parameter combination is determined;

[0033] S33, based on the optimal combination of environmental parameters, control is performed through the environmental control unit.

[0034] Optionally, after the S32 predicts the influence of the current parameters on the growth state of wheat, the combination optimization of the parameters is performed, and the optimal combination of parameters is found through the target optimization function to maximize the growth state of wheat. The target optimization function is to find the optimal combination of environmental parameters, which is converted into an optimization problem: The goal is to adjust , making wheat The growth status at any moment To achieve the optimal value, It is Temperature, humidity, light intensity, and carbon dioxide concentration parameters are obtained from sensors at all times.

[0035] Gradient optimization is a specific way to solve the objective function. By calculating the gradient of the loss function with respect to each environmental parameter, the system gradually adjusts each environmental parameter until the optimal combination of parameters is found.

[0036] Optionally, the regulating by the environment regulating unit specifically includes:

[0037] Temperature regulation module: By controlling the heater or cooling device, the temperature in the greenhouse is adjusted in real time to maintain it within the optimal growth range of wheat;

[0038] Humidity control module: According to the dynamic changes of humidity coupling coefficient, the spray system or ventilation system is adjusted to ensure that the humidity is suitable for wheat growth;

[0039] Light control module: Control light intensity by adjusting the lighting system or adjusting the greenhouse shading equipment to maintain a light level suitable for wheat photosynthesis;

[0040] Carbon dioxide concentration regulation module: according to the coupling relationship between light and carbon dioxide concentration, the carbon dioxide release device is controlled to promote the photosynthesis of wheat;

[0041] Through the environmental control unit, the temperature, humidity, light intensity and carbon dioxide concentration in the greenhouse are dynamically adjusted according to the real-time analysis results of the multi-parameter coupling model to ensure that each parameter is maintained within the optimal range during the wheat seedling cultivation process.

[0042] Beneficial effects of the present invention:

[0043] The present invention introduces a multi-parameter coupling model to comprehensively analyze the effects of multiple environmental parameters such as temperature, humidity, light intensity and carbon dioxide concentration on wheat growth, and considers the mutual coupling between them. Compared with the traditional single-parameter control method, the model can accurately predict the comprehensive impact of environmental conditions on wheat growth, and provides a more refined and dynamically adjusted control strategy. By combining historical data and real-time data for dynamic analysis, it ensures that the environmental parameters in the greenhouse can be adaptively maintained in the optimal state, thereby effectively improving the overall growth efficiency and quality of wheat seedlings.

[0044] The present invention is based on a real-time feedback mechanism and combines the sensor network to continuously monitor the temperature, humidity, light intensity and carbon dioxide concentration in the greenhouse. It can dynamically adjust the control equipment according to the data collected by the sensors. Through recursive least squares online learning, it can continuously update the coupling coefficients between various environmental parameters to ensure that the control strategy can be adjusted in real time with environmental changes and maintain a stable state in the greenhouse. This real-time control mechanism improves the response speed and adjustment accuracy of the system and significantly reduces the environmental fluctuations that may occur in the traditional manual adjustment process.

[0045] The present invention performs proportional control through the designed environmental control gain coefficient, so that the system can achieve rapid response and stable adjustment based on the deviation between the environmental parameters and the set target values. The gradient optimization algorithm and the empirical tuning method are combined to ensure that the gain coefficient can adapt to the environmental requirements of different growth stages and avoid the problems of over-adjustment or slow response. This innovation significantly improves the regulation efficiency, so that the environmental parameters in the wheat seedling process can be maintained within the optimal range in a more precise and reliable manner, ultimately improving the yield and quality of wheat. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0047] Figure 1 A schematic diagram of a monitoring method flow chart of an embodiment of the present invention;

[0048] Figure 2 Schematic diagram of environmental control according to an embodiment of the present invention. DETAILED DESCRIPTION

[0049] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0050] It should be noted that the references to "one embodiment", "embodiment", "exemplary embodiments", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0051] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0052] like Figure 1-Figure 2 As shown, the growth monitoring method based on greenhouse wheat seedling cultivation includes the following steps:

[0053] S1, deploys a sensor network in the greenhouse to collect temperature, humidity, light intensity, and carbon dioxide concentration;

[0054] S2, based on the collected data, a multi-parameter coupling model is constructed. By introducing the coupling coefficient, the dynamic interaction between multiple parameters is determined. The multi-parameter coupling model uses a multivariate regression analysis method, combines historical data with real-time data, and dynamically adjusts the coupling coefficient to ensure that the model can accurately reflect the complex linkage effects between environmental parameters in the greenhouse. The multi-parameter coupling model is constructed to analyze the impact of the coupling changes of various environmental parameters on the growth of wheat seedlings. The prediction results of the model are verified by experimental data, focusing on the analysis of the impact of different environmental control strategies on key stages such as germination, tillering and root development in the wheat seedling process under the conditions of the multi-parameter coupling model. The goal of the model is to identify the optimal combination of environmental conditions at each growth stage of wheat seedlings to maximize the growth efficiency and health of wheat;

[0055] S3, based on the multi-parameter coupling model, sets up the environmental control unit, and adjusts the temperature, humidity, light and carbon dioxide concentration parameters in the greenhouse in real time according to the analysis results of the multi-parameter coupling model to ensure that the environment is always in the optimal state during the wheat seedling cultivation process. The feedback mechanism of environmental control can detect abnormal situations in real-time monitoring and send out an alarm signal when the environmental parameters exceed the ideal range set by the model, prompting the operator to make necessary adjustments.

[0056] S1 includes designing the sensor network layout according to the structure and spatial layout inside the greenhouse; the sensor network includes temperature sensors, humidity sensors, light sensors and carbon dioxide concentration sensors.

[0057] S2 specifically includes:

[0058] S21, preprocessing the temperature, humidity, light intensity and carbon dioxide concentration data collected from the sensor network, including feature extraction of historical data and real-time data through the sliding window method, extracting the feature vector of the input parameters , Including temperature ,humidity , light intensity and carbon dioxide concentration ; The feature vector set is expressed as:

[0059] ,in, For the The temperature value at the moment, For the The humidity value at the moment, For the The light intensity at the time, For the The carbon dioxide concentration at the time;

[0060] S22, using the multivariate regression analysis method, based on the preprocessed input variable feature vector, constructs an integrated multi-parameter coupling model. The multi-parameter coupling model introduces multiple coupling coefficients to quantify the dynamic interaction between the four parameters, describe the nonlinear coupling effect between temperature, humidity, light intensity and carbon dioxide concentration, and determine the common impact on the wheat growth environment;

[0061] S23, the coupling coefficient is dynamically adjusted according to the changes in historical data and real-time monitoring data to ensure the adaptability of the model. An online learning algorithm is used to continuously update the coupling coefficient to ensure that the model continuously reflects the real-time dynamic changes in the internal environment of the greenhouse, thereby optimizing the environmental conditions in the greenhouse in real time.

[0062] The sliding window method specifically includes:

[0063] Set the length of the sliding window: Select the length of the sliding window , can be set to 5 minutes. The window length mainly depends on the data collection frequency and actual application requirements. The moving step of the sliding window Indicates the distance the window slides each time. The step size is set to 1 minute. Each sensor collects data once a minute, and the sliding window length is 5 minutes. , the step length is 1 minute, that is , each sliding window contains 5 data points;

[0064] Calculate features within the window: For each sliding window , respectively, from the temperature ,humidity , light intensity , CO2 concentration Extract statistical features, mean, standard deviation, maximum and minimum values ​​from the time series of data, and set the time series data ,in, Representative Temperature data at time points, similarly, Indicates humidity, Indicates the light intensity, Indicates the carbon monoxide concentration. sliding windows, the time range is , extract the following statistical features from the sliding window:

[0065] Mean: , and similarly calculate , , ;

[0066] Standard Deviation: , and similarly calculate , , ;

[0067] Maximum value: , and similarly calculate , , ;

[0068] Minimum: , and similarly calculate , , ;

[0069] For each sliding window Combine the features extracted from ;

[0070]

[0071] If four statistical features (mean, standard deviation, maximum value, minimum value) are extracted for each parameter (temperature, humidity, light intensity, carbon dioxide concentration), then each feature vector Contains 16 elements, the sliding window is in steps of Move to the next time period to form the next window , repeat the above feature extraction process until the entire time series is covered.

[0072] The multi-parameter coupling model is expressed as:

[0073] ；

[0074] in, It represents the growth state (growth rate) of the wheat seedling growth environment and is the output of the model; , , , Respectively represent temperature, humidity, light intensity and carbon dioxide concentration, which are the input variables of the model. is the individual influence coefficient of each parameter, is the coupling coefficient between parameters, which quantifies the coupling effects between temperature and humidity, temperature and light intensity, temperature and carbon dioxide concentration, humidity and light intensity, humidity and carbon dioxide concentration, and light intensity and carbon dioxide concentration. is the error term, which represents the prediction error of the model or the unobserved external influence;

[0075] By introducing the coupling coefficient, the model not only considers the impact of each parameter on the wheat growth environment, but also quantifies the nonlinear coupling effect between the parameters through cross terms, so that the model can more accurately reflect the complex environmental dynamic changes in the greenhouse.

[0076] The sensor network continuously monitors temperature, humidity, light intensity and carbon dioxide concentration, and transmits the data to the model in real time. The coupling coefficient is constantly adjusted with new data to ensure that the model can reflect the dynamic changes in the greenhouse environment in real time. S23 uses an online learning algorithm to continuously update the coupling coefficient, including:

[0077] Initialization: Based on historical data, the coupling coefficient β0 is determined using the initial regression model;

[0078] Data input: The sensor network monitors environmental data in real time and inputs X(k);

[0079] Recursive least squares method is used as the online learning algorithm to dynamically adjust the coupling coefficient according to the new data and the prediction results of the current model.

[0080] The update rule for the recursive least squares method consists of:

[0081] Set the initial coupling coefficient vector , and the covariance matrix , the coupling coefficient update rule is as follows:

[0082] ,in, is the updated coupling coefficient vector, that is, the current time step The coupling coefficient at the moment is based on the coupling coefficient of the previous step. and the gain matrix Adjusted, Indicated in The coupling coefficient for each time step is The coupling coefficient is transposed, is the target output at the current moment (the monitoring result of the wheat growth environment at the current moment, i.e., the growth rate), is the input feature vector at the current moment, including various parameters and their interaction terms;

[0083] ; is the gain matrix, calculated as: ,in is the forgetting factor (set to a value close to 1, such as ), used to control the weight of the model on historical data, and the gain matrix controls the update step size of the model;

[0084] Covariance matrix The update is expressed as: ,in, It is The covariance matrix of the step, is the transpose of the current input feature vector.

[0085] S3 specifically includes:

[0086] S31, collects real-time data on temperature, humidity, light intensity and carbon dioxide concentration in the greenhouse through a sensor network, and inputs the real-time data into a multi-parameter coupling model to analyze the difference between current environmental parameters and wheat growth requirements;

[0087] S32, based on the multi-parameter coupling model, analyzing the current temperature, humidity, light intensity and carbon dioxide concentration and the mutual coupling relationship to predict the growth state of wheat, and adjusting the environmental parameter combination according to the prediction results until the optimal environmental parameter combination is determined;

[0088] S33, based on the optimal combination of environmental parameters, control is performed through the environmental control unit.

[0089] After S32 predicts the impact of the current parameters on the growth state of wheat, it performs parameter combination optimization and finds the optimal parameter combination through the target optimization function to maximize the growth state of wheat. The target optimization function is to find the optimal combination of environmental parameters, which is converted into an optimization problem: The goal is to adjust , making wheat The growth status at any moment To achieve the optimal value, It is Temperature, humidity, light intensity, and carbon dioxide concentration parameters are obtained from sensors at all times.

[0090] Then, gradient optimization is a specific way to solve the objective function. By calculating the loss function

[0091] For the gradient of each environmental parameter (i.e., how these parameters affect the growth state of wheat), the system gradually adjusts each environmental parameter until the optimal parameter combination is found. This step can be regarded as a means of optimizing the objective function, where is the theoretically optimal wheat growth state. In order to optimize the environmental parameter combination by gradient descent, it is necessary to calculate the partial derivative of the loss function for each environmental parameter:

[0092] , similarly;

[0093] ;

[0094] ;

[0095] ;

[0096] Based on the gradient of each parameter, update the environment parameters to reduce the loss:

[0097] ;

[0098] ;

[0099] ;

[0100] ;

[0101] is the learning rate, which is used to control the update step size.

[0102] Repeat the above steps until the loss function Convergence means that the combination of environmental parameters approaches the optimal combination.

[0103] Through the gradient optimization method, environmental parameters such as temperature, humidity, light intensity and carbon dioxide concentration are gradually adjusted to minimize the objective function. After each adjustment, the system will recalculate the loss, update the parameters, and gradually approach the optimal environmental combination.

[0104] The specific control through the environmental control unit includes:

[0105] Temperature regulation module: By controlling the heater or cooling device, the temperature in the greenhouse is adjusted in real time to maintain it within the optimal growth range of wheat;

[0106] Humidity control module: According to the dynamic changes of humidity coupling coefficient, the spray system or ventilation system is adjusted to ensure that the humidity is suitable for wheat growth;

[0107] Light control module: Control light intensity by adjusting the lighting system or adjusting the greenhouse shading equipment to maintain a light level suitable for wheat photosynthesis;

[0108] Carbon dioxide concentration regulation module: according to the coupling relationship between light and carbon dioxide concentration, the carbon dioxide release device is controlled to promote the photosynthesis of wheat;

[0109] Through the environmental control unit, the temperature, humidity, light intensity and carbon dioxide concentration in the greenhouse are dynamically adjusted according to the real-time analysis results of the multi-parameter coupling model to ensure that each parameter is maintained within the optimal range during the wheat seedling cultivation process.

[0110] Once the optimal target environment parameter combination is found , the equipment in the greenhouse will be regulated. The regulation process uses the P control (proportional control) part of the PID controller. Specifically, the regulation is based on the deviation between the current environmental parameters and the set target value, and a proportional gain coefficient is used to adjust the control quantity (such as heater power, spray system, light intensity and carbon dioxide release). This method is the characteristic of proportional control (P control).

[0111] Temperature control: The system controls the actual temperature by controlling the heater or cooling equipment. Adjust to the optimal temperature : ; is the power output of the heater or cooling device;

[0112] Humidity control: The actual humidity is controlled by humidity control equipment :

[0113] ; is the spray volume or ventilation volume of the spray system or ventilation system;

[0114] Light intensity control: adjust the light intensity by controlling the light source or sunshade :

[0115] ; It is the light intensity of the lighting system or the opening and closing degree of the sunshade device, indicating the workload of the equipment controlling the lighting;

[0116] Carbon dioxide concentration control: regulated by carbon dioxide release device :

[0117] ; is the workload of the carbon dioxide release device, indicating the regulation intensity of the equipment controlling the carbon dioxide concentration;

[0118] , , as well as The proportional control gain coefficient of each parameter is used for the PID controller (proportional-integral-differential). Users can use the PID tuning tool to automatically calculate the optimal proportional control parameters.

[0119] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0120] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A growth monitoring method based on greenhouse wheat seedling cultivation, characterized in that: The following steps are involved: S1, deploys a sensor network in the greenhouse to collect temperature, humidity, light intensity, and carbon dioxide concentration; S2, based on the collected data, build a multi-parameter coupling model, by introducing the coupling coefficient, determine the dynamic interaction between multiple parameters, the multi-parameter coupling model uses multiple regression analysis method, combines historical data with real-time data, dynamically adjusts the coupling coefficient, builds a multi-parameter coupling model, and analyzes the impact of the coupling changes of various environmental parameters on the growth of wheat seedlings, including: S21, preprocessing the temperature, humidity, light intensity and carbon dioxide concentration data collected from the sensor network, including feature extraction of historical data and real-time data through the sliding window method, extracting the feature vector of the input parameters , Including temperature ,humidity , light intensity and carbon dioxide concentration ; The feature vector set is expressed as: ,in, For the The temperature value at the moment, For the The humidity value at the moment, For the The light intensity at the time, For the The carbon dioxide concentration at the time; S22, using a multivariate regression analysis method, based on the preprocessed input variable feature vector, construct an integrated multi-parameter coupling model, the multi-parameter coupling model introduces multiple coupling coefficients to quantify the dynamic interaction between the four parameters, describe the nonlinear coupling effect between temperature, humidity, light intensity and carbon dioxide concentration, and determine the common impact on the wheat growth environment; the multi-parameter coupling model is expressed as: ； in, represents the growth state of the wheat seedling growth environment and is the output of the model; T, H, I, Respectively represent temperature, humidity, light intensity and carbon dioxide concentration, which are the input variables of the model. is the individual influence coefficient of each parameter, is the coupling coefficient between parameters, which quantifies the coupling effects between temperature and humidity, temperature and light intensity, temperature and carbon dioxide concentration, humidity and light intensity, humidity and carbon dioxide concentration, and light intensity and carbon dioxide concentration. is the error term; S23, the coupling coefficient is dynamically adjusted according to the changes in historical data and real-time monitoring data to ensure the adaptability of the model. An online learning algorithm is used to continuously update the coupling coefficient to ensure that the model continuously reflects the real-time dynamic changes in the internal environment of the greenhouse. The online learning algorithm is used to continuously update the coupling coefficient, which specifically includes: Initialization: Based on historical data, the coupling coefficient β0 is determined using the initial regression model; Data input: The sensor network monitors environmental data in real time and inputs X(k); Recursive least squares method is used as the online learning algorithm to dynamically adjust the coupling coefficient according to the new data and the prediction results of the current model; S3, based on the multi-parameter coupling model, sets up the environmental control unit, and adjusts the temperature, humidity, light and carbon dioxide concentration parameters in the greenhouse in real time according to the analysis results of the multi-parameter coupling model to ensure that the environment is always in the optimal state during the wheat seedling cultivation process.

2. The growth monitoring method based on greenhouse wheat seedling cultivation according to claim 1, characterized in that: The S1 includes designing a sensor network layout according to the structure and spatial layout inside the greenhouse; the sensor network includes a temperature sensor, a humidity sensor, a light sensor and a carbon dioxide concentration sensor.

3. The growth monitoring method based on greenhouse wheat seedling cultivation according to claim 1, characterized in that: The sliding window method specifically includes: Set the length of the sliding window: Select the length of the sliding window , the moving step size of the sliding window represents the distance the window slides each time. Each sensor collects data once a minute, and the sliding window length is 5 minutes, that is, , the step length is 1 minute, that is , each sliding window contains 5 data points; Calculate features within the window: For each sliding window , respectively, from the temperature ,humidity , light intensity , CO2 concentration Extract statistical features, mean, standard deviation, maximum and minimum values ​​from the time series of data, and Combine the features extracted from .

4. The growth monitoring method based on greenhouse wheat seedling cultivation according to claim 1, characterized in that: The update rule of the recursive least squares method includes: Set the initial coupling coefficient vector and the covariance matrix , the coupling coefficient update rule is as follows: ,in, is the updated coupling coefficient vector, Indicated in The coupling coefficient for each time step is The coupling coefficient is transposed, is the target output at the current moment, is the input feature vector at the current moment, including the parameters and their interactions, is the gain matrix, which is used to control the weight of the model on historical data. The gain matrix controls the update step size of the model; Covariance matrix The update is expressed as: ,in, It is The covariance matrix of the step, is the transpose of the current input feature vector.

5. The growth monitoring method based on greenhouse wheat seedling cultivation according to claim 1, characterized in that: The S3 specifically includes: S31, collects real-time data on temperature, humidity, light intensity and carbon dioxide concentration in the greenhouse through a sensor network, and inputs the real-time data into a multi-parameter coupling model to analyze the difference between current environmental parameters and wheat growth requirements; S32, based on the multi-parameter coupling model, analyzing the current temperature, humidity, light intensity and carbon dioxide concentration and the mutual coupling relationship to predict the growth state of wheat, and adjusting the environmental parameter combination according to the prediction results until the optimal environmental parameter combination is determined; S33, based on the optimal combination of environmental parameters, control is performed through the environmental control unit.

6. The growth monitoring method based on greenhouse wheat seedling cultivation according to claim 5, characterized in that: After the S32 predicts the influence of the current parameters on the growth state of wheat, the combination optimization of the parameters is performed, and the optimal combination of parameters is found through the target optimization function to maximize the growth state of wheat. The target optimization function is to find the optimal combination of environmental parameters, which is converted into an optimization problem: The goal is to adjust , making wheat The growth status at any moment To achieve the optimal value, It is Temperature, humidity, light intensity, and carbon dioxide concentration parameters obtained from sensors at all times; Then, gradient optimization is a specific way to solve the objective optimization function. By calculating the gradient of the loss function with respect to each environmental parameter, each environmental parameter is gradually adjusted until the optimal parameter combination is found.

7. The growth monitoring method based on greenhouse wheat seedling cultivation according to claim 5, characterized in that: The control by the environment control unit specifically includes: Temperature regulation module: By controlling the heater or cooling device, the temperature in the greenhouse is adjusted in real time to maintain it within the optimal growth range of wheat; Humidity control module: According to the dynamic changes of humidity coupling coefficient, the spray system or ventilation system is adjusted to ensure that the humidity is suitable for wheat growth; Light control module: Control light intensity by adjusting the lighting system or adjusting the greenhouse shading equipment to maintain a light level suitable for wheat photosynthesis; Carbon dioxide concentration regulation module: According to the coupling relationship between light and carbon dioxide concentration, the carbon dioxide release device is controlled to promote the photosynthesis of wheat.

Images