Greenhouse planting environment intelligent management and control method and system based on crop model

Abstract

The invention discloses a greenhouse planting environment intelligent management and control method and system based on a crop model, and the method comprises the steps: obtaining the suitable range of a target crop variety for environment parameters in each growth stage, carrying out the preprocessing of an initial parameter, and obtaining the preprocessed environment parameter data; establishing a nonlinear mapping relation between the environmental parameters and crop growth states through a support vector machine regression method, and constructing a crop growth model; constructing a multi-objective optimization model based on the crop growth model, and obtaining environment parameter set values; transmitting the environment parameter set value to a greenhouse environment regulation and control system, regulating environment parameters in the greenhouse, feeding back growth state data to the crop growth model, and performing online updating and optimization to obtain an optimized crop growth model; and according to the optimized crop growth model, predicting the growth trend and the yield condition of the crop. According to the invention, dynamic optimization of facility crop growth and precise regulation and control of greenhouse water-soil-gas planting environments and the like are realized.

Description

Technical Field

[0001] The present invention relates to the field of information technology, and in particular to a method and system for intelligently controlling a greenhouse planting environment based on a crop model. Background Art

[0002] In the greenhouse planting environment intelligent control system, in order to achieve precise control of the crop growth environment, it is necessary to build a crop growth model that can accurately simulate and predict crop growth. The model needs to comprehensively consider the impact of multiple environmental parameters such as temperature, humidity, light, soil moisture, nutrients, etc. on crop growth in the facility greenhouse, and be able to quantify these impacts. However, due to the complexity and nonlinearity of the crop growth process, traditional modeling methods are difficult to meet the requirements of accuracy and real-time performance. At the same time, different crop varieties and growth stages have different requirements for environmental conditions, and how to reflect these differences in the model is also a difficulty. In addition, in practical applications, the environmental parameter data collected by sensors may have problems such as noise and outliers, and effective data cleaning and preprocessing are required to ensure the quality of model input data. The optimization algorithm based on the crop growth model also faces challenges. It is necessary to find the optimal combination of environmental parameters while meeting the needs of crop growth, taking into account factors such as energy consumption and cost. In short, how to build a robust, efficient, and interpretable crop growth model and organically combine it with the greenhouse environment control system is a key technical problem faced by the greenhouse planting environment intelligent control method and system. Summary of the invention

[0003] In order to solve the technical problems existing in the above-mentioned prior art, the present invention proposes a method and system for intelligent management and control of greenhouse planting environment based on crop model, which realizes precise regulation of greenhouse environment and dynamic optimization of crop growth, and effectively improves crop yield and resource utilization efficiency.

[0004] On the one hand, to achieve the above-mentioned purpose, the present invention provides a greenhouse planting environment intelligent management and control method based on a crop model, comprising:

[0005] Obtain the suitable range of environmental parameters for target crop varieties at each growth stage, pre-process the initial parameters, and obtain pre-processed environmental parameter data;

[0006] The nonlinear mapping relationship between environmental parameters and crop growth status is established through support vector machine regression method, and the crop growth model is constructed;

[0007] Building a multi-objective optimization model based on the crop growth model, solving the multi-objective optimization model, and obtaining environmental parameter setting values;

[0008] The environmental parameter setting value is transmitted to the greenhouse environmental control system to adjust the environmental parameters in the greenhouse, continuously collect growth status data, feed the growth status data back to the crop growth model, perform online updating and optimization, and obtain an optimized crop growth model;

[0009] The growth trend and yield of the crops are predicted based on the optimized crop growth model, and the environmental parameters are adjusted according to the output results until the ideal growth state and yield level are achieved.

[0010] On the other hand, to achieve the above-mentioned purpose, the present invention also provides a greenhouse planting environment intelligent management and control system based on a crop model, comprising:

[0011] The data acquisition module is used to obtain the suitable range of environmental parameters for the target crop varieties at each growth stage, pre-process the initial parameters, and obtain the pre-processed environmental parameter data;

[0012] The crop growth modeling module is used to establish a nonlinear mapping relationship between environmental parameters and crop growth status through the support vector machine regression method to construct a crop growth model;

[0013] A multi-objective optimization module, used to construct a multi-objective optimization model based on the crop growth model, solve the multi-objective optimization model, and obtain environmental parameter setting values;

[0014] The environmental control module is used to adjust the environmental parameters in the greenhouse according to the set values ​​of the environmental parameters, control the heating, ventilation, irrigation, lighting and fertilization equipment, and realize the precise adjustment of the environmental parameters in the greenhouse;

[0015] A model updating module, used for continuously collecting growth status data, feeding the growth status data back to the crop growth model, performing online updating and optimization, and obtaining an optimized crop growth model;

[0016] The growth prediction module is used to predict the growth trend and yield of crops according to the optimized crop growth model, and adjust environmental parameters according to the output results until the ideal growth state and yield level are achieved.

[0017] Compared with the prior art, the present invention has the following advantages and technical effects:

[0018] (1) The present invention constructs a crop growth model based on a pre-established crop growth parameter database combined with real-time collected environmental data. A nonlinear mapping relationship between environmental parameters and crop growth status is established through a support vector machine regression algorithm, and a genetic algorithm is used to solve a multi-objective optimization model to obtain the optimal environmental parameter combination. The system automatically adjusts the greenhouse environment according to the optimization results to create the best growth conditions for crops. At the same time, crop growth status data is continuously collected, and the model is updated and optimized online using an incremental learning algorithm to continuously improve the prediction accuracy. Based on the optimized model, the system can predict future crop growth trends and yields, and dynamically adjust environmental parameters according to the prediction results.

[0019] (2) Through intelligent algorithms and adaptive optimization, the present invention realizes the dynamic optimization of greenhouse crop growth and the precise regulation of greenhouse water-soil-air and other planting environments, effectively improving crop yields and resource utilization efficiency, and providing a new technical solution for the development of smart agriculture. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0021] Figure 1 This is a flow chart of a method for intelligent management and control of greenhouse planting environment based on a crop model according to an embodiment of the present invention;

[0022] Figure 2 The present invention is a schematic diagram of the structure of a greenhouse planting environment intelligent management and control system based on a crop model according to an embodiment of the present invention. DETAILED DESCRIPTION

[0023] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0024] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0025] This embodiment proposes a greenhouse planting environment intelligent management and control method based on crop models, such as Figure 1 ,include:

[0026] Obtain the suitable range of environmental parameters for target crop varieties at each growth stage, pre-process the initial parameters, and obtain pre-processed environmental parameter data;

[0027] The nonlinear mapping relationship between environmental parameters and crop growth status is established through support vector machine regression method, and the crop growth model is constructed;

[0028] Building a multi-objective optimization model based on the crop growth model, solving the multi-objective optimization model, and obtaining environmental parameter setting values;

[0029] The environmental parameter setting value is transmitted to the greenhouse environmental control system to adjust the environmental parameters in the greenhouse, continuously collect growth status data, feed the growth status data back to the crop growth model, perform online updating and optimization, and obtain an optimized crop growth model;

[0030] The growth trend and yield of the crops are predicted based on the optimized crop growth model, and the environmental parameters are adjusted according to the output results until the ideal growth state and yield level are achieved.

[0031] This embodiment builds a crop growth model based on a pre-established crop growth parameter database combined with real-time collected environmental data. A nonlinear mapping relationship between environmental parameters and crop growth status is established through a support vector machine regression algorithm, and a genetic algorithm is used to solve a multi-objective optimization model to obtain the optimal combination of environmental parameters. The greenhouse environment is automatically adjusted according to the optimization results to create the best growth conditions for crops. At the same time, crop growth status data is continuously collected, and the model is updated and optimized online using an incremental learning algorithm to continuously improve the prediction accuracy. Based on the optimized model, the system can predict future crop growth trends and yields, and dynamically adjust environmental parameters based on the prediction results.

[0032] Furthermore, the suitable range of environmental parameters for target crop varieties at each growth stage is obtained, the initial parameters are preprocessed, and the preprocessed environmental parameter data is obtained, including

[0033] For target crop varieties, obtain the suitable range of environmental parameters for target crops at different growth stages from the pre-established database of environmental parameters and crop growth relationships, including temperature, humidity, light, soil moisture and nutrient composition;

[0034] The Kalman filtering method is used to perform denoising on the initial parameters, eliminate outliers and random noise, and obtain pre-processed environmental parameter data.

[0035] Specifically, a database containing the relationship between environmental parameters and crop growth is established. Taking rice as an example, the database contains the suitable ranges of temperature, humidity, light, soil moisture, and nutrient composition for rice at different growth stages (such as sowing period, tillering period, heading period, etc.).

[0036] For the target crop varieties, the suitable range of environmental parameters at different growth stages is obtained from the database, including temperature, humidity, light, soil moisture, nutrient composition and other parameters. The obtained suitable range is used as the initial parameter of the crop growth model to simulate and predict the growth of crops under different environmental conditions.

[0037] The Kalman filter algorithm is used for denoising. The Kalman filter algorithm recursively estimates and updates the data by establishing state equations and observation equations, and uses the fusion of system state prediction and observation values ​​to filter out outliers and random noise in the data. After the Kalman filter algorithm is processed, the cleaned environmental parameter data such as temperature, humidity, light intensity, soil moisture, and nutrient composition are obtained. The cleaned data is stored in the database for subsequent data analysis and application.

[0038] Furthermore, a crop growth model is constructed, including:

[0039] According to different crop varieties and growth stages, corresponding support vector machine regression models are established.

[0040] Using the support vector machine regression model, the environmental parameter data is predicted to obtain the predicted value of the growth state of the crop under the current environmental conditions;

[0041] The predicted value of crop growth status is compared with the actual crop growth status data collected, and the model prediction error is calculated. If the model prediction error exceeds the preset threshold, the kernel function type and parameters of the support vector machine regression model are readjusted, and the updated model is used to predict the crop growth status again until the prediction error meets the requirements and the establishment of the crop growth model is completed.

[0042] Specifically, for different crop varieties and growth stages, a corresponding support vector machine regression model is established to fit the nonlinear mapping relationship between environmental parameters and crop growth status. When establishing the support vector machine regression model, the appropriate kernel function type is selected according to the growth stage of the crop. If the crop is in the early growth stage, a linear kernel function is selected; if the crop is in the middle and late growth stage, a Gaussian kernel function is selected. For the support vector machine regression model using the Gaussian kernel function, by analyzing the crop growth rate data, the parameters of the Gaussian kernel function are dynamically adjusted to adapt it to the crop growth rate, thereby improving the fitting accuracy of the model. The established support vector machine regression model is used to predict the environmental parameter data to obtain the predicted value of the growth status of the crop under the current environmental conditions. The predicted value of the crop growth status is compared with the actual collected crop growth status data, and the error of the model prediction is calculated to evaluate the fitting effect of the support vector machine regression model. If the model prediction error exceeds the preset threshold, the kernel function type and parameters of the support vector machine regression model are readjusted, and the crop growth status is predicted again using the updated model until the prediction error meets the requirements, and the establishment of the crop growth model is completed.

[0043] This kind of model-based precision management can significantly improve crop yield and quality. Continuous updating and optimization of the model is also important. As the seasons change or new varieties are introduced, the model may need to be retrained or fine-tuned. By regularly collecting new growth data and incorporating it into the model training process, you can ensure that the model always maintains high accuracy and adapts to changing planting conditions and crop characteristics.

[0044] Furthermore, a multi-objective optimization model is constructed based on the crop growth model, and the multi-objective optimization model is solved to obtain environmental parameter setting values, including:

[0045] Determining key environmental parameters that affect crop growth and yield based on the crop growth model;

[0046] Constructing a multi-objective optimization model with maximizing crop yield and minimizing energy consumption cost as objective functions, and taking the key environmental parameters as optimization variables;

[0047] The multi-objective optimization model is solved by using a genetic algorithm. In an iterative process, the crop growth model is used to simulate the crop growth process, predict the crop yield, and calculate the corresponding energy consumption cost according to the current environmental parameter combination;

[0048] By comparing the crop yields and energy consumption costs corresponding to different environmental parameter combinations, the environmental parameter combination with the best comprehensive performance is selected as the optimization result of the genetic algorithm;

[0049] The set values ​​of temperature, humidity, light intensity, soil moisture and nutrient composition are extracted through the optimal environmental parameter group as target parameters for environmental control in actual production.

[0050] Specifically, according to the crop growth model, the key environmental parameters affecting crop growth and yield are determined, including temperature, humidity, light intensity, soil moisture, nutrient composition, etc. A multi-objective optimization model with maximizing crop yield and minimizing energy consumption cost as the objective function is constructed, and the determined key environmental parameters are used as optimization variables. The constructed multi-objective optimization model is solved by a genetic algorithm, and the combination of environmental parameters is continuously optimized through operations such as selection, crossover and mutation until the set termination condition is met. In the iterative process of the genetic algorithm, according to the current environmental parameter combination, the crop growth process is simulated using the crop growth model, the crop yield is predicted, and the corresponding energy consumption cost is calculated. By comparing the crop yield and energy consumption cost corresponding to different environmental parameter combinations, the environmental parameter combination with better comprehensive performance is selected as the optimization result of the genetic algorithm. From the optimal environmental parameter combination obtained by the genetic algorithm, the set values ​​of temperature, humidity, light intensity, soil moisture and nutrient composition are extracted as the target parameters for environmental control in actual production. The optimized environmental parameter setting values ​​are applied to the actual crop production process. The temperature, humidity, light intensity, soil moisture and nutrient composition are adjusted through the environmental control system to maximize crop yield and minimize energy consumption costs.

[0051] Furthermore, a genetic algorithm is used to solve the constructed multi-objective optimization model, including:

[0052] S1, determine the optimization objective function and constraints, and encode the environmental parameter combination into individuals of the genetic algorithm;

[0053] S2, randomly generate an initial population, each individual corresponds to a set of environmental parameter combinations, and the corresponding parameter combination is obtained by decoding the encoded information of the individual;

[0054] S3, substituting the parameter combination of each individual into the multi-objective optimization model for solving, and obtaining the fitness value of the individual, wherein the higher the fitness value, the better the parameter combination;

[0055] S4, performing selection operations according to the fitness values ​​of the individuals, randomly pairing the selected individuals, and generating new individuals through crossover operations;

[0056] S5, perform mutation operation on the newly generated individuals, randomly change some bits of the individual code, and introduce new parameter values;

[0057] S6. Add the newly generated individual to the population and repeat steps S3-S6 until the termination condition is met. The parameter combination corresponding to the individual with the highest fitness value in the population is the optimal solution.

[0058] Specifically, the optimization objective function and constraint conditions are determined according to the multi-objective optimization model, and the environmental parameter combination is encoded as an individual of the genetic algorithm. The initial population is randomly generated, and each individual corresponds to a set of environmental parameter combinations. The corresponding parameter combination is obtained by decoding the encoded information of the individual. The parameter combination of each individual is substituted into the optimization model for solution to obtain the fitness value of the individual. The higher the fitness value, the better the parameter combination. The selection operation is performed according to the fitness value of the individual, and the individual with a higher fitness value has a greater probability of being selected. A certain number of individuals are selected by means of roulette or the like. The selected individuals are randomly paired, and new individuals are generated by crossover operation. The crossover operation includes single-point crossover, multi-point crossover, etc., which exchange part of the codes of two individuals. The newly generated individuals are mutated, and some bits of the individual codes are randomly changed, new parameter values ​​are introduced, and the diversity of the population is increased. The newly generated individuals are added to the population, and the above steps are repeated until the termination condition is met. The termination condition can be that the maximum number of iterations is reached or the fitness value reaches a threshold, etc. The parameter combination corresponding to the individual with the highest fitness value in the population finally obtained is the optimal solution.

[0059] Furthermore, the environmental parameter setting value is transmitted to the greenhouse environment control system to adjust the environmental parameters in the greenhouse, including:

[0060] Obtain preset environmental parameter settings, including target value ranges for temperature, humidity, and light parameters;

[0061] The greenhouse environmental parameters are collected in real time through sensors deployed in the greenhouse, and the real-time greenhouse environmental parameters are compared with the preset environmental parameter setting values;

[0062] If the real-time environmental parameters exceed the set value range, the greenhouse environmental control system will calculate the control instructions of each regulating device according to the deviation, and send the generated control instructions to the corresponding heating, ventilation, irrigation, lighting and fertilization equipment. Each device will make corresponding action adjustments according to the received control instructions.

[0063] After adjustment, the greenhouse environment control system obtains the real-time environmental parameter data collected by the sensor again to determine whether it reaches the set value range, and performs the next round of adjustment and control based on the feedback until the environmental parameters stabilize within the set range, providing the optimal environment for crop growth.

[0064] Specifically, preset environmental parameter setting values ​​are obtained, including target value ranges of parameters such as temperature, humidity, and light; greenhouse environmental parameters are collected in real time through sensors deployed in the greenhouse, and the collected data are transmitted to the greenhouse environmental control system; the greenhouse environmental control system receives the real-time environmental parameter data collected by the sensors and compares it with the preset environmental parameter setting values; if the real-time environmental parameters exceed the set value range, the greenhouse environmental control system calculates the control instructions of each adjustment device according to the deviation; the greenhouse environmental control system sends the generated control instructions to the corresponding heating, ventilation, irrigation, supplementary lighting, fertilization and other equipment; each device performs corresponding action adjustments according to the received control instructions, such as adjusting the heating power, ventilation time, irrigation amount, supplementary lighting intensity, fertilizer amount, etc.; after a period of adjustment, the greenhouse environmental control system obtains the real-time environmental parameter data collected by the sensors again, determines whether it reaches the set value range, and performs the next round of adjustment and control according to the feedback, until the environmental parameters are stabilized within the set range, providing the best environment for crop growth.

[0065] The core of greenhouse environmental control is to achieve precise control. Its operation process is rigorous and efficient, and it provides an ideal growth environment for crops. First, it is necessary to obtain the preset environmental parameter setting values, which are based on the growth needs and optimization goals of specific crops. For example, for thermophilic crops such as tomatoes, the optimal growth temperature may be set between 20°C and 28°C, and the relative humidity may be controlled between 60% and 80%. In terms of light intensity, it may be set at 300 to 600 micromoles per square meter per second according to the needs of tomatoes at different growth stages. The settings of these parameters are not static, but need to be adjusted according to actual conditions. For example, in rainy weather, the setting value of light intensity can be appropriately reduced to save energy. In order to grasp the environmental conditions in the greenhouse in real time, various sensors need to be deployed in the greenhouse. For example, temperature and humidity sensors are installed at different heights and corners of the greenhouse to comprehensively monitor the temperature and humidity distribution in the greenhouse. This can avoid the impact of crop growth due to local temperature or humidity abnormalities. Light sensors are usually installed near the crop canopy to accurately measure the actual light intensity received by the crop. The soil moisture sensor is inserted into the soil to monitor the moisture content of the soil and guide the operation of the irrigation system. For example, when the soil moisture sensor detects that the soil moisture content is less than 15%, it can be determined that irrigation is needed. The greenhouse environment control system is the "brain" of the entire system. It is responsible for receiving and processing the data collected by the sensor and comparing it with the preset environmental parameter setting values. This process is ongoing to ensure that the environmental parameters are always in the best state. For example, if the system receives data from the temperature sensor of 18°C, which is lower than the preset lower limit of 20°C, the system will determine that heating is required. If the real-time humidity is 85%, which is higher than the set upper limit of 80%, the system determines that ventilation is required. When the real-time environmental parameters exceed the set value range, the greenhouse environment control system will calculate the control instructions of each regulating device according to the preset control logic and algorithm. The control logic is formulated based on the crop growth model and environmental control experience, while the algorithm can be optimized according to the specific control objectives. For example, if the temperature is lower than the set value, the system may calculate the power adjustment instructions of the heating equipment based on the temperature difference, such as increasing the heating power by 20%. If the humidity is higher than the set value, the system may calculate the opening time of the ventilation equipment based on the humidity difference, such as opening the ventilation for 15 minutes. After the control instructions are generated, the greenhouse environment control system will send these instructions to the corresponding execution devices. For example, the heating power adjustment instruction is sent to the heater, the ventilation time instruction is sent to the ventilator, the irrigation amount instruction is sent to the irrigation system, and the fill light intensity instruction is sent to the fill light. These devices perform corresponding actions according to the instructions received to adjust the greenhouse environment. After the execution device adjusts according to the instructions, the greenhouse environment will gradually tend to the set value. The greenhouse environment control system will again obtain the real-time environmental parameter data collected by the sensor and compare it with the set value.If the environmental parameters still exceed the set value range, the system will perform the next round of adjustment control until the environmental parameters stabilize within the set range. For example, after a period of heating, the temperature sensor data becomes 22°C, which is within the set range, and the system stops the heating command. After a period of ventilation, the humidity sensor data becomes 75%, which is within the set range, and the system stops the ventilation command. This repetitive adjustment process ensures that the greenhouse environment is always in the most suitable state for crop growth, thereby improving crop yield and quality, and achieving the goal of energy saving and consumption reduction.

[0066] Furthermore, the growth status data is continuously collected and fed back to the crop growth model for online updating and optimization to obtain an optimized crop growth model, including:

[0067] Continuously collecting new crop growth status data, inputting the new data into the crop growth model, and using an incremental learning algorithm to update model parameters online;

[0068] By comparing the actual crop growth status data with the predicted results, the model prediction error is calculated. When the prediction error exceeds the preset threshold, the model optimization process is triggered. By adjusting the model hyperparameters and optimizing the network structure, the optimized crop growth model is obtained.

[0069] Specifically, environmental parameter data, including temperature, humidity, light intensity, etc., are obtained through sensors. According to the preset crop growth environment threshold, it is judged whether the current environment is suitable for crop growth. If the environmental parameters exceed the threshold range, the environmental adjustment device is triggered to adjust the environmental parameters to the optimal range. During the crop growth process, computer vision technology is used to collect crop images in real time through cameras, and the images are segmented and feature extracted to obtain growth status data such as crop height and leaf area. The crop leaf image is input into the chlorophyll content estimation model, and the chlorophyll content of the leaf is judged through the convolutional neural network algorithm to obtain the crop chlorophyll content data. The collected growth status data such as crop height, leaf area, chlorophyll content, etc. are stored in the growth status database in chronological order to form crop growth status time series data. According to the crop growth status time series data, the long short-term memory network (LSTM) algorithm is used to establish a crop growth prediction model, and the prediction results of crop growth trend and expected yield are obtained through model training. During the crop growth process, new growth status data is continuously collected and input into the crop growth prediction model. The incremental learning algorithm is used to update the model parameters online so that the model can adapt to the dynamic changes of crop growth and improve the prediction accuracy. By comparing the difference between the actual crop growth status data and the prediction results, the model prediction error is calculated. When the prediction error exceeds the preset threshold, the model optimization process is triggered to further improve the prediction performance of the crop growth model by adjusting the model hyperparameters and optimizing the network structure.

[0070] Further, the environmental parameters are adjusted according to the output results, including:

[0071] If the prediction result of the crop growth model meets the preset yield target, the current environmental parameter setting is maintained; if the prediction result of the crop growth model is lower than the expected yield, the optimization algorithm is re-triggered, and the environmental parameters that need to be adjusted are determined based on the analysis results of the optimization algorithm. The environmental parameters are automatically adjusted to reach the ideal set values ​​determined by the optimization algorithm; the crop growth status and yield forecast are continuously monitored until the ideal growth status and expected yield level are reached.

[0072] Specifically, the optimized crop growth model is built based on the long short-term memory network (LSTM) algorithm, which can effectively capture the time series characteristics of crop growth. When the model is applied to the growth trend and yield prediction for the next 7 days, the current environmental parameters and crop growth status data need to be input. For example, for tomato crops, the model may predict that the plant height will increase by 10 cm, the leaf area will increase by 15%, and the expected yield will be 4 kg per plant in the next 7 days. Comparison of the predicted results with the preset yield target is a key step in judging the growth status of crops. Assuming that the preset tomato yield target is 5 kg per plant, and the predicted result is 4 kg, it means that the current growth status has not met expectations. At this time, it is necessary to trigger the optimization algorithm to analyze the key environmental factors affecting crop growth. The optimization algorithm may use multiple regression analysis or machine learning methods, such as random forest algorithms, to determine the main factors affecting tomato yield. The analysis results may show that light intensity and temperature are the two most critical factors affecting tomato growth. Specifically, the current light intensity may be low, while the temperature is slightly above the optimal range. Based on the analysis results, the intelligent control system automatically adjusts the environmental parameters. For example, the light intensity is increased from the original 20,000 lux to 25,000 lux, while the temperature is reduced from 28°C to 25°C. These adjustments are designed to create a more ideal growth environment for tomatoes, promote photosynthesis, and increase yields. After the environmental parameters are adjusted, the system will continue to monitor the crop growth status and yield forecast. This process may take several days to several weeks until the crop reaches the ideal growth state and expected yield level. During this period, the system will continue to collect new growth data, update the growth model, and make further environmental adjustments as needed. The advantage of this dynamic optimization process is that it can respond to crop growth needs in a timely manner and maximize yield potential. Through continuous data collection and model updates, the system is able to continuously improve prediction accuracy and environmental control precision. This not only helps to increase crop yields, but also optimize resource utilization, reduce energy consumption and environmental impact.

[0073] This embodiment also provides a greenhouse planting environment intelligent management and control system based on crop models, such as Figure 2 ,include:

[0074] The data acquisition module is used to obtain the suitable range of environmental parameters for the target crop varieties at each growth stage, pre-process the initial parameters, and obtain the pre-processed environmental parameter data;

[0075] The crop growth modeling module is used to establish a nonlinear mapping relationship between environmental parameters and crop growth status through the support vector machine regression method to construct a crop growth model;

[0076] A multi-objective optimization module, used to construct a multi-objective optimization model based on the crop growth model, solve the multi-objective optimization model, and obtain environmental parameter setting values;

[0077] The environmental control module is used to adjust the environmental parameters in the greenhouse according to the set values ​​of the environmental parameters, control the heating, ventilation, irrigation, lighting and fertilization equipment, and realize the precise adjustment of the environmental parameters in the greenhouse;

[0078] A model updating module, used for continuously collecting growth status data, feeding the growth status data back to the crop growth model, performing online updating and optimization, and obtaining an optimized crop growth model;

[0079] The growth prediction module is used to predict the growth trend and yield of crops according to the optimized crop growth model, and adjust environmental parameters according to the output results until the ideal growth state and yield level are achieved.

[0080] The above are only preferred specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A greenhouse planting environment intelligent management and control method based on crop model, characterized in that: include: Obtain the suitable range of environmental parameters for target crop varieties at each growth stage, pre-process the initial parameters, and obtain pre-processed environmental parameter data; The nonlinear mapping relationship between environmental parameters and crop growth status is established through support vector machine regression method, and the crop growth model is constructed; Building a multi-objective optimization model based on the crop growth model, solving the multi-objective optimization model, and obtaining environmental parameter setting values; The environmental parameter setting value is transmitted to the greenhouse environmental control system to adjust the environmental parameters in the greenhouse, continuously collect growth status data, feed the growth status data back to the crop growth model, perform online updating and optimization, and obtain an optimized crop growth model; The growth trend and yield of the crops are predicted based on the optimized crop growth model, and the environmental parameters are adjusted according to the output results until the ideal growth state and yield level are achieved.

2. The method for intelligent management and control of greenhouse planting environment based on crop model according to claim 1, characterized in that: Obtain the suitable range of environmental parameters for target crop varieties at each growth stage, pre-process the initial parameters, and obtain the pre-processed environmental parameter data, including For target crop varieties, obtain the suitable range of environmental parameters for target crops at different growth stages from the pre-established database of environmental parameters and crop growth relationships, including temperature, humidity, light, soil moisture and nutrient composition; The Kalman filtering method is used to perform denoising on the initial parameters, eliminate outliers and random noise, and obtain pre-processed environmental parameter data.

3. The method for intelligent management and control of greenhouse planting environment based on crop model according to claim 1, characterized in that: Constructing the crop growth model includes: According to different crop varieties and growth stages, corresponding support vector machine regression models are established. Using the support vector machine regression model, the environmental parameter data is predicted to obtain the predicted value of the growth state of the crop under the current environmental conditions; The predicted value of crop growth status is compared with the actual crop growth status data collected, and the model prediction error is calculated. If the model prediction error exceeds the preset threshold, the kernel function type and parameters of the support vector machine regression model are readjusted, and the updated model is used to predict the crop growth status again until the prediction error meets the requirements and the establishment of the crop growth model is completed.

4. The method for intelligent management and control of greenhouse planting environment based on crop model according to claim 3 is characterized in that: When establishing the corresponding support vector machine regression model, the appropriate kernel function type is selected according to the growth stage of the crop. If the crop is in the early growth stage, the linear kernel function is selected; if the crop is in the middle and late growth stage, the Gaussian kernel function is selected.

5. The method for intelligent management and control of greenhouse planting environment based on crop model according to claim 1, characterized in that: A multi-objective optimization model is constructed based on the crop growth model, and the multi-objective optimization model is solved to obtain environmental parameter setting values, including: Determining key environmental parameters that affect crop growth and yield based on the crop growth model; Constructing a multi-objective optimization model with maximizing crop yield and minimizing energy consumption cost as objective functions, and taking the key environmental parameters as optimization variables; The multi-objective optimization model is solved by using a genetic algorithm. In an iterative process, the crop growth model is used to simulate the crop growth process, predict the crop yield, and calculate the corresponding energy consumption cost according to the current environmental parameter combination; By comparing the crop yields and energy consumption costs corresponding to different environmental parameter combinations, the environmental parameter combination with the best comprehensive performance is selected as the optimization result of the genetic algorithm; The set values ​​of temperature, humidity, light intensity, soil moisture and nutrient composition are extracted through the optimal environmental parameter group as target parameters for environmental control in actual production.

6. The method for intelligent management and control of greenhouse planting environment based on crop model according to claim 1, characterized in that: Genetic algorithm is used to solve the constructed multi-objective optimization model, including: S1, determine the optimization objective function and constraints, and encode the environmental parameter combination into individuals of the genetic algorithm; S2, randomly generate an initial population, each individual corresponds to a set of environmental parameter combinations, and the corresponding parameter combination is obtained by decoding the encoded information of the individual; S3, substituting the parameter combination of each individual into the multi-objective optimization model for solving, and obtaining the fitness value of the individual, wherein the higher the fitness value, the better the parameter combination; S4, performing a selection operation according to the fitness value of the individual, randomly pairing the selected individuals, and generating new individuals through a crossover operation; S5, perform mutation operation on the newly generated individuals, randomly change some bits of the individual code, and introduce new parameter values; S6. Add the newly generated individual to the population and repeat steps S3-S6 until the termination condition is met. The parameter combination corresponding to the individual with the highest fitness value in the population is the optimal solution.

7. The method for intelligent management and control of greenhouse planting environment based on crop model according to claim 1, characterized in that: The environmental parameter setting value is transmitted to the greenhouse environmental control system to adjust the environmental parameters in the greenhouse, including: Obtain preset environmental parameter settings, including target value ranges for temperature, humidity, and light parameters; The greenhouse environmental parameters are collected in real time through sensors deployed in the greenhouse, and the real-time greenhouse environmental parameters are compared with the preset environmental parameter setting values; If the real-time environmental parameters exceed the set value range, the greenhouse environmental control system will calculate the control instructions of each regulating device according to the deviation, and send the generated control instructions to the corresponding heating, ventilation, irrigation, lighting and fertilization equipment. Each device will make corresponding action adjustments according to the received control instructions. After adjustment, the greenhouse environment control system obtains the real-time environmental parameter data collected by the sensor again to determine whether it reaches the set value range, and performs the next round of adjustment and control based on the feedback until the environmental parameters stabilize within the set range, providing the optimal environment for crop growth.

8. The method for intelligent management and control of greenhouse planting environment based on crop model according to claim 1, characterized in that: Continuously collect growth status data, feed the growth status data back to the crop growth model, perform online updates and optimizations, and obtain an optimized crop growth model, including: Continuously collecting new crop growth status data, inputting the new data into the crop growth model, and using an incremental learning algorithm to update model parameters online; By comparing the actual crop growth status data with the predicted results, the model prediction error is calculated. When the prediction error exceeds the preset threshold, the model optimization process is triggered. By adjusting the model hyperparameters and optimizing the network structure, the optimized crop growth model is obtained.

9. The method for intelligent management and control of greenhouse planting environment based on crop model according to claim 8, characterized in that: Adjust the environment parameters according to the output results, including: If the prediction result of the crop growth model meets the preset yield target, the current environmental parameter setting is maintained; if the prediction result of the crop growth model is lower than the expected yield, the optimization algorithm is re-triggered, and the environmental parameters that need to be adjusted are determined based on the analysis results of the optimization algorithm. The environmental parameters are automatically adjusted to reach the ideal set values ​​determined by the optimization algorithm; the crop growth status and yield forecast are continuously monitored until the ideal growth status and expected yield level are reached.

10. An intelligent management and control system for greenhouse planting environment based on crop model, characterized in that: include: The data acquisition module is used to obtain the suitable range of environmental parameters for the target crop varieties at each growth stage, pre-process the initial parameters, and obtain the pre-processed environmental parameter data; The crop growth modeling module is used to establish a nonlinear mapping relationship between environmental parameters and crop growth status through the support vector machine regression method to construct a crop growth model; A multi-objective optimization module, used to construct a multi-objective optimization model based on the crop growth model, solve the multi-objective optimization model, and obtain environmental parameter setting values; The environmental control module is used to adjust the environmental parameters in the greenhouse according to the set values ​​of the environmental parameters, control the heating, ventilation, irrigation, lighting and fertilization equipment, and realize the precise adjustment of the environmental parameters in the greenhouse; A model updating module, used for continuously collecting growth status data, feeding the growth status data back to the crop growth model, performing online updating and optimization, and obtaining an optimized crop growth model; The growth prediction module is used to predict the growth trend and yield of crops according to the optimized crop growth model, and adjust environmental parameters according to the output results until the ideal growth state and yield level are achieved.

Images