Intelligent adjusting system for agricultural planting greenhouse

Abstract

The invention relates to the technical field of agricultural planting greenhouse intelligent adjusting systems, and discloses an agricultural planting greenhouse intelligent adjusting system which comprises a data collecting and monitoring module, and the output end of the data collecting and monitoring module is in communication connection with a data processing and prediction analysis module. The output end of the data processing and prediction analysis module is in communication connection with a decision support system, the output end of the decision support system is in communication connection with a user interaction interface, and the output end of the user interaction interface is in communication connection with an execution and feedback module. According to the intelligent adjusting system for the agricultural planting greenhouse, a plurality of modules such as data collection, data processing, decision support, user interaction and execution and feedback are highly integrated in one system, automation and intelligence of greenhouse planting are achieved, and the intelligent adjusting system is high in practicability through an intelligent decision engine and a machine learning platform. The environment requirement of the greenhouse can be analyzed according to the monitoring data and the historical data.

Description

Technical Field

[0001] The invention relates to the technical field of intelligent regulating systems for agricultural planting greenhouses, and in particular to an intelligent regulating system for agricultural planting greenhouses. Background Art

[0002] The intelligent regulation system for agricultural greenhouses is a system that uses modern information technology, such as the Internet of Things, big data analysis, cloud computing, and artificial intelligence, to provide intelligent management and automatic control for crop growth in greenhouses. However, existing systems are often limited to collecting and adjusting basic environmental parameters, and lack comprehensive analysis of information such as soil health and plant growth status, resulting in the inability to achieve comprehensive environmental control. In addition, most systems fail to predict future climate changes or the occurrence of pests and diseases, and cannot adjust environmental settings in advance to optimize growth conditions. Summary of the invention

[0003] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0004] To achieve the above object, the present invention provides the following technical solutions: An intelligent adjustment system for an agricultural greenhouse includes a data collection and monitoring module, the output end of the data collection and monitoring module is communicatively connected to a data processing and prediction analysis module, the output end of the data processing and prediction analysis module is communicatively connected to a decision support system, the output end of the decision support system is communicatively connected to a user interaction interface, and the output end of the user interaction interface is communicatively connected to an execution and feedback module.

[0005] As a further solution of the present invention: the data collection and monitoring module includes an environmental sensor, a soil sensor, a plant growth monitor and a data acquisition terminal, as follows: Environmental sensors: including temperature sensors, humidity sensors, light intensity sensors, and CO2 concentration sensors; Soil sensors: soil moisture sensor, soil pH sensor and soil nutrient analyzer; Plant growth monitor: high-resolution stereo camera and plant physiological and biochemical indicator sensors; Data acquisition terminal: responsible for collecting all sensor data and performing preliminary data formatting and cleaning.

[0006] As a further solution of the present invention: the data processing and predictive analysis module includes a central server, analysis software and a machine learning platform, and the decision support system includes an intelligent decision engine, an operation and control interface and a strategy database.

[0007] As a further solution of the present invention: the user interaction interface includes a mobile application and a notification system, the execution and feedback module includes a control execution unit and a state feedback sensor, and the control execution unit also includes an electric window controller, an irrigation system, a temperature and humidity control system, and auxiliary lighting equipment.

[0008] As a further solution of the present invention: In the machine learning platform, I use a multivariate regression analysis algorithm, which is as follows: Suppose we need to predict and control the temperature (Y) of a greenhouse based on some key environmental and operational variables such as the outside temperature (X1), humidity (X2), CO2 concentration (X3), and the previous day’s inside temperature (X4); Build a multiple linear regression model to predict the internal temperature of a greenhouse: ; Among them: Y is the dependent variable, which represents the temperature inside the greenhouse; X1, X2, X3, and X4 are independent variables, which represent the external temperature, humidity, CO2 concentration, and the internal temperature of the previous day, respectively; β0, β1, β2, β3, and β4 are model parameters, which represent the degree of influence of each variable on the dependent variable; ϵ is the error term, which represents the random variation that the model cannot explain.

[0009] As a further solution of the present invention: the specific model of the sensor is as follows: Temperature sensor model Honeywell T10, humidity sensor model Sensirion SHT35, light intensity sensor model Apogee MQ-500, CO2 concentration sensor model SenseAir S8, soil moisture sensor model DecagonDevices EC-5, soil pH sensor model Spectrum Technologies FieldScout SoilStik pHMeter, and soil nutrient analyzer model Horiba LAQUAtwin; The plant growth monitor uses a high-resolution stereo camera, the specific model of which is Microsoft KinectAzure; The specific model of the plant physiological and biochemical index sensor is CID CI-340 Handheld Photosynthesis System; The specific model of the data acquisition terminal is National Instruments CompactDAQ.

[0010] As a further solution of the present invention: the random forest algorithm is used inside the decision support system, which is as follows: Sample selection: Use bootstrap sampling to obtain N samples from the training data set D; Feature selection: For each node, m features are randomly selected from all features, where (M is the total number of features), select the best split feature; Tree construction: Each tree is grown to its maximum depth without pruning. Prediction function: For classification problems, majority voting is used, and for regression problems, average output is used; Information gain calculation when splitting a node: ; in: is the information gain of the feature at the parent node Dp, I(D) is the impurity of the dataset D (such as Gini impurity or entropy), Nleft and Nright are the number of samples in the left and right subsets after the split, and Dleft and Dright are the left and right sub-datasets after the split.

[0011] Compared with the prior art, the present invention has the following beneficial effects: The present invention highly integrates multiple modules such as data collection, data processing, decision support, user interaction, execution and feedback into one system, realizing the automation and intelligence of greenhouse cultivation. Through the intelligent decision-making engine and machine learning platform, the present invention can analyze the environmental requirements of the greenhouse according to monitoring data and historical data, and perform precise environmental adjustments in real time. At the same time, the present invention has a large amount of advanced planting strategies and historical adjustment data, which provides rich data support for the machine learning platform and intelligent decision-making engine, so that the system can make decisions more accurately. The present invention provides an intuitive user operation interface, through which the user can manually adjust the greenhouse environment, or automatically adjust it through intelligent recommendations, which greatly reduces the difficulty of user operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 A schematic diagram of a system module of an intelligent regulation system for an agricultural greenhouse; Figure 2 This is a schematic diagram of the system principle of a data collection and monitoring module in an intelligent adjustment system for an agricultural greenhouse. DETAILED DESCRIPTION

[0013] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and understandable, the specific implementation modes of the present invention are described in detail below in conjunction with the accompanying drawings.

[0014] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0015] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments. Example

[0016] See also Figure 1-2 , is an embodiment of the present invention, which provides an intelligent adjustment system for an agricultural greenhouse, including a data collection and monitoring module, the output end of the data collection and monitoring module is communicatively connected to a data processing and prediction analysis module, the output end of the data processing and prediction analysis module is communicatively connected to a decision support system, the output end of the decision support system is communicatively connected to a user interaction interface, and the output end of the user interaction interface is communicatively connected to an execution and feedback module.

[0017] Specifically, the data collection and monitoring module includes environmental sensors, soil sensors, plant growth monitors, and data acquisition terminals, as follows: Environmental sensors: including temperature sensors, humidity sensors, light intensity sensors, and CO2 concentration sensors; Soil sensors: soil moisture sensor, soil pH sensor and soil nutrient analyzer; Plant growth monitor: high-resolution stereo camera and plant physiological and biochemical indicator sensors; Data acquisition terminal: responsible for collecting all sensor data and performing preliminary data formatting and cleaning.

[0018] Furthermore, by deploying a variety of sensors, the system can comprehensively monitor and collect key indicators of the environment, soil and plant growth conditions in the greenhouse, providing detailed basic data for subsequent data analysis and adjustment. The data acquisition terminal can collect sensor data in real time and determine whether to trigger an alarm or automatically adjust greenhouse environmental parameters through preset thresholds to ensure the stability and optimization of the crop growth environment. By monitoring soil moisture, pH value, nutrients, and plant physiological and biochemical indicators, it can provide accurate nutrition and management for crops, thereby improving crop growth efficiency and yield.

[0019] Specifically, the data processing and predictive analysis module includes a central server, analysis software, and a machine learning platform, and the decision support system includes an intelligent decision engine, an operation and control interface, and a strategy database.

[0020] Furthermore, the central server can centrally process and store large amounts of data to ensure the real-time and accuracy of the data. The analysis software further processes the data, extracts useful information, and provides support for decision-making. With the help of machine learning platforms and advanced analysis algorithms, it can accurately predict the environment and crop growth trends in the greenhouse, providing a scientific basis for management decisions. The intelligent decision-making engine can respond quickly based on real-time and historical data, and put forward targeted management suggestions and operational guidance.

[0021] Specifically, the user interaction interface includes mobile applications and notification systems, the execution and feedback module includes a control execution unit and a state feedback sensor, and the control execution unit also includes an electric window controller, an irrigation system, a temperature and humidity control system, and auxiliary lighting equipment.

[0022] Furthermore, mobile applications enable users to monitor and control the greenhouse environment anytime and anywhere through mobile devices such as smartphones or tablets, improving user convenience and interactivity. The control execution unit can accurately control the equipment in the greenhouse, such as electric windows, irrigation systems, temperature and humidity control systems, and auxiliary lighting equipment, based on user input or instructions automatically generated by the system.

[0023] Specifically, in the machine learning platform, I use the multivariate regression analysis algorithm, which is as follows: Suppose we need to predict and control the temperature (Y) of a greenhouse based on some key environmental and operational variables such as the outside temperature (X1), humidity (X2), CO2 concentration (X3), and the previous day’s inside temperature (X4); Build a multiple linear regression model to predict the internal temperature of a greenhouse: ; Among them: Y is the dependent variable, which represents the temperature inside the greenhouse; X1, X2, X3, and X4 are independent variables, which represent the external temperature, humidity, CO2 concentration, and the internal temperature of the previous day, respectively; β0, β1, β2, β3, and β4 are model parameters, which represent the degree of influence of each variable on the dependent variable; ϵ is the error term, which represents the random variation that the model cannot explain.

[0024] Furthermore, the model trained with historical data can predict the temperature in the greenhouse in the future, allowing greenhouse managers to make adjustments in advance to maintain the optimal temperature for crop growth. Constant temperature helps reduce the occurrence of diseases, because extreme temperatures may make crops more susceptible to diseases. Combining real-time data and model predictions can achieve rapid response and adjustment, and correct temperature deviations in a timely manner.

[0025] Specifically, the specific models of the sensors are as follows: Temperature sensor model Honeywell T10, humidity sensor model Sensirion SHT35, light intensity sensor model Apogee MQ-500, CO2 concentration sensor model SenseAir S8, soil moisture sensor model DecagonDevices EC-5, soil pH sensor model Spectrum Technologies FieldScout SoilStik pHMeter, and soil nutrient analyzer model Horiba LAQUAtwin; The plant growth monitor uses a high-resolution stereo camera, the specific model of which is Microsoft KinectAzure; The specific model of the plant physiological and biochemical index sensor is CID CI-340 Handheld PhotosynthesisSystem; The specific model of the data acquisition terminal is National Instruments CompactDAQ.

[0026] Specifically, the random forest algorithm is used within the decision support system, which is as follows: Sample selection: Use bootstrap sampling to obtain N samples from the training data set D; Feature selection: For each node, m features are randomly selected from all features, where (M is the total number of features), select the best split feature; Tree construction: Each tree is grown to its maximum depth without pruning. Prediction function: For classification problems, majority voting is used, and for regression problems, average output is used; Information gain calculation when splitting a node: ; in: is the information gain of the feature at the parent node Dp, I(D) is the impurity of the dataset D (such as Gini impurity or entropy), Nleft and Nright are the number of samples in the left and right subsets after the split, and Dleft and Dright are the left and right sub-datasets after the split.

[0027] Furthermore, by constructing multiple decision trees and performing voting or average predictions, random forests can effectively reduce the risk of overfitting of a single decision tree and improve the generalization ability of the model. Random forests can capture nonlinear relationships in the data and usually show high prediction accuracy in polynomial regression, classification and other complex problems. Random forests are highly robust to noisy data, and even if the data contains a certain amount of noise, it will not have much impact on the prediction results of the model.

[0028] When in use, environmental sensors (temperature, humidity, light intensity, CO2 concentration), soil sensors (soil moisture, pH, nutrients) and plant growth monitors (high-resolution stereo cameras, plant physiological and biochemical indicator sensors) monitor the environmental conditions and plant growth conditions in the greenhouse in real time. The data acquisition terminal is responsible for collecting all sensor data and performing preliminary data formatting and cleaning. The central server receives the raw data from the data acquisition terminal and performs data processing and predictive analysis through analysis software and machine learning platforms. The multivariate regression analysis algorithm is used to predict the internal temperature (Y) of the greenhouse based on variables such as external temperature (X1), humidity (X2), CO2 concentration (X3) and the internal temperature (X4) of the previous day. The intelligent decision-making engine generates the best adjustment suggestions based on the analysis results of the machine learning platform and uses advanced algorithms such as the random forest algorithm. The operation and control interface is provided to the The user's intuitive and convenient operation method enables users to quickly implement the recommendations of the decision support system. The strategy database stores a large number of previous decision cases and historical data, providing a reference and learning basis for future decisions. The mobile application and notification system allow users to view real-time data, predictive analysis results and decision suggestions, and perform necessary operations. Users can adjust the environmental conditions of the greenhouse through the interface, such as controlling windows, irrigation systems, temperature and humidity control systems, and auxiliary lighting equipment. The control execution unit receives user instructions and adjusts various equipment in the greenhouse to optimize environmental conditions. The state feedback sensor monitors the adjusted environmental conditions in real time and feeds data back to the data collection and monitoring module to form a closed-loop control. The system continuously collects data, analyzes and executes decisions, and uses machine learning algorithms to continuously optimize prediction models and decision strategies to improve the efficiency of greenhouse management and the quality of plant growth.

[0029] In summary, by highly integrating multiple modules such as data collection, data processing, decision support, user interaction, execution and feedback into one system, the automation and intelligence of greenhouse cultivation is realized. Through the intelligent decision-making engine and machine learning platform, the present invention can analyze the environmental requirements of the greenhouse according to monitoring data and historical data, and perform precise environmental adjustments in real time. At the same time, the present invention has a large amount of advanced planting strategies and historical adjustment data, which provides rich data support for the machine learning platform and intelligent decision-making engine, so that the system can make decisions more accurately. The present invention provides an intuitive user operation interface, through which the user can manually adjust the greenhouse environment, or automatically adjust it through intelligent recommendations, which greatly reduces the difficulty of user operation.

[0030] Importantly, it should be noted that the construction and arrangement of the present application shown in a number of different exemplary embodiments are only exemplary. Although only a few embodiments are described in detail in this disclosure, it should be readily understood by those who refer to this disclosure that many modifications are possible (e.g., the size, scale, structure, shape and proportion of various elements, and parameter values ​​(e.g., temperature, pressure, etc.), mounting arrangements, use of materials, color, changes in orientation, etc.) without substantially departing from the novel teachings and advantages of the subject matter described in the application. For example, an element shown as integrally formed may be composed of multiple parts or elements, the position of the element may be inverted or otherwise changed, and the nature or number or position of the discrete element may be altered or changed. Therefore, all such modifications are intended to be included within the scope of the present invention. The order or sequence of any process or method steps may be changed or reordered according to an alternative embodiment. In the claims, any "device plus function" clause is intended to cover the structure described herein that performs the function, and is not only structurally equivalent but also equivalent structure. Other substitutions, modifications, changes and omissions may be made in the design, operating conditions and arrangement of the exemplary embodiments without departing from the scope of the present invention. Therefore, the invention is not limited to a specific embodiment, but extends to numerous modifications still falling within the scope of the appended claims.

[0031] Additionally, in order to provide a concise description of exemplary embodiments, all features of an actual embodiment may not be described (ie, those features that are not relevant to the best mode presently contemplated for carrying out the invention or those features that are not relevant to implementing the invention).

[0032] It will be appreciated that in the development of any actual implementation, as in any engineering or design project, numerous implementation-specific decisions may be made. Such a development effort may be complex and time-consuming, but will be a routine task of design, fabrication, and production for those of ordinary skill having the benefit of this disclosure without undue experimentation.

[0033] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An intelligent regulation system for agricultural greenhouses, including a data collection and monitoring module, characterized in that: The output end of the data collection and monitoring module is communicatively connected to the data processing and prediction analysis module, the output end of the data processing and prediction analysis module is communicatively connected to the decision support system, the output end of the decision support system is communicatively connected to the user interaction interface, and the output end of the user interaction interface is communicatively connected to the execution and feedback module.

2. The intelligent adjustment system for agricultural greenhouse according to claim 1 is characterized in that: The data collection and monitoring module includes an environmental sensor, a soil sensor, a plant growth monitor and a data acquisition terminal, as follows: Environmental sensors: including temperature sensors, humidity sensors, light intensity sensors, and CO2 concentration sensors; Soil sensors: soil moisture sensor, soil pH sensor and soil nutrient analyzer; Plant growth monitor: high-resolution stereo camera and plant physiological and biochemical indicator sensors; Data acquisition terminal: responsible for collecting all sensor data and performing preliminary data formatting and cleaning.

3. The intelligent adjustment system for agricultural greenhouse according to claim 1 is characterized in that: The data processing and predictive analysis module includes a central server, analysis software and a machine learning platform, and the decision support system includes an intelligent decision engine, an operation and control interface and a strategy database.

4. The intelligent adjustment system for agricultural greenhouse according to claim 1, characterized in that: The user interaction interface includes a mobile application and a notification system, the execution and feedback module includes a control execution unit and a state feedback sensor, and the control execution unit also includes an electric window controller, an irrigation system, a temperature and humidity control system, and auxiliary lighting equipment.

5. The intelligent adjustment system for agricultural greenhouse according to claim 3 is characterized in that: In the machine learning platform, I use a multivariate regression analysis algorithm, which is as follows: Suppose we need to predict and control the temperature (Y) of a greenhouse based on some key environmental and operational variables such as the outside temperature (X1), humidity (X2), CO2 concentration (X3), and the previous day’s internal temperature (X4); A multivariate linear regression model was established to predict the internal temperature of the greenhouse: Y = β0 + β1X1 + β2X2 + β3X3 + β4X4 + ∈; Among them: Y is the dependent variable, which represents the temperature inside the greenhouse; X1, X2, X3, and X4 are independent variables, representing the external temperature, humidity, CO2 concentration, and the internal temperature of the previous day, respectively; β0, β1, β2, β3, and β4 are model parameters, representing the degree of influence of each variable on the dependent variable; ∈ is the error term, which represents the random variation that the model cannot explain.

6. The intelligent adjustment system for agricultural greenhouse according to claim 2, characterized in that: The specific models of the sensors are as follows: Temperature sensor model Honeywell T10, humidity sensor model Sensirion SHT35, light intensity sensor model Apogee MQ-500, CO2 concentration sensor model SenseAir S8, soil moisture sensor model DecagonDevices EC-5, soil pH sensor model Spectrum Technologies FieldScout SoilStik pHMeter, and soil nutrient analyzer model Horiba LAQUAtwin; The plant growth monitor uses a high-resolution stereo camera, and its specific model is Microsoft KinectAzure; The specific model of the plant physiological and biochemical index sensor is CID CI-340 Handheld Photosynthesis System; The specific model of the data acquisition terminal is National Instruments CompactDAQ.

7. The intelligent adjustment system for agricultural greenhouse according to claim 3 is characterized by: The decision support system internally uses the random forest algorithm, which is as follows: Sample selection: Obtain N samples from the training data set D by bootstrap sampling; Feature selection: For each node, randomly select m features from all features, where m << M (M is the total number of features), and select the best splitting feature; Tree construction: Each tree is grown to the maximum depth as much as possible without pruning; Prediction function: For classification problems, use the majority voting method, and for regression problems, use the average output; Calculation of information gain when splitting nodes: Among them: IG(D p ,f) is the information gain of the feature at the parent node Dp, I(D) is the impurity of the dataset D (such as Gini impurity or entropy), Nleft and Nright are the number of samples in the left and right subsets after the split, and Dleft and Dright are the left and right sub-datasets after the split.

Images