Intelligent greenhouse with intelligent monitoring system and use method thereof

Abstract

The invention relates to the field of intelligent agriculture, and particularly discloses an intelligent greenhouse with an intelligent monitoring system and a use method thereof, the intelligent greenhouse comprises an environment observation module, a data transmission module, a data storage module, an environment data analysis module, a greenhouse equipment control module, a crop image analysis module and a crop growth analysis module; according to the intelligent greenhouse of the intelligent monitoring system and the use method of the intelligent greenhouse, through collection and analysis of greenhouse environment data and crop data, an optimization prediction algorithm is provided, greenhouse environment data in future time is predicted, work of equipment in the greenhouse is controlled, crop images are segmented, and crop growth conditions are identified and analyzed; and taking corresponding measures to regulate and control the growth of the crops based on the identified growth condition.

Description

Technical Field

[0001] The present invention relates to the field of smart agriculture, and in particular to a smart greenhouse with an intelligent monitoring system and a method of using the same. Background Art

[0002] With the rapid development of information technology and intelligent technology, traditional agricultural production methods are often limited by natural environmental conditions and human resources. Farmers often need to spend a lot of time and energy on monitoring, managing crops and operating agricultural equipment. At the same time, due to the lack of real-time monitoring and precise control of traditional agricultural production methods, they are often easily affected by factors such as weather changes, pests and diseases, resulting in low crop yields and unstable quality. Therefore, there is an urgent need for a new type of intelligent agricultural production method that can achieve accurate monitoring and intelligent management of the crop growth environment and improve agricultural production efficiency and quality.

[0003] Therefore, smart greenhouse technology is of great significance in improving agricultural production efficiency and quality, but there are still some limitations and shortcomings in practical applications. First, the accuracy of sensors currently used in smart greenhouse systems is limited and cannot meet the needs of accurate monitoring of greenhouse environments and crop growth processes. For example, the measurement accuracy of temperature and humidity sensors may be biased, resulting in inaccurate monitoring results, affecting subsequent data analysis and decision-making. Secondly, smart greenhouse systems need to process a large amount of real-time monitoring data and image data, as well as perform complex data analysis and algorithm calculations. However, the data processing capabilities of current smart greenhouse systems are relatively weak, and cannot meet the requirements for real-time data processing and rapid response, resulting in limited accuracy and practicality of data analysis results.

[0004] In addition, the current intelligent control algorithms in smart greenhouse systems do not yet have a fully mature solution for the complexity and variability of greenhouse environments and crop growth processes. Current intelligent control algorithms are often based on simple rules or empirical models, lacking pertinence and flexibility, resulting in unstable control effects and unable to meet the needs of different environmental conditions and crop varieties. The construction and operation and maintenance costs of smart greenhouse systems are high, limiting their promotion and application in agricultural production.

[0005] In summary, the shortcomings of the current smart greenhouse technology restrict its further application and development in agricultural production. Therefore, it is necessary to propose a new type of smart greenhouse technology to overcome the limitations of existing technology, further improve the efficiency and quality of agricultural production, and promote the sustainable development of agriculture. Summary of the invention

[0006] The purpose of the present invention is to provide a smart greenhouse with an intelligent monitoring system and a method of using the same, aiming to solve the problems mentioned in the above background.

[0007] In order to achieve the above-mentioned purpose, the present invention proposes a smart greenhouse with an intelligent monitoring system and a method of using the same, including an environmental observation module, a data transmission module, a data storage module, an environmental data analysis module, a greenhouse equipment control module, a crop image analysis module, and a crop growth analysis module; the environmental observation module monitors the greenhouse environment and crops by installing sensors and cameras; the data transmission module transmits the monitoring data wirelessly; the data storage module stores the received data; the environmental data analysis module proposes an optimization prediction algorithm to predict the environmental data situation in the future based on the collected environmental data; the greenhouse equipment control module controls the operation of agricultural equipment in the greenhouse according to the greenhouse environmental situation; the crop image analysis module proposes a crop image analysis algorithm to accurately identify crop images; the crop growth analysis module analyzes and judges the growth status of crops by analyzing crop images.

[0008] Furthermore, the environmental observation module collects greenhouse environmental data through sensors, and the greenhouse environmental data includes greenhouse air temperature data, greenhouse air humidity data, greenhouse soil temperature data, greenhouse soil humidity data, greenhouse carbon dioxide concentration data, greenhouse light intensity data, and greenhouse soil pH data; and monitors crops through high-definition cameras.

[0009] Furthermore, the data transmission module uses wireless communication technology to transmit the data collected by the environment observation module stably and at high speed through the network.

[0010] Furthermore, the data storage module uses encryption operations through the data storage server to encrypt and store the received data, and perform multiple backup operations of the data.

[0011] Furthermore, the prediction algorithm is optimized, a prediction network model is constructed, and through multi-objective optimization, the parameters in the prediction network are updated, the prediction network model is trained, and the environmental data is predicted.

[0012] Further, multi-objective optimization is performed to update the parameters in the prediction network. The detailed process is as follows: Based on the collected environmental data, a prediction network is constructed. The training network is divided into an input network, a cache network, and an output network. The environmental data is divided into two parts, one of which is defined as a training data set. , used to train the prediction network, and a part of it is used as a validation data set to verify the prediction network. The training data set is input into the input network of the training network. The training data set input into the input network is expressed as follows: , in, Represents the training data set The first number in the training data set The second number in the training data set The Number, training data set The The number of training data sets input is calculated and input into the cache network. The value of each node in the cache network is expressed as follows: , in, Represents the cache network The value of a network node, Indicates the input network The value and cache network The weights between network nodes, Represents the total number of network nodes in the training data set. The values ​​of the cached network nodes are calculated again as the output of the output network. The calculation formula is expressed as: , in, Represents the output network The value of a network node, Indicates the cache network The value and output network The weights between network nodes, Represents the cache network The value of a network node, Represents the total number of network nodes in the cache network. Using multi-objective optimization, an optimized population is constructed. The weights between the input network and the cache network and the weights between the cache network and the output network are used as individuals in the optimized population. Individuals are moved and updated in the optimized population for optimization. The formula for the movement and update speed of individuals in the population is expressed as follows: , in, represents the first The individual in Mobile update speed in the sub-optimization phase, represents the first The individual in Mobile update speed in the sub-optimization phase, represents the first The individual in Inertia parameters in the sub-optimization stage, represents the first The individual in The learning parameters in the sub-optimization phase, represents the first The individual in The best position of the neighborhood in the sub-optimization stage, represents the first The individual in The global optimal position in the sub-optimization stage. During the optimization process, individuals will exchange data with each other during the mobile update process. The data exchange is related to the individual mobile update speed and position. The data exchange function is as follows: , in, Represents an individual and individuals In the Data exchange function in the sub-optimization stage, Indicates the exchange parameters, Represents an individual No. The position of the sub-optimization stage, Represents an individual No. The position of the sub-optimization stage, represents the first The individual in Mobile update speed in the sub-optimization phase, Represents the shape coefficient, and the data exchange function represents the data exchange between individuals. Based on the data exchange function, the optimization degree of individuals is calculated as follows: , in, Represents an individual No. The optimization degree of the sub-optimization stage, It represents the total number of data exchange functions. During the optimization process, the optimal position individuals and optimization degree are retained each time. The output network outputs and the input network are used to check the optimization accuracy. The individual movement updates are continuously performed. The optimization process is iterated to train the prediction network. When the optimization accuracy is reached, each individual represents the weight in the prediction network. The training of the prediction network is completed. The prediction data is verified for the trained prediction network using the verification data set. The optimization prediction algorithm proposed in the present invention constructs a three-layer prediction network model of input network, cache network, and output network, defines the weights between each prediction network layer, constructs an optimization population through multi-objective optimization, calculates the individual movement update speed in the optimization population, calculates the individual optimization degree based on the exchange function between individuals, optimizes the weights, and realizes the training of the prediction network. Compared with the traditional prediction algorithm, the optimization prediction algorithm proposed in this paper introduces individual optimization to optimize the weights, thereby improving the accuracy of data prediction.

[0013] Furthermore, the greenhouse equipment control module automatically controls the corresponding equipment to operate for abnormal environmental data based on the predictive analysis results of the greenhouse environmental data, performs greenhouse environmental management, and keeps the greenhouse environmental data fluctuations within the range acceptable to crops.

[0014] Furthermore, the crop image analysis algorithm performs image segmentation by dividing the segmentation area and blurring the pixels.

[0015] Furthermore, the detailed process of image segmentation is as follows: For the image data of crops, firstly, a local segmentation area is taken at the segmentation boundary, where the pixel value is used to represent the pixel point of the local segmentation area, which is expressed as follows: ,in, Represents the pixel value matrix of the local segmentation area, The pixel values ​​of the pixel points in the first row and first column of the local segmentation area and the pixel values ​​of the pixel points in the first row and first column of the local segmentation area are represented respectively. The pixel value of the pixel point in the column, the local segmentation area The pixel value of the pixel point in the first column of the row, the pixel value of the local segmentation area Line The pixel value of the pixel point in the column, the local segmentation area Line The pixel values ​​of the pixels in the column define a fuzzy segmentation set In the fuzzy segmentation set, the first value is the smallest pixel value in the local segmentation area, and the last value is the largest pixel value in the local segmentation area. In addition to the first and last values, the fuzzy segmentation set The values ​​are expressed as: , in, Represents the fuzzy segmentation set values, Representation Matrix The minimum value in Representation Matrix The maximum value in , based on the fuzzy segmentation set, the pixels in the local segmentation area are mapped to the fuzzy segmentation set, and the mapping result is the value in the fuzzy segmentation set closest to the pixel value of the corresponding pixel point. By mapping the pixels in the local segmentation area, the pixel values ​​of the pixels in the local segmentation area are fuzzified, and based on the fuzzification result, the fuzzy pixel values ​​are corrected to calculate the fuzzy segmentation index of the local segmentation area. The calculation formula is as follows: , in, Represents the fuzzy segmentation index of the local segmentation area, is a counting function that calculates the number of pixels in the local segmentation area. represents the approximation function, Indicates the total number of rows in the local segmentation area. Represents the total number of local segmentation area columns, taking the closest fuzzy segmentation set The median value is calculated based on the fuzzy index to calculate the correlation between pixels. The calculation formula is as follows: , in, Represents pixel The degree of association with points in the neighborhood, Represents the local segmentation area Line The pixel values ​​of the pixels in the column are divided based on the correlation of the pixels to complete the image segmentation process. The crop image analysis algorithm proposed in the present invention defines a fuzzy segmentation set, fuzzifies the pixel values ​​of the divided local segmentation area, calculates the fuzzy segmentation index based on the fuzzification result, obtains the correlation between the pixels, divides the pixels based on the correlation, and segments the image. The crop image analysis algorithm proposed in the present invention fuzzily processes the pixels and then divides the image based on the correlation. Compared with traditional image segmentation, it can improve the speed of image segmentation under the premise of a certain segmentation accuracy.

[0016] Furthermore, the crop growth analysis module uses crop image recognition results and network data to analyze and determine whether the current growth status of crops has reached the expected growth status. For crops that have not reached the expected growth status, corresponding measures are taken to regulate the growth status.

[0017] A method for using a smart greenhouse with an intelligent monitoring system. First, an environmental observation module collects greenhouse environmental data and crop images through sensors and cameras. Then, a data transmission module transmits the greenhouse environmental data and crop images through a wireless network. Then, a data storage module stores the received greenhouse environmental data and crop images. Then, an environmental data analysis module predicts environmental data conditions in the future based on the collected environmental data. Then, a greenhouse equipment control module predicts data based on greenhouse environmental conditions and controls the operation of agricultural equipment in the greenhouse. Then, a crop image analysis module segments and identifies crop images. Finally, a crop growth analysis module takes corresponding measures for the growth conditions of crops based on the results of crop image analysis.

[0018] The beneficial effects of the present invention are as follows: 1. The optimization prediction algorithm proposed in the environmental data analysis module of the present invention constructs a three-layer prediction network model of input network, cache network and output network, defines the weights between each prediction network layer, constructs an optimization population through multi-objective optimization, calculates the individual movement update speed in the optimization population, calculates the individual optimization degree based on the exchange function between individuals, optimizes the weights, and realizes the training of the prediction network. Compared with the traditional prediction algorithm, the optimization prediction algorithm proposed in this paper introduces individual optimization to optimize the weights, thereby improving the accuracy of data prediction; 2. The crop image analysis algorithm proposed by the crop image analysis module of the present invention defines a fuzzy segmentation set, performs fuzzy processing on the pixel values ​​of the divided local segmented areas, calculates the fuzzy segmentation index based on the fuzzification result, obtains the correlation between the pixels, divides the pixels based on the correlation, and segments the image. The crop image analysis algorithm proposed by the present invention fuzzily processes the pixels and then divides the image based on the correlation. Compared with traditional image segmentation, it can improve the speed of image segmentation under the premise of a certain segmentation accuracy. The smart greenhouse of the intelligent monitoring system proposed by the present invention and its use method can realize precise control of the crop growth process by real-time monitoring of the greenhouse environment and crop growth, and automatically adjusting the environmental conditions and agricultural equipment in the greenhouse. In this way, farmers no longer need to monitor and adjust manually for a long time, which greatly improves the efficiency of agricultural production. 3. The smart greenhouse system of the present invention can realize real-time monitoring and precise control of environmental parameters in the greenhouse, avoiding the environmental pollution problems that may be caused by traditional agricultural production methods. By reducing the use of chemical substances such as pesticides and fertilizers, it can reduce pollution to soil and water sources and promote the sustainable development of agricultural production; through automation technology and intelligent management, it can reduce labor costs and improve the economic benefits of agricultural production. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings in the following description are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0020] Figure 1 This is a diagram of the smart greenhouse system of the present invention. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] See also Figure 1 In order to achieve the above-mentioned purpose, the present invention proposes a smart greenhouse with an intelligent monitoring system and a method of using the same, including an environment observation module, a data transmission module, a data storage module, an environment data analysis module, a greenhouse equipment control module, a crop image analysis module, and a crop growth analysis module; the environment observation module monitors the greenhouse environment and crops by installing sensors and cameras; the data transmission module transmits the monitoring data wirelessly; the data storage module stores the received data; the environment data analysis module proposes an optimization prediction algorithm to predict the environment data situation in the future based on the collected environment data; the greenhouse equipment control module controls the operation of agricultural equipment in the greenhouse according to the greenhouse environment; the crop image analysis module proposes a crop image analysis algorithm to accurately identify crop images; the crop growth analysis module analyzes and judges the growth status of crops by analyzing crop images.

[0023] The environmental observation module collects greenhouse environmental data through sensors, including greenhouse air temperature data, greenhouse air humidity data, greenhouse soil temperature data, greenhouse soil humidity data, greenhouse carbon dioxide concentration data, greenhouse light intensity data, and greenhouse soil pH data; and monitors crops through high-definition cameras. The data transmission module uses wireless communication technology to transmit the data collected by the environmental observation module stably and quickly through the network.

[0024] The data storage module uses encryption operations to encrypt and store the received data through the data storage server, and performs multiple data backup operations. Optimize the prediction algorithm, build a prediction network model, update the parameters in the prediction network through multi-objective optimization, train the prediction network model, and predict the environmental data. The detailed process is as follows: Based on the collected environmental data, build a prediction network, and divide the training network into input network, cache network, and output network. The environmental data is divided into two parts, one of which is defined as the training data set training , used to train the prediction network, and a part of it is used as a validation data set to verify the prediction network. The training data set is input into the input network of the training network. The training data set input into the input network is expressed as follows: , in, Represents the training data set The first number in the training data set The second number in the training data set The Number, training data set The The number of training data sets input is calculated and input into the cache network. The value of each node in the cache network is expressed as follows: , in, Represents the cache network The value of a network node, Indicates the input network The value and cache network The weights between network nodes, Represents the total number of network nodes in the training data set. The values ​​of the cached network nodes are calculated again as the output of the output network. The calculation formula is expressed as: , in, Represents the output network The value of a network node, Indicates the cache network The value and output network The weights between network nodes, Represents the cache network The value of a network node, Represents the total number of network nodes in the cache network. Using multi-objective optimization, an optimized population is constructed. The weights between the input network and the cache network and the weights between the cache network and the output network are used as individuals in the optimized population. Individuals are moved and updated in the optimized population for optimization. The formula for the movement and update speed of individuals in the population is expressed as follows: , in, represents the first The individual in Mobile update speed in the sub-optimization phase, represents the first The individual in Mobile update speed in the sub-optimization phase, represents the first The individual in Inertia parameters in the sub-optimization stage, represents the first The individual in The learning parameters in the sub-optimization phase, represents the first The individual in The best position of the neighborhood in the sub-optimization stage, represents the first The individual in The global optimal position in the sub-optimization stage. During the optimization process, individuals will exchange data with each other during the mobile update process. The data exchange is related to the individual mobile update speed and position. The data exchange function is as follows: , in, Represents an individual and individuals In the Data exchange function in the sub-optimization stage, Indicates the exchange parameters, Represents an individual No. The position of the sub-optimization stage, Represents an individual No. The position of the sub-optimization stage, represents the first The individual in Mobile update speed in the sub-optimization phase, Represents the shape coefficient, and the data exchange function represents the data exchange between individuals. Based on the data exchange function, the optimization degree of individuals is calculated as follows: , in, Represents an individual No. The optimization degree of the sub-optimization stage, It represents the total number of data exchange functions. During the optimization process, the best position individuals and optimization degree are retained each time. The optimization accuracy is checked through the output network output and input network. The individual movement updates are continuously performed. The optimization process is iterated and the prediction network is trained. When the optimization accuracy is reached, each individual represents the weight in the prediction network. The training of the prediction network is completed. For the trained prediction network, the prediction data is verified using the verification data set.

[0025] See also Figure 1 Specifically, the greenhouse equipment control module automatically controls the corresponding equipment to work for abnormal environmental data based on the prediction and analysis results of the greenhouse environmental data, performs greenhouse environmental management, and keeps the fluctuation of greenhouse environmental data within the acceptable range for crops.

[0026] See also Figure 1Specifically, the crop image analysis algorithm performs image segmentation by dividing the segmentation area and blurring the pixels. The detailed process is as follows: For crop image data, firstly, we take the local segmentation area at the segmentation boundary, where the pixel value is used to represent the pixel point of the local segmentation area, as shown below: ,in, Represents the pixel value matrix of the local segmentation area, The pixel values ​​of the pixel points in the first row and first column of the local segmentation area and the pixel values ​​of the pixel points in the first row and first column of the local segmentation area are represented respectively. The pixel value of the pixel point in the column, the local segmentation area The pixel value of the pixel point in the first column of the row, the pixel value of the local segmentation area Line The pixel value of the pixel point in the column, the local segmentation area Line The pixel values ​​of the pixels in the column define a fuzzy segmentation set In the fuzzy segmentation set, the first value is the smallest pixel value in the local segmentation area, and the last value is the largest pixel value in the local segmentation area. In addition to the first and last values, the fuzzy segmentation set The values ​​are expressed as: , in, Represents the fuzzy segmentation set values, Representation Matrix The minimum value in Representation Matrix The maximum value in , based on the fuzzy segmentation set, the pixels in the local segmentation area are mapped to the fuzzy segmentation set, and the mapping result is the value in the fuzzy segmentation set closest to the pixel value of the corresponding pixel point. By mapping the pixels in the local segmentation area, the pixel values ​​of the pixels in the local segmentation area are fuzzified, and based on the fuzzification result, the fuzzy pixel values ​​are corrected to calculate the fuzzy segmentation index of the local segmentation area. The calculation formula is as follows: , in, Represents the fuzzy segmentation index of the local segmentation area, is a counting function that calculates the number of pixels in the local segmentation area. represents the approximation function, Indicates the total number of rows in the local segmentation area. Represents the total number of local segmentation area columns, taking the closest fuzzy segmentation set The median value is calculated based on the fuzzy index to calculate the correlation between pixels. The calculation formula is as follows: , in, Represents pixel The degree of association with points in the neighborhood, Represents the local segmentation area Line The pixel values ​​of the pixels in the column are divided based on the correlation of the pixels to complete the image segmentation process.

[0027] The crop growth analysis module uses crop image recognition results and network data to analyze and determine whether the current growth status of crops has reached the expected growth status. For crops that have not reached the expected growth status, corresponding measures are taken to regulate the growth status.

[0028] In the specific implementation, first, the environmental observation module collects greenhouse environmental data and crop images through sensors and cameras, and then the data transmission module transmits the greenhouse environmental data and crop images through a wireless network. Then, the data storage module stores the received greenhouse environmental data and crop images. Then, the environmental data analysis module predicts the environmental data conditions in the future based on the collected environmental data. Then, the greenhouse equipment control module controls the operation of agricultural equipment in the greenhouse according to the greenhouse environmental conditions prediction data. Then, the crop image analysis module segments and identifies the crop images. Finally, the crop growth analysis module takes corresponding measures on the growth conditions of crops based on the crop image analysis results.

[0029] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.

Claims

1. A smart greenhouse with an intelligent monitoring system, characterized in that: It includes an environmental observation module, a data transmission module, a data storage module, an environmental data analysis module, a greenhouse equipment control module, a crop image analysis module and a crop growth analysis module; the environmental observation module monitors the greenhouse environment and crops by installing sensors and cameras; the data transmission module transmits the monitoring data wirelessly; the data storage module performs multiple backup storage of the received data through a storage server; the environmental data analysis module proposes an optimization prediction algorithm to predict the environmental data conditions in the future based on the collected environmental data; the greenhouse equipment control module controls the operation of agricultural equipment in the greenhouse according to the greenhouse environmental conditions; the crop image analysis module proposes a crop image analysis algorithm to analyze and identify crop images; the crop growth analysis module takes corresponding measures for the growth of crops by analyzing crop images.

2. The smart greenhouse with an intelligent monitoring system according to claim 1, characterized in that: The environmental observation module collects greenhouse environmental data through sensors, and the greenhouse environmental data includes greenhouse air temperature data, greenhouse air humidity data, greenhouse soil temperature data, greenhouse soil humidity data, greenhouse carbon dioxide concentration data, greenhouse light intensity data, and greenhouse soil pH data; and monitors crops through high-definition cameras.

3. The smart greenhouse with an intelligent monitoring system according to claim 1, characterized in that: The data transmission module uses wireless communication technology to transmit the data collected by the environment observation module through the network.

4. The smart greenhouse with an intelligent monitoring system according to claim 1, characterized in that: The optimization prediction algorithm constructs a prediction network model, updates the parameters in the prediction network through multi-objective optimization, trains the prediction network model, and predicts environmental data.

5. The smart greenhouse with an intelligent monitoring system according to claim 4 is characterized in that: The multi-objective optimization updates the parameters in the prediction network. The detailed process is as follows: Based on the collected environmental data, a prediction network is constructed. The training network is divided into an input network, a cache network, and an output network. The environmental data is divided into two parts, one of which is defined as a training data set. , used to train the prediction network, and a part of it is used as a validation data set to verify the prediction network. The training data set is input into the input network of the training network. The training data set input into the input network is expressed as follows: ， in, Represents the training data set The first number in the training data set The second number in the training data set The Number, training data set The The number of training data sets input is calculated and input into the cache network. The value of each node in the cache network is expressed as follows: ， in, Represents the cache network The value of a network node, Indicates the input network The value and cache network The weights between network nodes, Represents the total number of network nodes in the training data set. The values ​​of the cached network nodes are calculated again as the output of the output network. The calculation formula is expressed as: ， in, Represents the output network The value of a network node, Indicates the cache network The value and output network The weights between network nodes, Represents the cache network The value of a network node, Represents the total number of network nodes in the cache network. Using multi-objective optimization, an optimized population is constructed. The weights between the input network and the cache network and the weights between the cache network and the output network are used as individuals in the optimized population. Individuals are moved and updated in the optimized population for optimization. The formula for the movement and update speed of individuals in the population is expressed as follows: ， in, represents the number of optimized populations The individual in Mobile update speed in the sub-optimization phase, represents the first The individual in Mobile update speed in the sub-optimization phase, represents the number of optimized populations The individual in Inertia parameters in the sub-optimization stage, represents the first The individual in The learning parameters in the sub-optimization phase, represents the number of optimized populations The individual in The best position of the neighborhood in the sub-optimization stage, represents the number of optimized populations The individual in The global optimal position in the sub-optimization stage. During the optimization process, individuals will exchange data with each other during the mobile update process. The data exchange is related to the individual mobile update speed and position. The data exchange function is as follows: ， in, Represents an individual and individuals In the Data exchange function in the sub-optimization stage, Indicates the exchange parameters, Represents an individual No. The position of the sub-optimization stage, Represents an individual No. The position of the sub-optimization stage, represents the number of optimized populations The individual in Mobile update speed in the sub-optimization phase, Represents the shape coefficient, and the data exchange function represents the data exchange between individuals. Based on the data exchange function, the optimization degree of individuals is calculated as follows: ， in, Represents an individual No. The optimization degree of the sub-optimization stage, It represents the total number of data exchange functions. During the optimization process, the best position individuals and optimization degree are retained each time. The optimization accuracy is checked through the output network output and input network. The individual movement updates are continuously performed. The optimization process is iterated and the prediction network is trained. When the optimization accuracy is reached, each individual represents the weight in the prediction network. The training of the prediction network is completed. For the trained prediction network, the prediction data is verified using the verification data set.

6. The smart greenhouse with an intelligent monitoring system according to claim 1, characterized in that: The greenhouse equipment control module automatically controls corresponding equipment to work for abnormal environmental data based on the prediction and analysis results of the greenhouse environmental data, performs greenhouse environmental management, and keeps the fluctuation of greenhouse environmental data within the range acceptable to crops.

7. The smart greenhouse with an intelligent monitoring system according to claim 1, characterized in that: The crop image analysis algorithm performs image segmentation by dividing the segmentation area and blurring the pixel points.

8. The smart greenhouse with intelligent monitoring system according to claim 7, characterized in that: The detailed process of image segmentation is as follows: For crop image data, firstly, we take the local segmentation area at the segmentation boundary, where the pixel value is used to represent the pixel point of the local segmentation area, as shown below: ,in, Represents the pixel value matrix of the local segmentation area, The pixel values ​​of the pixel points in the first row and first column of the local segmentation area and the pixel values ​​of the pixel points in the first row and first column of the local segmentation area are represented respectively. The pixel value of the pixel point in the column, the local segmentation area The pixel value of the pixel point in the first column of the row, the pixel value of the local segmentation area Line The pixel value of the pixel point in the column, the local segmentation area Line The pixel values ​​of the pixels in the column define a fuzzy segmentation set In the fuzzy segmentation set, the first value is the smallest pixel value in the local segmentation area, and the last value is the largest pixel value in the local segmentation area. In addition to the first and last values, the fuzzy segmentation set The values ​​are expressed as: ， in, Represents the fuzzy segmentation set values, Representation Matrix The minimum value in Representation Matrix The maximum value in , based on the fuzzy segmentation set, the pixels in the local segmentation area are mapped to the fuzzy segmentation set, and the mapping result is the value in the fuzzy segmentation set closest to the pixel value of the corresponding pixel point. By mapping the pixels in the local segmentation area, the pixel values ​​of the pixels in the local segmentation area are fuzzified, and based on the fuzzification result, the fuzzy pixel values ​​are corrected to calculate the fuzzy segmentation index of the local segmentation area. The calculation formula is as follows: ， in, Represents the fuzzy segmentation index of the local segmentation area, is a counting function that calculates the number of pixels in the local segmentation area. represents the approximation function, Indicates the total number of rows in the local segmentation area. Represents the total number of local segmentation area columns, taking the closest fuzzy segmentation set The median value is calculated based on the fuzzy index to calculate the correlation between pixels. The calculation formula is as follows: ， in, Represents pixel The degree of association with points in the neighborhood, Represents the local segmentation area Line The pixel values ​​of the pixels in the column are divided based on the correlation of the pixels to complete the image segmentation process.

9. The smart greenhouse with an intelligent monitoring system as claimed in claim 1, characterized in that: The crop growth analysis module analyzes and determines whether the current growth status of crops has reached the expected growth status based on the crop image recognition results and network data, and takes corresponding measures to regulate the growth of crops that have not reached the expected growth status.

10. The method for using the smart greenhouse according to any one of claims 1 to 9, characterized in that: The steps are as follows: First, the environmental observation module collects greenhouse environmental data and crop images through sensors and cameras, then the data transmission module transmits the greenhouse environmental data and crop images through a wireless network, then the data storage module stores the received greenhouse environmental data and crop images, then the environmental data analysis module predicts the environmental data conditions in the future based on the collected environmental data, then the greenhouse equipment control module predicts the data according to the greenhouse environmental conditions and controls the operation of agricultural equipment in the greenhouse, then the crop image analysis module segments and identifies the crop images, and finally, the crop growth analysis module takes corresponding measures on the growth conditions of crops based on the crop image analysis results.

Images