Greenhouse environment coordinated regulation and control method and system, and electronic device

Abstract

A greenhouse environment coordinated regulation and control method, which is applied to a greenhouse environment coordinated regulation and control system, and an electronic device executing the greenhouse environment coordinated regulation and control method. The greenhouse environment coordinated regulation and control method comprises the following steps: collecting indoor environment data of a greenhouse, outdoor environment data of the greenhouse, operating data of an environment regulation and control device, and crop physiological and ecological data to construct a data set; on the basis of the data set, constructing a crop stem diameter dynamic change prediction model; and on the basis of the stem diameter dynamic change prediction model, an optimal stem diameter change range within a fixed period, and environment factor constraint conditions, constructing a target optimization function, and using a swarm optimization algorithm to obtain an air environment factor coordinated regulation and control target value in the greenhouse, so as to obtain an operating policy of the environment regulation and control device.

Description

Methods, systems and electronic devices for coordinated control of greenhouse environment

[0001] This disclosure claims priority to Chinese Patent Application No. 2024118537698, filed on December 16, 2024, entitled "Method and System for Synergistic Regulation of Greenhouse Environment Based on Crop Stem Diameter Changes", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This disclosure relates to the field of smart agriculture technology, and more specifically, to a method, system, and electronic device for coordinated control of greenhouse environment based on changes in crop stem diameter. Background Technology

[0003] Crop growth has strict requirements for environmental conditions. Factors such as temperature and light in greenhouses directly affect crop growth rate, fruit development, and final yield. Among related technologies, greenhouse environment control methods are usually controlled manually based on experience, resulting in low levels of automation and reliance on human experience. Summary of the Invention

[0004] The purpose of this disclosure is to provide a new technical solution for a method, system, and electronic equipment for coordinated control of greenhouse environment based on changes in crop stem diameter. This solution enables real-time control of the operating status of greenhouse environmental control equipment based on changes in crop stem diameter to achieve environmental factor control targets and improve the level of intelligence.

[0005] The first aspect of this disclosure provides a method for coordinated regulation of greenhouse environment based on crop stem diameter changes, comprising the following steps: collecting environmental data inside the greenhouse, environmental data outside the greenhouse, operational data of environmental regulation equipment, and crop physiological and ecological data to construct a dataset; constructing a dynamic change prediction model for crop stem diameter based on the dataset; constructing an objective optimization function based on the dynamic change prediction model for stem diameter, the optimal range of stem diameter change within a fixed period, and environmental factor constraints; obtaining the target value for coordinated regulation of air environmental factors inside the greenhouse using a population optimization algorithm; and obtaining the operation strategy of the environmental regulation equipment.

[0006] Optionally, a dynamic change prediction model for crop stem diameter can be constructed using an intelligent learning method that combines an improved SSA algorithm with Transformer-XL.

[0007] Optionally, the crop stem diameter dynamic change prediction model is the LightGBM-SSA-Transformer-XL model, and the construction of the crop stem diameter dynamic change prediction model includes the following steps:

[0008] S1. Divide the sample dataset into multiple dataset types according to the preset environmental change rules, and further divide the training sample set and test sample set for each type;

[0009] S2. The LightGBM algorithm is used to extract features from the input parameter variables of the training sample set to screen out the feature factors that affect the growth rate of crop stem diameter;

[0010] S3. Using the feature factors selected by the LightGBM algorithm in the training sample set, construct the Transformer-XL model, and use the SSA algorithm to optimize the hyperparameters of the Transformer-XL model to obtain the LightGBM-SSA-Transformer-XL model.

[0011] S4. Select the feature factors in the test sample set that have been filtered by the LightGBM algorithm, and test the LightGBM-SSA-Transformer-XL model to obtain the optimal LightGBM-SSA-Transformer-XL model.

[0012] S5. Real-time collection of environmental data inside and outside the greenhouse, operation data of environmental control equipment, and crop physiological and ecological data, and input into the optimal LightGBM-SSA-Transformer-XL model to predict the future dynamic trend of crop stem diameter.

[0013] Optionally, step S3, which uses the SSA algorithm to optimize the hyperparameters of the Transformer-XL model, includes the following steps:

[0014] S31. Initialize SSA parameters, including population size and maximum number of iterations;

[0015] S32. Convert the hyperparameters of the Transformer-XL model into the position coordinates of the tunicate, and calculate the fitness of each tunicate;

[0016] S33. Sort the fitness values ​​of salps, take the position of the best salps as the position of the food source, take the first a% of the salps chain as the leader and the last (100-a)% as the followers, update the positions of the salps leader and followers respectively, and a% is less than 50%.

[0017] S34. Repeat steps S31 to S33. When the maximum number of iterations is reached, the optimal values ​​of the number of encoder layers, batch size, and learning rate of the Transformer-XL model are obtained.

[0018] Optionally, the top 30% of the tunicate chain can be designated as leaders and the bottom 70% as followers, and the positions of the tunicate leaders and followers can be updated accordingly.

[0019] Optionally, in step S1, the sample dataset is divided into three dataset types based on seasonal changes and weather type: winter low temperature and high humidity, summer high temperature, and spring and autumn heat preservation.

[0020] Optionally, the greenhouse internal environmental data includes air temperature, air humidity, light intensity, photosynthetically active radiation, and carbon dioxide concentration; the greenhouse external environmental data includes outdoor air temperature, air humidity, photosynthetically active radiation, rainfall, and wind speed; the environmental control equipment operation data includes equipment operation mode and operation time data; and the crop physiological and ecological data includes leaf temperature, leaf humidity, and stem diameter change data.

[0021] A second aspect of this disclosure provides a greenhouse environment collaborative regulation system based on crop stem diameter changes, comprising: a data acquisition module, which collects greenhouse internal environmental data, greenhouse external environmental data, environmental regulation equipment operation data, and crop physiological and ecological data to construct a dataset; a cloud platform service module, which includes a stem diameter change prediction module and an environmental factor collaborative regulation module, wherein the stem diameter change prediction module constructs a crop stem diameter dynamic change prediction model based on the dataset, and the environmental factor collaborative regulation module constructs an objective optimization function based on the stem diameter dynamic change prediction model, the optimal stem diameter change range within a fixed period, and environmental factor constraints, and uses a population optimization algorithm to obtain the collaborative regulation target value of air environmental factors in the greenhouse, thereby obtaining the environmental regulation equipment operation strategy; and an equipment execution module, which sends execution instructions to the regulation equipment in real time based on the generated environmental regulation strategy.

[0022] A third aspect of this disclosure provides an electronic device comprising: a processor and a memory, wherein computer program instructions are stored in the memory, wherein when the computer program instructions are executed by the processor, the processor causes the processor to perform the steps of the method described above.

[0023] A fourth aspect of this disclosure provides a computer-readable storage medium storing a computer program that, when executed by a processor, causes the processor to perform the steps of the above-described method.

[0024] According to the greenhouse environment coordinated regulation method based on crop stem diameter change according to the embodiments of this disclosure, a target optimization function is constructed with crop stem diameter growth rate as the main regulation index, thereby obtaining the regulation strategy of greenhouse crop growth environment factors, which can provide a reliable technical method for greenhouse crop growth environment control and management.

[0025] Other features and advantages of this disclosure will become clear from the following detailed description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description

[0026] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments of the present disclosure and, together with their description, serve to explain the principles of the present disclosure.

[0027] Figure 1 is a schematic diagram of the structure of the greenhouse environment collaborative control system according to an embodiment of the present disclosure;

[0028] Figure 2 is a flowchart of a greenhouse environmental factor synergistic regulation method based on crop stem diameter change according to an embodiment of this disclosure;

[0029] Figure 3 is a flowchart of the crop stem diameter change prediction method according to an embodiment of the present disclosure;

[0030] Figure 4 is a schematic diagram of an electronic device according to an embodiment of the present disclosure.

[0031] Reference numerals: Electronic device 200; Processor 201; Memory 202; Operating system 2021; Application program 2022; Network interface 203; Input device 204; Hard disk 205; Display device 206. Detailed Implementation

[0032] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of the present disclosure.

[0033] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit this disclosure or its application or use.

[0034] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.

[0035] In all the examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values.

[0036] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.

[0037] The following describes, with reference to the accompanying drawings, a method for coordinated control of greenhouse environment based on changes in crop stem diameter, according to an embodiment of this disclosure.

[0038] As shown in Figures 1 to 3, the greenhouse environment coordinated regulation method based on crop stem diameter changes according to embodiments of this disclosure includes the following steps:

[0039] Data sets are constructed by collecting environmental data from inside and outside the greenhouse, operational data from environmental control equipment, and crop physiological and ecological data. The greenhouse environmental data includes both internal and external environmental data. Internal greenhouse environmental data can be defined as environmental factor data, such as air temperature, humidity, light intensity, photosynthetically active radiation (PAR), and carbon dioxide concentration. External greenhouse environmental data can be defined as environmental factor data or outdoor meteorological data, such as outdoor air temperature, humidity, PAR, rainfall, and wind speed. Environmental control equipment operational data can be defined as equipment operation data, such as equipment operation methods and operation times. Crop physiological and ecological data can be defined as crop growth data, such as changes in leaf temperature, leaf humidity, and stem diameter.

[0040] Optionally, data processing can be performed when constructing the dataset. For example, the collected data can be transmitted to a cloud platform server for data processing such as anomaly removal, data imputation, and normalization.

[0041] Build a predictive model for the dynamic changes in crop stem diameter based on datasets, for example, using artificial intelligence algorithms to build a predictive model for the dynamic changes in crop stem diameter using cleaned datasets.

[0042] Based on a dynamic stem diameter change prediction model, the optimal range of stem diameter change within a fixed period, and environmental factor constraints, an objective optimization function is constructed. A swarm optimization algorithm is then used to obtain the target values ​​for the coordinated regulation of air environmental factors within the greenhouse, leading to the operational strategy for environmental control equipment. In other words, using the micro-change in stem diameter as the core control indicator, an objective optimization function is constructed based on a dynamic stem diameter change prediction model, the optimal range of stem diameter change within a fixed period, and environmental factor constraints. A swarm optimization algorithm is then used to obtain the target values ​​for the coordinated regulation of air environmental factors within the greenhouse, thereby deriving the operational strategy for environmental control equipment.

[0043] Furthermore, in crop cultivation, stem diameter change is one of the key indicators for assessing crop growth, and its monitoring method is convenient and harmless to crops. By monitoring minute changes in crop stem diameter in real time, the growth rate, growth status, and physiological state of the plant can be reflected promptly, providing a scientific basis for environmental regulation. With breakthroughs in sensor and phenotypic monitoring technologies, it has become possible to use crop stem diameter change as a basis for regulating environmental factors in greenhouses. Therefore, this disclosure provides a method for coordinated regulation of the greenhouse environment based on crop stem diameter change, which is of great significance in ensuring that the greenhouse environment is always in the optimal state for crop growth. It can not only improve crop yield and quality but also promote the sustainable development of agricultural production.

[0044] It should be noted that the greenhouse environment synergistic regulation method based on crop stem diameter changes in this disclosure can be used for vines or creeping crops such as tomatoes, sweet peppers, and cucumbers.

[0045] Therefore, the greenhouse environment coordinated regulation method based on crop stem diameter change according to the embodiments of this disclosure constructs a target optimization function with crop stem diameter growth rate as the main regulation index, thereby obtaining the regulation strategy of greenhouse crop growth environment factors, which can provide a reliable technical method for greenhouse crop growth environment control and management.

[0046] Alternatively, the objective optimization function can be constructed as follows:

[0047] The environmental constraints are as follows:

[0048] In equations (6) and (7), F(x) is the objective optimization function; f(x) is the stem diameter change prediction model function; S obj The optimal setting value for the slight change in crop stem diameter within a specific period; S max The maximum change in stem diameter within a specific period; S min The minimum change in stem diameter within a specific period; t min Minimum temperature; t max Maximum temperature; t aim Temperature control target value; I aim Target value for light regulation; h aim , humidity control target value; S(t,i,h), stem diameter change prediction model function; St, constraint condition set.

[0049] In equations (6) and (7), the stem diameter change prediction model function f(x) and the optimal setting value S for the micro-change of crop stem diameter within a specific period are used. obj The objective function is F(x), and the range of stem diameter variation within a specific period is set (S). min S maxThe data comes from production experience in crop cultivation. The number of environmental constraints is consistent with the actual input parameters of the prediction model, among which the target value for temperature regulation is t. aim It needs to meet the pre-set reasonable control range (t) min , t max ); Target value i for illumination control aim It needs to meet the pre-set reasonable control range (i) min i max Humidity control target value h aim It needs to meet the pre-set reasonable control range (h) min h max ).

[0050] Moreover, the optimization objective is to make the function infinitely close to the optimal set value of stem diameter growth change within a fixed time period while satisfying the constraints. The second-generation non-dominated sorting genetic algorithm (NSGA-II) was selected, and the results were verified based on the measured environmental and stem diameter change data in the greenhouse. Finally, the greenhouse environment regulation strategy for the entire growth period of crops was obtained.

[0051] According to one embodiment of this disclosure, a dynamic change prediction model for crop stem diameter is constructed using an intelligent learning method combining an improved SSA (Salp Swarm Algorithm) and Transformer-XL. Specifically, in this embodiment, the method for predicting crop stem diameter changes in a greenhouse employs an intelligent learning method combining the improved SSA and Transformer-XL algorithms to predict the trend of crop stem diameter changes in real time based on the combined model of the improved SSA and Transformer-XL. The improved SSA algorithm may include a dynamically adaptive SSA algorithm.

[0052] In some specific embodiments of this disclosure, the crop stem diameter dynamic change prediction model is the LightGBM-SSA-Transformer-XL model, as shown in Figure 3. The construction of the crop stem diameter dynamic change prediction model includes the following steps:

[0053] S1. Divide the sample dataset into multiple dataset types according to the preset environmental change rules, and further divide the training sample set and test sample set for each type;

[0054] S2. The LightGBM algorithm is used to extract features from the input parameter variables of the training sample set, identifying the feature factors affecting the growth rate of crop stem diameter. Specifically, LightGBM is a lightweight gradient boosting machine algorithm. In step S2, the lightweight gradient boosting machine algorithm is used to obtain the feature importance of the input data, screen the main feature factors affecting the growth rate of crop stem diameter, and thus improve the model's prediction accuracy and running speed.

[0055] S3. Using the feature factors selected by the LightGBM algorithm from the training sample set, a Transformer-XL model is constructed. The hyperparameters of the Transformer-XL model are then optimized using an improved SSA algorithm to obtain the LightGBM-SSA-Transformer-XL model. In other words, a crop stem diameter dynamic change prediction model based on the Transformer-XL model is constructed using the training sample set. The improved Salp Swarm Algorithm (SSA) is used to optimize the hyperparameters of the Transformer-XL model, such as the number of encoder layers, batch size, and learning rate.

[0056] In step S3, Transformer-XL is an improved method for the traditional Transformer model. This method introduces a recurrence mechanism and relative position encoding, primarily optimizing for long sequence modeling problems. During training, Transformer-XL processes the sequence segment by segment, avoiding the problem that the complexity of global self-attention calculation increases sharply with the sequence length. Meanwhile, the traditional Transformer model, due to its use of absolute position encoding to calculate attention scores, cannot adapt to changes in relative distance between different positions, making it difficult to capture long-term dependencies in time series problems. In this embodiment, Transformer-XL uses relative position encoding, effectively solving the above problems.

[0057] Furthermore, the tunicate swarm algorithm in step S3 is a novel swarm intelligence optimization algorithm. Its concept originates from the aggregation behavior of tunicates, specifically the tunicate chain. In SSA, the tunicate chain consists of two types of tunicates: leaders and followers. The leader is located at the front of the chain, while the other individuals act as followers.

[0058] The following is a detailed explanation of the tunic group algorithm.

[0059] First, in the algorithm, the location of the food source is the target location for all tunicates, and the leader's position update formula is:

[0060] Where t is the current iteration number, For the current leader of the sea squirt, F is located in the j-th dimension. j Let ub be the location of the food source in the j-th dimension. j lb j c1 and c2 are the upper and lower bounds of the j-th dimension, respectively; c2 and c3 are random numbers uniformly distributed between (0, 1), and T is the upper and lower bounds of the j-th dimension. max To determine the maximum number of iterations, c1 decreases adaptively as the number of iterations increases, and its value is:

[0061] Second, the formula for updating the position of followers is:

[0062] in, and Let i and i-1 be the positions of the previous generation of tunicate followers in the j-th dimension.

[0063] To better balance the exploratory and exploitative capabilities of the tunic swarm algorithm and avoid getting trapped in local optima, this disclosure proposes a dynamic adaptive weighting method. This method enhances the exploratory capabilities of followers in the early stages of the search and improves their exploitative capabilities in the later stages. The algorithm improvements are illustrated in the following formula:

[0064] In equations (4) and (5), w(t) represents the weight.

[0065] S4. Select feature factors from the test sample set filtered by the LightGBM algorithm, and test the LightGBM-SSA-Transformer-XL model to obtain the optimal LightGBM-SSA-Transformer-XL model. In other words, select a test sample set, test the Transformer-XL model with optimized hyperparameters, and obtain the optimal Transformer-XL model.

[0066] S5. Real-time collection of environmental data inside and outside the greenhouse, operational data of environmental control equipment, and crop physiological and ecological data are input into the optimal LightGBM-SSA-Transformer-XL model to predict the future dynamic trend of crop stem diameter. In other words, real-time collection of environmental factor data inside and outside the greenhouse, as well as crop data, is used to input the real-time data into the optimal LightGBM-SSA-Transformer-XL model to predict the future dynamic trend of crop stem diameter.

[0067] According to an embodiment of this disclosure, step S3, which uses the SSA algorithm to optimize the hyperparameters of the Transformer-XL model, includes the following steps:

[0068] S31. Initialize the parameters of the Salicylia Group Algorithm (SSA), including the population size and the maximum number of iterations;

[0069] S32. Convert the hyperparameters of the Transformer-XL model into the position coordinates of the tunicate, and calculate the fitness of each tunicate;

[0070] S33. Sort the fitness values ​​of salps, take the position of the best salps as the position of the food source, take the first a% of the salps chain as the leader and the last (100-a)% as the followers, update the positions of the salps leader and followers respectively, and a% is less than 50%.

[0071] S34. Repeat steps S31 to S33. When the maximum number of iterations is reached, the optimal values ​​of the number of encoder layers, batch size, and learning rate of the Transformer-XL model are obtained.

[0072] In this embodiment, the improved tunic swarm algorithm is used to optimize the hyperparameters of the Transformer-XL model, such as the number of encoder layers, batch size, and learning rate.

[0073] In some specific embodiments of this disclosure, the first 30% of the tunicate chain are designated as leaders and the last 70% as followers. Updating the positions of the leaders and followers can improve decision-making efficiency and group collaboration. This allows leaders to quickly formulate directions and strategies, reducing disagreements in the decision-making process, while the majority of followers focus on execution, ensuring coordinated group actions.

[0074] According to one embodiment of this disclosure, in step S1, the sample dataset is divided into three dataset types based on seasonal changes and weather type: winter low temperature and high humidity, summer high temperature, and spring and autumn warm weather. That is, the sample dataset is divided into three dataset types based on seasonal changes and weather type: winter low temperature and high humidity, summer high temperature, and spring and autumn warm weather. Simultaneously, training and testing sets are divided for each type. This seasonal division allows the model to focus on specific climatic conditions, improving its adaptability and prediction accuracy for each season.

[0075] In some specific embodiments of this disclosure, the greenhouse internal environmental data includes air temperature, air humidity, light intensity, photosynthetically active radiation, and carbon dioxide concentration; the greenhouse external environmental data includes outdoor air temperature, air humidity, photosynthetically active radiation, rainfall, and wind speed; the environmental control equipment operation data includes equipment operation mode and operation time data; and the crop physiological and ecological data includes leaf temperature, leaf humidity, and stem diameter change data. In this embodiment, by simultaneously selecting the above data, the changes in crop stem diameter growth can be predicted more accurately.

[0076] As shown in Figure 1, this disclosure also provides a greenhouse environment collaborative control system based on crop stem diameter changes, including: a data acquisition module, a stem diameter change prediction module, an environmental factor collaborative control module, and an equipment execution module. In other words, the greenhouse environment collaborative control system based on crop stem diameter changes includes: a data acquisition module, a cloud platform service module, and an equipment execution module, wherein the cloud platform service module includes the stem diameter change prediction module and the environmental factor collaborative control module.

[0077] Specifically, the data acquisition module mainly collects environmental data inside and outside the greenhouse, operational data of environmental control equipment, and crop physiological and ecological data to construct a dataset. In other words, the data acquisition module can acquire environmental data inside and outside the greenhouse, as well as crop growth data. The environmental factors inside the greenhouse mainly include air temperature, air humidity, light intensity, photoactive radiation, and carbon dioxide concentration; the environmental factors outside the greenhouse include air temperature, air humidity, light intensity, photoactive radiation, wind speed, wind direction, and rainfall; the equipment operation data includes the operating status and operation time of the environmental control equipment; and the crop physiological and ecological data includes information on changes in crop leaf temperature, leaf humidity, and stem diameter. By simultaneously using the above data, the changes in crop stem diameter and growth can be predicted more accurately.

[0078] The cloud platform service module includes a stem diameter change prediction module and an environmental factor coordinated regulation module. The stem diameter change prediction module constructs a dynamic change prediction model for crop stem diameter based on a dataset. The environmental factor coordinated regulation module constructs an objective optimization function based on the stem diameter dynamic change prediction model, the optimal range of stem diameter change within a fixed period, and environmental factor constraints. It then uses a swarm optimization algorithm to obtain the target values ​​for coordinated regulation of air environmental factors within the greenhouse, thus deriving the operating strategy for environmental regulation equipment.

[0079] Among them, the cloud platform service module uses IoT, sensors and other technologies to process the collected data, such as technology transmission, storage and cleaning of massive data; and it can accurately and dynamically predict the short-term changes in stem diameter based on artificial intelligence algorithms. Using the changes in stem diameter as the basis for regulation, it constructs a target optimization function to obtain the threshold for the coordinated regulation of multiple environmental factors within a fixed growth cycle (e.g., one week) of crops, and then generates an environmental regulation strategy.

[0080] The device execution module sends execution commands to the control equipment in real time based on the generated environmental control strategy.

[0081] In other words, this disclosure also provides a greenhouse environmental factor coordinated regulation system based on crop stem diameter changes, mainly including a data acquisition module, a cloud platform service module, and an equipment execution module. The greenhouse environmental coordinated regulation system based on crop stem diameter changes according to the embodiments of this disclosure corresponds to the method in the above embodiments, and can realize intelligent management and control of the crop growth environment, which will not be elaborated further here.

[0082] Optionally, the cloud platform service module also includes a data storage and cleaning module, namely, the cloud platform service module includes a data storage and cleaning module, a stem diameter change prediction module, and an environmental factor synergistic regulation module.

[0083] The following detailed description, in conjunction with specific embodiments, illustrates the greenhouse environment collaborative control method and system based on crop stem diameter changes according to embodiments of this disclosure.

[0084] Example 1

[0085] Example 1 selects tomato as the crop type. The greenhouse environment collaborative control system based on crop stem diameter change in Example 1 is a crop growth-driven greenhouse environment collaborative control system. The system includes a data acquisition module, a cloud platform service module, and an equipment execution module.

[0086] Example 1 specifically includes the following steps:

[0087] 1) Collect greenhouse environmental data, greenhouse external environmental data, environmental control equipment operation data, and crop physiological and ecological data within a predetermined time period.

[0088] 2) Clean all the above data and divide the processed sample set into three types according to seasonal changes and weather type: winter low temperature and high humidity, summer high temperature, and spring and autumn heat preservation. At the same time, training set and test set are divided for each type.

[0089] 3) Using the training and test sets, crop stem diameter change prediction models (LightGBM-SSA-Transformer-XL model) were constructed based on the Lightweight Gradient Boosting Machine (LightGBM), the improved Sulphuroide Group (SSA) algorithm, and the Transformer variant (Transformer-XL) model, respectively.

[0090] 4) Combining the LightGBM-SSA-Transformer-XL model, a target optimization function is constructed. A swarm intelligence optimization algorithm (second-generation non-dominated sorting genetic algorithm) is used to numerically solve the target function, obtaining the target thresholds for the coordinated regulation of crop growth environmental parameters. Furthermore, based on the target values ​​for the coordinated regulation of environmental factors, an environmental regulation strategy is generated according to the current status of the environmental regulation equipment.

[0091] As can be seen, Example 1 provides a method for coordinated regulation of greenhouse environment based on changes in crop stem diameter. The change in stem diameter growth is used as the core regulation indicator to form a set of environmental parameter regulation strategies for greenhouse tomatoes driven by crop growth, thereby realizing intelligent management and control of crop growth environment.

[0092] This disclosure also provides an electronic device 200, including: a processor 201 and a memory 202, wherein computer program instructions are stored in the memory 202, wherein when the computer program instructions are executed by the processor 201, the processor 201 performs the steps of the method in the above embodiments.

[0093] Furthermore, as shown in Figure 4, the electronic device 200 also includes a network interface 203, an input device 204, a hard disk 205, and a display device 206.

[0094] The various interfaces and devices described above can be interconnected via a bus architecture. The bus architecture can include any number of interconnecting buses and bridges. Specifically, various circuits of one or more central processing units 201 (CPUs), represented by processor 201, and one or more memories 202, represented by memory 202, are connected together. The bus architecture can also connect various other circuits such as peripheral devices, voltage regulators, and power management circuits. It is understood that the bus architecture is used to implement communication between these components. In addition to the data bus, the bus architecture also includes a power bus, a control bus, and a status signal bus, which are well known in the art and therefore will not be described in detail herein.

[0095] The network interface 203 can connect to a network (such as the Internet, local area network, etc.), obtain relevant data from the network, and save it to the hard disk 205.

[0096] Input device 204 can receive various instructions input by the operator and send them to processor 201 for execution. Input device 204 may include a keyboard or clicking device (e.g., mouse, trackball, touchpad, or touch screen).

[0097] Display device 206 can display the results obtained by the processor 201 executing instructions.

[0098] The memory 202 is used to store the programs and data necessary for the operation of the operating system 2021, as well as intermediate results and other data during the calculation process of the processor 201.

[0099] It is understood that the memory 202 in the embodiments of this disclosure may be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory may be random access memory (RAM), which is used as an external cache. The memory 202 of the apparatus and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory 202.

[0100] In some implementations, memory 202 stores elements such as executable modules or data structures, or subsets thereof, or extended sets thereof: operating system 2021 and application 2022.

[0101] The operating system 2021 includes various system programs, such as the framework layer, core library layer, and driver layer, used to implement various basic business functions and handle hardware-based tasks. The application program 2022 includes various applications, such as a browser, used to implement various application functions. Programs implementing the methods of this disclosure embodiment can be included in the application program 2022.

[0102] When the processor 201 calls and executes the application program 2022 and data stored in the memory 202, specifically the program or instructions stored in the application program 2022, it executes the steps of the method according to the above embodiment.

[0103] The methods disclosed in the above embodiments of this disclosure can be applied to or implemented by processor 201. Processor 201 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuit of the hardware in processor 201 or by instructions in software form. The processor 201 may be a general-purpose processor, digital signal processor (DSP), application-specific integrated circuit (ASIC), off-the-shelf programmable gate array (FPGA), or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component, and can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this disclosure. The general-purpose processor may be a microprocessor or processor 201 may be any conventional processor 201, etc. The steps of the methods disclosed in the embodiments of this disclosure can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules may be located in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in memory 202. The processor 201 reads the information in memory 202 and, in conjunction with its hardware, completes the steps of the above method.

[0104] It is understood that the embodiments described herein can be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof. For hardware implementation, the processing unit can be implemented in one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers, microprocessors, other electronic units for performing the functions of this disclosure, or combinations thereof.

[0105] For software implementation, the techniques described herein can be implemented through modules (e.g., procedures, functions, etc.) that perform the functions described herein. The software code can be stored in memory 202 and executed by processor 201. Memory 202 can be implemented in processor 201 or external to processor 201.

[0106] Specifically, the processor 201 is also used to read computer programs and perform the following steps: the method predicts and outputs the answer to the question asked by the user.

[0107] This disclosure also provides a computer-readable storage medium storing a computer program that, when executed by a processor 201, causes the processor 201 to perform the steps of the methods described in the above embodiments.

[0108] In the several embodiments provided in this disclosure, it should be understood that the disclosed methods and apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0109] Furthermore, the functional units in the various embodiments of this disclosure can be integrated into one processing unit, or each unit can be physically comprised separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in a combination of hardware and software functional units.

[0110] The integrated units implemented as software functional units described above can be stored in a computer-readable storage medium. These software functional units, stored in a storage medium, include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute some steps of the transmission and reception methods of the various embodiments of this disclosure. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0111] While specific embodiments of this disclosure have been described in detail by way of example, those skilled in the art should understand that the examples are for illustrative purposes only and not intended to limit the scope of this disclosure. Those skilled in the art should understand that modifications can be made to the above embodiments without departing from the scope and spirit of this disclosure. The scope of this disclosure is defined by the appended claims.

Claims

1. A method for coordinated regulation of greenhouse environment based on changes in crop stem diameter, characterized by, Includes the following steps: Collect environmental data inside and outside the greenhouse, operational data of environmental control equipment, and crop physiological and ecological data to construct a dataset. A prediction model for dynamic changes in crop stem diameter was constructed based on the dataset. Based on the aforementioned stem diameter dynamic change prediction model, the optimal range of stem diameter change within a fixed period, and environmental factor constraints, an objective optimization function is constructed. The target value of coordinated regulation of air environmental factors in the greenhouse is obtained using a population optimization algorithm, and the operation strategy of environmental regulation equipment is derived.

2. The method for coordinated regulation of greenhouse environment based on changes in crop stem diameter according to claim 1, wherein, A predictive model for the dynamic change of crop stem diameter was constructed using an intelligent learning method that combines an improved SSA algorithm with Transformer-XL.

3. The method for coordinated regulation of greenhouse environment based on crop stem diameter variation according to claim 1 or 2, characterized in that, The crop stem diameter dynamic change prediction model is the LightGBM-SSA-Transformer-XL model. The construction of the crop stem diameter dynamic change prediction model includes the following steps: S1. Divide the sample dataset into multiple dataset types according to the preset environmental change rules, and further divide the training sample set and test sample set for each type; S2. The LightGBM algorithm is used to extract features from the input parameter variables of the training sample set to screen out the feature factors that affect the growth rate of crop stem diameter; S3. Using the feature factors selected by the LightGBM algorithm in the training sample set, construct the Transformer-XL model, and use the SSA algorithm to optimize the hyperparameters of the Transformer-XL model to obtain the LightGBM-SSA-Transformer-XL model. S4. Select the feature factors in the test sample set that have been filtered by the LightGBM algorithm, and test the LightGBM-SSA-Transformer-XL model to obtain the optimal LightGBM-SSA-Transformer-XL model. S5. Real-time collection of environmental data inside and outside the greenhouse, operation data of environmental control equipment, and crop physiological and ecological data, and input into the optimal LightGBM-SSA-Transformer-XL model to predict the future dynamic trend of crop stem diameter.

4. The method for coordinated regulation of greenhouse environment based on the change of crop stem diameter according to any one of claims 1-3, characterized in that, Step S3, which uses the SSA algorithm to optimize the hyperparameters of the Transformer-XL model, includes the following steps: S31. Initialize SSA parameters, including population size and maximum number of iterations; S32. Convert the hyperparameters of the Transformer-XL model into the position coordinates of the tunicate, and calculate the fitness of each tunicate; S33. Sort the fitness values ​​of salps, take the position of the best salps as the position of the food source, take the first a% of the salps chain as the leader and the last (100-a)% as the followers, update the positions of the salps leader and followers respectively, and a% is less than 50%. S34. Repeat steps S31 to S33. When the maximum number of iterations is reached, the optimal values ​​of the number of encoder layers, batch size, and learning rate of the Transformer-XL model are obtained.

5. The method for coordinated regulation of greenhouse environment based on the change of crop stem diameter according to any one of claims 1-4, characterized in that, The top 30% of the Salicornia chain are designated as leaders, and the bottom 70% as followers. The positions of the Salicornia leaders and followers are updated accordingly.

6. The method for coordinated regulation of greenhouse environment based on the change of crop stem diameter according to any one of claims 1-5, characterized in that, In step S1, the sample dataset is divided into three types based on seasonal changes and weather type: winter low temperature and high humidity, summer high temperature, and spring and autumn heat preservation.

7. The method for coordinated regulation of greenhouse environment based on the changes in crop stem diameter according to any one of claims 1-6, characterized in that, The greenhouse internal environmental data includes air temperature, air humidity, light intensity, photosynthetically active radiation, and carbon dioxide concentration; the greenhouse external environmental data includes outdoor air temperature, air humidity, photosynthetically active radiation, rainfall, and wind speed. The environmental control equipment operation data includes equipment operation mode and operation time data; the crop physiological and ecological data includes leaf temperature, leaf humidity and stem diameter change data.

8. A greenhouse environment co-regulation system based on crop stem diameter change, characterized in that, include: The data acquisition module collects environmental data inside and outside the greenhouse, operational data of environmental control equipment, and crop physiological and ecological data to construct a dataset. The cloud platform service module includes a stem diameter change prediction module and an environmental factor coordinated regulation module. The stem diameter change prediction module constructs a crop stem diameter dynamic change prediction model based on the dataset. The environmental factor coordinated regulation module constructs an objective optimization function based on the stem diameter dynamic change prediction model, the optimal stem diameter change range within a fixed period, and environmental factor constraints. It then uses a population optimization algorithm to obtain the target value for coordinated regulation of air environmental factors in the greenhouse and obtains the operation strategy of the environmental regulation equipment. The device execution module sends execution instructions to the control device in real time based on the generated environmental control strategy.

9. An electronic device, comprising: include: A processor and a memory, wherein computer program instructions are stored in the memory, wherein when the computer program instructions are executed by the processor, the processor causes the processor to perform the method of any one of claims 1-7.

10. The electronic device according to claim 9, characterized in that, It also includes a computer-readable storage medium for an electronic device, the computer-readable storage medium storing a computer program that, when executed by a processor, causes the processor to perform the method of any one of claims 1-7.

Images