Greenhouse environment control system, control parameter optimization method, device and medium

Abstract

The application provides a greenhouse environment control system, a control parameter optimization method, equipment and a medium. A multi-dimensional environment data coupling mode of a target greenhouse is determined through multi-dimensional environment data in the target greenhouse. The equipment is configured in the environment data coupling mode to regulate and control the target greenhouse. A regulation deviation between each dimensional environment data in the multi-dimensional environment data and a preset reference value of the corresponding dimension is determined. The regulation constraint of each dimensional environment data in the target greenhouse is determined through all the regulation deviations and the environment data coupling mode. The disturbance constraint condition of the target greenhouse is determined according to environment interference information of the target greenhouse and historical multi-dimensional environment data of the target greenhouse. The parameters of the greenhouse environment control equipment in the target greenhouse in the regulation process are optimized through all the regulation constraints and the disturbance constraint condition. According to the application, the greenhouse environment control process can be cooperatively optimized based on the coupling relationship between each dimensional environment data in the greenhouse environment.

Description

Technical Field

[0001] This application relates to the field of environmental control technology, and more specifically, to a greenhouse environmental control system, a method for optimizing control parameters, equipment, and a medium. Background Technology

[0002] Environmental control is a technology that uses sensing technology, control theory and execution equipment to monitor and precisely regulate physical and chemical environmental parameters such as temperature, humidity, light, and gas concentration in a specific space in real time. Its core objective is to overcome the influence of external natural climate fluctuations and internal disturbance factors, and dynamically maintain the internal environment in the optimal state that meets the needs of process or biological growth.

[0003] Greenhouse environments are crucial for crop growth, with significant coupling relationships between multiple environmental factors such as temperature, humidity, light, and carbon dioxide concentration. These factors are also susceptible to external weather changes (e.g., cold waves, heavy rains) and internal equipment malfunctions. Traditional methods for optimizing greenhouse environmental control parameters often employ single-dimensional, independent control models, neglecting the interactions between various environmental factors and lacking precise identification of dominant influencing factors. Furthermore, they fail to adequately integrate historical data and real-time interference information to establish effective constraints, resulting in untargeted parameter settings, weak anti-interference capabilities, and frequent issues such as excessive environmental deviations and high equipment energy consumption. This makes it difficult to adapt to the dynamic needs of crops at different growth stages, hindering yield and quality improvement in greenhouse cultivation. Therefore, how to collaboratively optimize the greenhouse environmental control process based on the coupling relationships between various dimensions of environmental data has become a challenge for the industry. Summary of the Invention

[0004] This application provides a greenhouse environment control system, control parameter optimization method, equipment and medium, which can collaboratively optimize the greenhouse environment control process based on the coupling relationship between environmental data of various dimensions in the greenhouse environment.

[0005] In a first aspect, this application provides a method for optimizing greenhouse environmental control parameters, wherein the target greenhouse is environmentally controlled by greenhouse environmental control equipment, and the method includes the following steps: Collect multi-dimensional environmental data inside the target greenhouse; Based on the coupling relationship between the environmental data of each dimension in the multi-dimensional environmental data, a coupling correlation analysis is performed on the environmental data of each dimension of the target greenhouse in the environmental control process to obtain the environmental data coupling mode that plays a dominant role in the environmental control process of the target greenhouse. The greenhouse environment control equipment is configured to the environmental data coupling mode to regulate the target greenhouse, and the regulation deviation between each dimension of the multi-dimensional environmental data and the preset reference value of the corresponding dimension is determined during the regulation process. The environmental control of the target greenhouse is constrained by all the regulation deviations and the environmental data coupling mode to obtain the regulation constraints of each dimension of the environmental data in the target greenhouse. Obtain environmental disturbance information of the target greenhouse, and determine the disturbance constraint conditions of the target greenhouse during environmental control based on the environmental disturbance information and the historical multi-dimensional environmental data of the target greenhouse. The parameters of the greenhouse environment control equipment in the target greenhouse are optimized during the control process by using all the control constraints and the disturbance constraints.

[0006] In some embodiments, the multidimensional environmental data includes air temperature, relative humidity, soil temperature, soil moisture content, carbon dioxide concentration, light intensity, and duration of light exposure.

[0007] In some embodiments, based on the coupling relationship between the environmental data of each dimension in the multi-dimensional environmental data, a coupling correlation analysis is performed on the environmental data of each dimension of the target greenhouse during the environmental control process to obtain the environmental data coupling mode that plays a dominant role in the environmental control process of the target greenhouse. Specifically, this includes: The multi-dimensional environmental data is denoised to obtain denoised multi-dimensional environmental data. Determine the coupling relationship between the environmental data of each dimension in the denoised multi-dimensional environmental data; Determine the physiological characteristics of the target greenhouse crops; Based on the physiological characteristics, determine the influence weights of environmental data in various dimensions on the crops during the environmental control process in the target greenhouse; The environmental data coupling pattern in which the target greenhouse plays a dominant role in the environmental control process is determined by the coupling relationship and all the influence weights.

[0008] In some embodiments, the greenhouse environment control device is configured in the environmental data coupling mode to regulate the target greenhouse, and the regulation deviation between each dimension of the multi-dimensional environmental data and the preset reference value of the corresponding dimension is determined during the regulation process. Specifically, this includes: The greenhouse environment control equipment is configured to the environmental data coupling mode to regulate the target greenhouse; Collect environmental data from each dimension of the multi-dimensional environmental data during the regulation process to obtain regulation environmental data for each dimension. The environmental data for each dimension is compared with the preset reference value for the corresponding dimension to determine the control deviation between the environmental data for each dimension and the preset reference value for the corresponding dimension during the control process.

[0009] In some embodiments, constraint analysis is performed on the environmental control of the target greenhouse through all regulation deviations and the environmental data coupling mode to obtain the regulation constraints of environmental data in various dimensions of the target greenhouse, specifically including: Based on all the control deviations and the environmental data coupling mode, determine the mutual constraints between environmental data of various dimensions in the target greenhouse environmental control process; The control constraints of environmental data in various dimensions in the target greenhouse are determined by the interrelationships between environmental data in various dimensions.

[0010] In some embodiments, determining the disturbance constraint conditions of the target greenhouse during environmental control based on the environmental disturbance information and historical multi-dimensional environmental data of the target greenhouse specifically includes: Acquire historical, multi-dimensional environmental data for the target greenhouse; Based on the environmental interference information and the historical multi-dimensional environmental data, determine the fluctuation patterns of environmental data in each dimension under different interferences; The perturbation constraints of the target greenhouse under environmental control were determined by analyzing all the fluctuation patterns.

[0011] In some embodiments, optimizing the parameters of the greenhouse environment control equipment within the target greenhouse during the regulation process using all regulation constraints and the disturbance constraints specifically includes: Determine the adjustable parameters of the greenhouse environment control equipment during the control process of the target greenhouse; The adjustable parameters are optimized by applying all control constraints and the disturbance constraints to obtain the adjustable optimized parameters. The adjustable optimization parameters are input into the greenhouse environment control equipment to optimize and regulate the target greenhouse.

[0012] Secondly, this application provides a greenhouse environment control system, wherein the target greenhouse is environmentally controlled by greenhouse environment control equipment. The system includes a control parameter optimization unit, which includes: The data acquisition module is used to collect multi-dimensional environmental data inside the target greenhouse. The processing module is used to perform coupling correlation analysis on the environmental data of the target greenhouse in the environmental control process based on the coupling relationship between the environmental data of each dimension in the multi-dimensional environmental data, so as to obtain the environmental data coupling mode that plays a dominant role in the environmental control process of the target greenhouse. The processing module is further configured to configure the greenhouse environment control equipment into the environmental data coupling mode to regulate the target greenhouse, and to determine the regulation deviation between the environmental data of each dimension in the multi-dimensional environmental data and the preset reference value of the corresponding dimension during the regulation process. The module performs constraint analysis on the environmental control of the target greenhouse through all the regulation deviations and the environmental data coupling mode to obtain the regulation constraints of the environmental data of each dimension in the target greenhouse. The processing module is also used to acquire environmental disturbance information of the target greenhouse, and determine the disturbance constraint conditions of the target greenhouse during environmental control based on the environmental disturbance information and the historical multi-dimensional environmental data of the target greenhouse. The execution module is used to optimize the parameters of the greenhouse environment control equipment in the target greenhouse during the control process by using all the control constraints and the disturbance constraints.

[0013] Thirdly, this application provides a computer device, the computer device including a memory and a processor, the memory storing code, and the processor being configured to acquire the code and execute the above-described greenhouse environment control parameter optimization method.

[0014] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for optimizing greenhouse environment control parameters.

[0015] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects: The greenhouse environmental control system, control parameter optimization method, equipment, and medium provided in this application first collect multi-dimensional environmental data within the target greenhouse; based on the coupling relationship between the various dimensions of environmental data, a coupling correlation analysis is performed on the environmental data of the target greenhouse during the environmental control process to obtain the environmental data coupling mode that plays a dominant role in the environmental control process; the greenhouse environmental control equipment is configured to the environmental data coupling mode to regulate the target greenhouse, and the regulation deviation between the environmental data of each dimension and the preset reference value of the corresponding dimension is determined during the regulation process; constraint analysis is performed on the environmental control of the target greenhouse through all regulation deviations and the environmental data coupling mode to obtain the regulation constraints of the environmental data of each dimension in the target greenhouse; environmental disturbance information of the target greenhouse is acquired, and disturbance constraint conditions of the target greenhouse during environmental control are determined based on the environmental disturbance information and the historical multi-dimensional environmental data of the target greenhouse; the parameters of the greenhouse environmental control equipment in the target greenhouse during the regulation process are optimized through all regulation constraints and the disturbance constraint conditions.

[0016] Therefore, this application demonstrates that, in the greenhouse environmental control process, firstly, by collecting multi-dimensional environmental data and performing coupling correlation analysis, it can identify key coupling modes that play a dominant role in complex environmental interactions, understanding the intrinsic relationships between various environmental factors at the system level, and laying a theoretical foundation for collaborative control. Secondly, by introducing control deviation analysis into the control process and combining it with the identified coupling modes, it can accurately determine the dynamic control constraints of each environmental parameter, avoiding system imbalance caused by isolated control of a single parameter, and enhancing the adaptability and coordination of the control strategy. Furthermore, by introducing environmental disturbance information and historical data to determine disturbance constraints, it can anticipate and resist the impact of external environmental fluctuations, improving the robustness of control. Finally, by comprehensively optimizing the control equipment parameters based on control constraints and disturbance boundaries, it achieves optimal allocation of environmental control resources, ensuring that the greenhouse environment can be stably maintained at the optimal state for crop growth while saving energy. Using the above scheme, the greenhouse environmental control process can be collaboratively optimized based on the coupling relationships between environmental data of various dimensions within the greenhouse environment. Attached Figure Description

[0017] Figure 1 This is an exemplary flowchart of a greenhouse environment control parameter optimization method according to some embodiments of this application; Figure 2 This is an exemplary flowchart illustrating the determination of control deviation according to some embodiments of this application; Figure 3 This is an exemplary flowchart illustrating the determination of disturbance constraints according to some embodiments of this application; Figure 4 This is a schematic diagram of the structure of the control parameter optimization unit shown in some embodiments of this application; Figure 5 This is a schematic diagram of the structure of a computer device for implementing a method for optimizing greenhouse environment control parameters according to some embodiments of this application. Detailed Implementation

[0018] To better understand the technical solution of this application, the technical solution of this application will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0019] refer to Figure 1 The figure is an exemplary flowchart of a greenhouse environment control parameter optimization method according to some embodiments of this application. The greenhouse environment control parameter optimization method mainly includes the following steps: In step 101, multi-dimensional environmental data of the target greenhouse are collected.

[0020] It should be noted that the multi-dimensional environmental data in this application consists of multiple dimensions of environmental data. Each dimension of environmental data corresponds to one of the following: air temperature, relative humidity, soil temperature, soil moisture content, carbon dioxide concentration, light intensity, and light duration. The multi-dimensional environmental data reflects the comprehensive environmental conditions of crop growth in the target greenhouse and the real-time status of key environmental factors such as soil, air, and light. The multi-dimensional environmental data indicates the overall stability of the greenhouse environment, the synergistic or restrictive relationships between various environmental factors, and whether the needs of crops at different growth stages for various environmental conditions are met.

[0021] In step 102, based on the coupling relationship between the environmental data of each dimension in the multi-dimensional environmental data, a coupling correlation analysis is performed on the environmental data of each dimension of the target greenhouse during the environmental control process to obtain the environmental data coupling mode of the environmental data of the target greenhouse during the environmental control process.

[0022] In some embodiments, the coupling relationship between the environmental data of each dimension in the multi-dimensional environmental data is used to perform coupling correlation analysis on the environmental data of the target greenhouse in the environmental control process, and the resulting environmental data coupling mode that plays a dominant role in the environmental control process of the target greenhouse can be achieved by the following steps: The multi-dimensional environmental data is denoised to obtain denoised multi-dimensional environmental data. Determine the coupling relationship between the environmental data of each dimension in the denoised multi-dimensional environmental data; Determine the physiological characteristics of the target greenhouse crops; Based on the physiological characteristics, determine the influence weights of environmental data in various dimensions on the crops during the environmental control process in the target greenhouse; The environmental data coupling pattern in which the target greenhouse plays a dominant role in the environmental control process is determined by the coupling relationship and all the influence weights.

[0023] In specific implementation, the multi-dimensional environmental data is denoised to obtain the denoised multi-dimensional environmental data. This can be achieved in the following way: First, the 3σ principle is used to identify outliers, that is, when the data deviates from the mean by more than 3 times the standard deviation, it is judged as an anomaly. After removing outliers, a denoising method is selected according to the noise characteristics of different dimensions of data. For high-frequency fluctuating light and wind speed data, the moving average method is used, with the window size set to 5-10 sampling points. The mean within the window is calculated according to the time series to replace the original value. For slowly changing data such as temperature and humidity, Kalman filtering is used. By establishing a state equation of current value = predicted value at the previous moment + process noise, and combining it with the sensor measurement value for dynamic correction, random noise is reduced, and the denoised multi-dimensional environmental data is obtained. Other methods can also be used in other embodiments, which are not limited here.

[0024] In addition, in specific implementation, the coupling relationship between environmental data in each dimension of the denoised multi-dimensional environmental data can be determined in the following way: First, the denoised data is normalized to the minimum-maximum value and mapped to the [0,1] interval to eliminate the influence of dimensions. Then, the coupling strength is quantified by statistical methods. The Pearson correlation coefficient is used to calculate linear coupling, such as the negative correlation between temperature and humidity. The ratio of the product of the covariance and standard deviation of the two-dimensional data is calculated. The closer the absolute value is to 1, the stronger the linear coupling. Mutual information is used to calculate nonlinear coupling. By constructing the joint probability distribution and marginal probability distribution of the two-dimensional data, the mutual information value is calculated according to the formula. The larger the value, the tighter the nonlinear correlation. Granger causality test is used to determine causal coupling. For two-dimensional time series data, by constructing an autoregressive model, if the introduction of the lag term of dimension A can significantly improve the prediction accuracy of dimension B, then A is determined to be a Granger cause of B, such as the causal influence of the fan operating status on the air velocity. Finally, the coupling relationship between environmental data in each dimension of the multi-dimensional environmental data containing linear, nonlinear and causal relationships is formed. Other methods can also be used to determine this in other embodiments, which are not limited here.

[0025] In addition, in specific implementation, the physiological characteristics of the target greenhouse crop can be determined in the following way: by consulting the cultivation data and field trial data of the target greenhouse crop, the sensitive environmental factors of its key growth stages (seedling stage, flowering stage, and fruiting stage) are identified. For example, the root development during the seedling stage is sensitive to soil temperature and soil moisture, the pollination during the flowering stage is sensitive to air humidity and temperature, and the fruit enlargement during the fruiting stage is sensitive to photosynthetically active radiation and carbon dioxide concentration. A list of sensitive environmental factors for each growth stage is compiled and used as the physiological characteristics of the target greenhouse crop. Other methods can be used to determine these characteristics in other embodiments, which are not limited here.

[0026] In addition, in specific implementation, the influence weights of environmental data of various dimensions on the crops during the environmental control process of the target greenhouse, based on the physiological characteristics, can be determined in the following way: using the analytic hierarchy process (AHP), with the crop growth state as the target layer and each environmental dimension as the indicator layer, the importance of each dimension within the same growth stage is compared pairwise to construct a judgment matrix; the subjective weights of each dimension are obtained by calculating the eigenvector corresponding to the largest eigenvalue of the matrix; at the same time, the information entropy of each dimension data is calculated using the entropy weight method. The smaller the entropy value, the higher the dispersion, the greater the information content, and the higher the weight, to obtain the objective weights. The subjective and objective weights are then fused in a 7:3 ratio, and the fused weights are used as the influence weights of the corresponding dimension environmental data on the crops during the environmental control process of the target greenhouse. Other methods can also be used to determine this in other embodiments, which are not limited here.

[0027] In addition, in specific implementation, the environmental data coupling mode that plays a dominant role in the environmental control process of the target greenhouse can be determined by the following method through the coupling relationship and all influence weights: multiply the coupling strength value in the coupling relationship with the influence weight of the corresponding dimension to obtain the comprehensive score of the coupling and weight of each dimension data; after sorting the scores, select the top 2-3 dimensions with the highest scores as the core dominant dimensions, and at the same time refer to the association rules in the coupling relationship, such as the coupling strength of light and carbon dioxide > 0.7 and both scores are in the top three, to determine the synergistic or restrictive relationship between the dominant dimensions; finally, the core dominant dimensions, association rules, synergistic or restrictive relationship are used as the environmental data coupling mode of the target greenhouse in the environmental control process. For example, the environmental data coupling mode can be the synergistic dominant mode of light and carbon dioxide in the result period, which clarifies that when the light intensity increases, the carbon dioxide concentration needs to increase synchronously to match the photosynthetic demand. Other methods can also be used to determine this in other embodiments, which are not limited here.

[0028] It should be noted that the coupling relationship in this application reflects the degree of interaction between multi-dimensional environmental data, and the coupling relationship represents the close correlation between different environmental factors in the process of change; physiological characteristics reflect the inherent sensitivity requirements and growth patterns of the target greenhouse crops to environmental conditions at different growth stages, and physiological characteristics represent the degree of dependence of their growth and development on specific environmental factors; influence weight reflects the differences in the importance of each environmental dimension to crop growth, and influence weight represents the priority of different environmental factors in regulation; environmental data coupling mode reflects the core regulation direction of environmental data that plays a leading role in the environmental control process of the target greenhouse, and environmental data coupling mode represents the key basis for guiding the operation of environmental control equipment.

[0029] In step 103, the greenhouse environment control device is configured to the environmental data coupling mode to regulate the target greenhouse, and the regulation deviation between each dimension of the multi-dimensional environmental data and the preset reference value of the corresponding dimension is determined during the regulation process. The environmental control of the target greenhouse is constrained by all the regulation deviations and the environmental data coupling mode to obtain the regulation constraints of each dimension of the environmental data in the target greenhouse.

[0030] In some embodiments, reference Figure 2 As shown, this figure is an exemplary flowchart for determining the control deviation in some embodiments of this application. In this embodiment, the greenhouse environment control device is configured to the environmental data coupling mode to control the target greenhouse, and the control deviation between each dimension of the multi-dimensional environmental data and the preset reference value of the corresponding dimension can be determined by the following steps: In step 1031, the greenhouse environment control device is configured to the environmental data coupling mode to regulate the target greenhouse; In step 1032, environmental data of each dimension in the multi-dimensional environmental data are collected during the regulation process to obtain regulation environmental data of each dimension; In step 1033, the environmental data of each dimension are compared with the preset reference value of the corresponding dimension to determine the control deviation between the environmental data of each dimension and the preset reference value of the corresponding dimension in the multi-dimensional environmental data during the control process.

[0031] In specific implementation, the greenhouse environment control equipment can be configured into the environmental data coupling mode to regulate the target greenhouse in the following way: the environmental data coupling mode is converted into a regulation command that the greenhouse environment control equipment can recognize. This command needs to be converted into specific parameters through the equipment's built-in parsing module and then transmitted to the execution unit of the control equipment through the industrial bus to start the regulation.

[0032] In addition, in specific implementation, the environmental data of each dimension in the multi-dimensional environmental data during the control process can be collected in the following way to obtain the control environmental data of each dimension: During the control process, the sensor network pre-deployed in the greenhouse is used to collect environmental data of each dimension at a fixed sampling period. The collected data is preprocessed by the edge computing gateway, and the instantaneous values ​​of high-frequency fluctuations are smoothed by the moving average method. Jump values ​​caused by poor sensor contact are removed to obtain the control environmental data of each dimension. The control environmental data of each dimension refers to the environmental data during the control process. Other methods can be used to collect the data in other embodiments, which will not be elaborated here.

[0033] In addition, in specific implementation, the control deviation between the environmental data of each dimension and the preset reference value of the corresponding dimension is compared with the control environmental data of each dimension during the control process. This can be achieved by the following method: calling the preset reference value of the corresponding dimension from the local database of the greenhouse environmental control equipment. This reference value is preset based on the physiological characteristics of the crop, such as the light reference value of 400-600 μmol / m²・s and the carbon dioxide reference value of 600-800 ppm during the fruiting period of tomatoes, stored in the form of intervals. Finally, the control deviation is calculated by comparing the control environmental data of each dimension with the corresponding reference value. For a single reference value, the deviation is the actual value minus the reference value. For an interval reference value, if the actual value is within the interval, the deviation is recorded as 0. If it exceeds the interval, the deviation is the actual value minus the interval boundary value. Other methods can be used to determine this in other embodiments, which are not limited here.

[0034] It should be noted that the control deviation in this application refers to the deviation between the environmental data of each dimension in the multi-dimensional environmental data and the standard parameters during the control process, and can be used to reflect the control effect of greenhouse environmental control equipment.

[0035] In some embodiments, the environmental control of the target greenhouse is constrained by all control deviations and the environmental data coupling mode, and the control constraints of environmental data in various dimensions of the target greenhouse can be obtained by the following steps: Based on all the control deviations and the environmental data coupling mode, determine the mutual constraints between environmental data of various dimensions in the target greenhouse environmental control process; The control constraints of environmental data in various dimensions in the target greenhouse are determined by the interrelationships between environmental data in various dimensions.

[0036] In specific implementation, determining the inter-constraint relationships between various dimensions of environmental data during the target greenhouse environmental control process, based on all control deviations and the environmental data coupling mode, can be achieved in the following way: Correlation analysis is performed between the control deviations of each dimension and the core dominant dimensions and association rules in the environmental data coupling mode. Higher weights are assigned to the deviations of the core dominant dimensions. By setting weighting coefficients (1.0 for core dimensions and 0.6 for non-core dimensions), and combining the constraint strength in the coupling relationship, the influence of the deviation is calculated. For example, this can be calculated using the formula: deviation value × weight × constraint strength. A matrix of inter-constraint relationships between dimensions is constructed. The larger the element value in the matrix, the greater the influence. This indicates that the mutual influence between the two dimensional deviations is more significant. Based on this matrix, specific constraints are analyzed: if the deviation of the core dimension of light is negative and has a synergistic relationship with the dimension of carbon dioxide, then the positive deviation of the dimension of carbon dioxide will lead to a decrease in carbon dioxide utilization efficiency due to insufficient light. In this case, the upper limit of the carbon dioxide deviation needs to be constrained. If the deviation of the core dimension of temperature is positive and has a constraint relationship with the dimension of humidity, then the positive deviation of humidity will exacerbate the risk of disease under high temperature. The range of humidity deviation needs to be tightened. Finally, the mutual constraints between the environmental data of each dimension in the process of controlling the target greenhouse environment are obtained. In other embodiments, other methods can be used to determine this, which are not limited here.

[0037] In addition, in specific implementation, the control constraints of environmental data in various dimensions in the target greenhouse can be determined by the following method based on the mutual constraints between environmental data in various dimensions: based on the physiological tolerance limit of crops in the target greenhouse, for example, cucumbers will stop growing if the temperature deviation exceeds ±3℃, the control constraints of each dimension are determined by the threshold method. The constraint threshold of the core dimension is taken as 70% of the tolerance limit, and the non-core dimensions are dynamically adjusted according to the constraint relationship with the core dimension. For example, the humidity constraint due to temperature is tightened from ±10% to ±6%, and finally a clear allowable deviation range for each dimension is formed, that is, the control constraint. Other methods can also be used to determine the control constraints in other embodiments, which are not limited here.

[0038] It should be noted that the mutual constraint relationship in this application represents the mutual influence and restriction relationship between the data of each environmental dimension in the target greenhouse during the regulation process, reflecting the degree of constraint of the deviation changes of different environmental dimensions on the regulation space of other dimensions; the regulation constraint represents the maximum allowable deviation boundary of each environmental dimension data in regulation under the mutual constraint relationship, reflecting the rigid regulation standard set to ensure the effectiveness of regulation and the safety of crop growth after combining the crop physiological tolerance limit and the inter-dimensional linkage restriction, and clearly defining the threshold requirements that the control equipment cannot break when adjusting each environmental factor.

[0039] In step 104, environmental disturbance information of the target greenhouse is obtained, and disturbance constraint conditions of the target greenhouse during environmental control are determined based on the environmental disturbance information and historical multi-dimensional environmental data of the target greenhouse.

[0040] It should be noted that the environmental disturbance information of the target greenhouse in this application includes natural disturbances, equipment disturbances, and human disturbances. For example, natural disturbances include extreme outdoor weather, wind speed, and precipitation; equipment disturbances include temperature control / supplementary lighting equipment failures and energy consumption fluctuations; and human disturbances include agricultural operations, personnel intervention, and the occurrence of pests and diseases. The environmental disturbance information reflects the real-time status and characteristics of various external meteorological, equipment operation, and human operation factors that affect the stability of the greenhouse's internal environment. The environmental disturbance information indicates the potential fluctuation risks that may be faced during the greenhouse environmental control process and the intensity and range of the impact of different types of disturbances on environmental data in various dimensions, providing a core basis for determining disturbance constraints.

[0041] In some embodiments, reference Figure 3 As shown, this figure is an exemplary flowchart of determining disturbance constraints in some embodiments of this application. In this embodiment, determining the disturbance constraints of the target greenhouse under environmental control based on the environmental disturbance information and the historical multi-dimensional environmental data of the target greenhouse can be achieved by the following steps: In step 1041, historical multi-dimensional environmental data of the target greenhouse are acquired; In step 1042, the fluctuation patterns of environmental data in each dimension under different disturbances are determined based on the environmental interference information and the historical multi-dimensional environmental data. In step 1043, the disturbance constraints of the target greenhouse under environmental control are determined by all the fluctuation patterns.

[0042] Among them, historical multi-dimensional environmental data of the target greenhouse for the past 1-3 years are retrieved from the local database of the greenhouse environmental control equipment.

[0043] In addition, in specific implementation, the fluctuation pattern of environmental data in each dimension under different interferences can be determined by the following method based on the environmental interference information and the historical multi-dimensional environmental data: the environmental interference information is then classified, and for each type of interference, environmental data in each dimension during the period when the interference occurs is extracted from the historical multi-dimensional environmental data. The fluctuation amplitude and average rate of change of the extracted dimensional environmental data are calculated, and the environmental dimensions that are significantly affected by the interference are screened out, thereby determining the fluctuation pattern of environmental data in each dimension under different interferences. Other methods can also be used to determine this in other embodiments, which are not limited here.

[0044] In addition, in specific implementation, the disturbance constraint conditions of the target greenhouse under environmental control can be determined by the following method based on all fluctuation patterns: extract the maximum allowable fluctuation amplitude and the maximum allowable rate of change of each dimension under different disturbances from all fluctuation patterns. For example, under severe cold wave disturbance, the maximum allowable rate of temperature drop is 3℃ / h and the fluctuation amplitude does not exceed 5℃ within 1 hour. Integrate these quantitative indicators into structured parameters of disturbance type, environmental dimension, maximum fluctuation amplitude, and maximum rate of change, which form the disturbance constraint conditions of the target greenhouse under environmental control. Other methods can also be used to determine these conditions in other embodiments, which are not limited here.

[0045] It should be noted that the fluctuation pattern in this application represents the specific characteristics of the changes in environmental data of each dimension of the target greenhouse over time under different types of environmental disturbances, reflecting the intensity, rhythm and trend of the impact of different disturbances on each environmental dimension; the disturbance constraint condition represents the constraint condition of each environmental dimension under the disturbance scenario, reflecting the rigid upper limit standard that the abnormal fluctuation of environmental data in the target greenhouse environmental control cannot be broken in order to ensure the normal growth of crops and the stable operation of equipment.

[0046] In step 105, the parameters of the greenhouse environment control equipment in the target greenhouse are optimized during the control process by using all the control constraints and the disturbance constraints.

[0047] In some embodiments, optimizing the parameters of the greenhouse environment control equipment within the target greenhouse during the control process using all control constraints and the disturbance constraints can be achieved through the following steps: Determine the adjustable parameters of the greenhouse environment control equipment during the control process of the target greenhouse; The adjustable parameters are optimized by applying all control constraints and the disturbance constraints to obtain the adjustable optimized parameters. The adjustable optimization parameters are input into the greenhouse environment control equipment to optimize and regulate the target greenhouse.

[0048] The adjustable parameters of the greenhouse environmental control equipment during the control process of the target greenhouse include: the output power of the heater (0-100%), the start / stop trigger threshold (e.g., starting when the temperature is below X℃), the atomization rate of the humidifier (5-30L / h), the fan speed level (1-5), the ventilation interval (10-60 minutes / time), the light intensity level of the supplemental lighting (300-1000μmol / m²・s) and the operating duration, and the release rate of the carbon dioxide generator (100-500ppm / h). All parameters must have clearly defined physical adjustable ranges based on the rated specifications of the equipment hardware. Furthermore, in specific implementation, the adjustable parameters are optimized through all control constraints and the aforementioned disturbance constraints. The adjustable optimization parameters can be achieved in the following way: First, the core optimization objectives are defined as minimizing the control deviations in each dimension and minimizing the energy consumption of the equipment. For the first objective, the absolute control deviations in each environmental dimension are calculated, such as temperature deviation |Tactual - Treference| and carbon dioxide deviation |Cactual - Creference|. Then, the deviations are weighted and summed according to the influence weights of each dimension to obtain the total control deviation quantification value. For the second objective, the product of the unit time energy consumption and operating time of each control device is calculated and summed to obtain the total energy consumption quantification value. Subsequently, according to… Prioritize the allocation of weights for regulation, for example, prioritize ensuring environmental compliance, so set the total regulation deviation weight to 0.7 and the total energy consumption weight to 0.3, with the sum of the two weights being 1; finally, construct the optimization objective function: minimum parameter = 0.7 × total regulation deviation quantification value + 0.3 × total energy consumption quantification value. The smaller the function value, the better the regulation effect. The regulation constraints and disturbance constraints need to be used as the feasible region limit of the function. At the same time, the regulation constraints and disturbance constraints are embedded as constraint conditions into the function. By traversing the value combinations of adjustable parameters, the value points are divided according to a 5% gradient within the physically adjustable range. The parameter combination that satisfies all constraints and minimizes the objective function value is selected as the adjustable optimization parameter. In addition, in specific implementation, the adjustable optimization parameters can be input into the greenhouse environment control equipment to optimize and control the target greenhouse in the following way: the adjustable optimization parameters are finally sent to the execution unit of the greenhouse environment control equipment in real time through the industrial bus. At the same time, the environmental data after regulation is collected every 5 seconds by relying on the sensor network. If the data exceeds the regulation constraints or disturbance constraints, the above optimization process is immediately repeated to dynamically correct the parameters, so as to ensure that the regulation continuously meets the constraint requirements and completes the optimization regulation.

[0049] It should be noted that the adjustable parameters in this application refer to the specific control items that can be manually or automatically adjusted within the rated specifications of the physical hardware of the greenhouse environmental control equipment, reflecting the control capability and operating space of the equipment itself; the adjustable optimization parameters refer to the optimal parameter combination obtained after adjustment with the goal of minimizing control deviation and minimizing energy consumption, reflecting the optimal operating standard that balances the control effect and energy-saving requirements of the equipment under multiple constraints of ensuring crop growth safety, meeting environmental control standards and stable equipment operation.

[0050] Furthermore, in another aspect of this application, in some embodiments, this application provides a greenhouse environment control system, which includes a control parameter optimization unit, with reference to... Figure 4 The figure is a schematic diagram of the structure of a control parameter optimization unit according to some embodiments of this application. The control parameter optimization unit 400 includes: a data acquisition module 401, a processing module 402, and an execution module 403, which are described below: The acquisition module 401 in this application is mainly used to acquire multi-dimensional environmental data inside the target greenhouse; Processing module 402, in this application, is used to perform coupling correlation analysis on the environmental data of the target greenhouse in the environmental control process based on the coupling relationship between the environmental data of each dimension in the multi-dimensional environmental data, so as to obtain the environmental data coupling mode that plays a dominant role in the environmental control process of the target greenhouse. It should be noted that the processing module 402 in this application is also used to configure the greenhouse environment control device into the environmental data coupling mode to regulate the target greenhouse, and to determine the regulation deviation between the environmental data of each dimension in the multi-dimensional environmental data and the preset reference value of the corresponding dimension during the regulation process. Through all the regulation deviations and the environmental data coupling mode, the environmental control of the target greenhouse is constrained and analyzed to obtain the regulation constraints of the environmental data of each dimension in the target greenhouse. In addition, it should be noted that the processing module 402 in this application is also used to obtain environmental disturbance information of the target greenhouse, and to determine the disturbance constraint conditions of the target greenhouse during environmental control based on the environmental disturbance information and the historical multi-dimensional environmental data of the target greenhouse. The execution module 403 in this application is mainly used to optimize the parameters of the greenhouse environment control equipment in the target greenhouse during the control process through all the control constraints and the disturbance constraints.

[0051] In addition, this application also provides a computer device, the computer device including a memory and a processor, the memory storing code, and the processor being configured to acquire the code and execute the above-described greenhouse environment control parameter optimization method.

[0052] In some embodiments, reference Figure 5 The figure is a schematic diagram of the structure of a computer device for implementing a greenhouse environment control parameter optimization method according to some embodiments of this application. The greenhouse environment control parameter optimization method in the above embodiments can be implemented through... Figure 5 The computer device 500 shown is used to implement this, and the computer device 500 includes at least one processor 501, a communication bus 502, a memory 503, and at least one communication interface 504.

[0053] Processor 501 can be a general-purpose central processing unit (CPU) or an application-specific integrated circuit (ASIC).

[0054] The communication bus 502 can be used to transmit information between the aforementioned components.

[0055] Memory 503 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital versatile optical discs, Blu-ray discs, etc.), magnetic disks or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. Memory 503 may exist independently and be connected to processor 501 via communication bus 502. Memory 503 may also be integrated with processor 501.

[0056] The memory 503 stores program code for executing the scheme of this application, and its execution is controlled by the processor 501. The processor 501 executes the program code stored in the memory 503. The program code may include one or more software modules. The method used in the above embodiments can be implemented by the processor 501 and one or more software modules in the program code in the memory 503.

[0057] Communication interface 504 uses any transceiver-like device to communicate with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0058] In a specific implementation, as one example, a computer device may include multiple processors, each of which may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. Here, a processor may refer to one or more devices, circuits, and / or processing cores used to process data (e.g., computer program instructions).

[0059] The aforementioned computer device can be a general-purpose computer device or a special-purpose computer device. In specific implementations, the computer device can be a desktop computer, a portable computer, a network server, a handheld digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, or an embedded device. This application does not limit the type of computer device.

[0060] In addition, this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for optimizing greenhouse environment control parameters.

[0061] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0062] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for optimizing greenhouse environmental control parameters, wherein, The method of controlling the environment of a target greenhouse using greenhouse environmental control equipment is characterized by the following steps: Collect multi-dimensional environmental data inside the target greenhouse; Based on the coupling relationship between the environmental data of each dimension in the multi-dimensional environmental data, a coupling correlation analysis is performed on the environmental data of each dimension of the target greenhouse in the environmental control process to obtain the environmental data coupling mode that plays a dominant role in the environmental control process of the target greenhouse. The greenhouse environment control equipment is configured to the environmental data coupling mode to regulate the target greenhouse, and the regulation deviation between each dimension of the multi-dimensional environmental data and the preset reference value of the corresponding dimension is determined during the regulation process. The environmental control of the target greenhouse is constrained by all the regulation deviations and the environmental data coupling mode to obtain the regulation constraints of each dimension of the environmental data in the target greenhouse. Obtain environmental disturbance information of the target greenhouse, and determine the disturbance constraint conditions of the target greenhouse during environmental control based on the environmental disturbance information and the historical multi-dimensional environmental data of the target greenhouse. The parameters of the greenhouse environment control equipment in the target greenhouse are optimized during the control process by using all the control constraints and the disturbance constraints.

2. The method as described in claim 1, characterized in that, The multi-dimensional environmental data includes air temperature, relative humidity, soil temperature, soil moisture content, carbon dioxide concentration, light intensity, and duration of light exposure.

3. The method as described in claim 1, characterized in that, Based on the coupling relationships between the various dimensions of environmental data in the multi-dimensional environmental data, a coupling correlation analysis is performed on the environmental data of the target greenhouse in the environmental control process. The specific environmental data coupling modes that play a dominant role in the environmental control process of the target greenhouse include: The multi-dimensional environmental data is denoised to obtain denoised multi-dimensional environmental data. Determine the coupling relationship between the environmental data of each dimension in the denoised multi-dimensional environmental data; Determine the physiological characteristics of the target greenhouse crops; Based on the physiological characteristics, determine the influence weights of environmental data in various dimensions on the crops during the environmental control process in the target greenhouse; The environmental data coupling pattern in which the target greenhouse plays a dominant role in the environmental control process is determined by the coupling relationship and all the influence weights.

4. The method as described in claim 1, characterized in that, The greenhouse environment control equipment is configured to the environmental data coupling mode to regulate the target greenhouse, and the regulation deviation between each dimension of the multi-dimensional environmental data and the preset reference value of the corresponding dimension is determined during the regulation process. Specifically, this includes: The greenhouse environment control equipment is configured to the environmental data coupling mode to regulate the target greenhouse; Collect environmental data from each dimension of the multi-dimensional environmental data during the regulation process to obtain regulation environmental data for each dimension. The environmental data for each dimension is compared with the preset reference value for the corresponding dimension to determine the control deviation between the environmental data for each dimension and the preset reference value for the corresponding dimension during the control process.

5. The method as described in claim 1, characterized in that, By performing constraint analysis on the environmental control of the target greenhouse using all regulation deviations and the environmental data coupling mode, the specific regulation constraints of the environmental data in various dimensions of the target greenhouse are obtained, including: Based on all the control deviations and the environmental data coupling mode, determine the mutual constraints between environmental data of various dimensions in the target greenhouse environmental control process; The control constraints of environmental data in various dimensions in the target greenhouse are determined by the interrelationships between environmental data in various dimensions.

6. The method as described in claim 1, characterized in that, Based on the aforementioned environmental disturbance information and historical multi-dimensional environmental data of the target greenhouse, the specific disturbance constraint conditions for environmental control of the target greenhouse include: Acquire historical, multi-dimensional environmental data for the target greenhouse; Based on the environmental interference information and the historical multi-dimensional environmental data, determine the fluctuation patterns of environmental data in each dimension under different interferences; The perturbation constraints of the target greenhouse under environmental control were determined by analyzing all the fluctuation patterns.

7. The method as described in claim 1, characterized in that, The optimization of the parameters of the greenhouse environment control equipment in the target greenhouse during the regulation process is specifically achieved by using all regulation constraints and the aforementioned disturbance constraints, including: Determine the adjustable parameters of the greenhouse environment control equipment during the control process of the target greenhouse; The adjustable parameters are optimized by applying all control constraints and the disturbance constraints to obtain the adjustable optimized parameters. The adjustable optimization parameters are input into the greenhouse environment control equipment to optimize and regulate the target greenhouse.

8. A greenhouse environment control system, wherein, The system controls the environment of a target greenhouse using greenhouse environment control equipment. The system includes a control parameter optimization unit, characterized in that the control parameter optimization unit comprises: The data acquisition module is used to collect multi-dimensional environmental data inside the target greenhouse. The processing module is used to perform coupling correlation analysis on the environmental data of the target greenhouse in the environmental control process based on the coupling relationship between the environmental data of each dimension in the multi-dimensional environmental data, so as to obtain the environmental data coupling mode that plays a dominant role in the environmental control process of the target greenhouse. The processing module is further configured to configure the greenhouse environment control equipment into the environmental data coupling mode to regulate the target greenhouse, and to determine the regulation deviation between the environmental data of each dimension in the multi-dimensional environmental data and the preset reference value of the corresponding dimension during the regulation process. The module performs constraint analysis on the environmental control of the target greenhouse through all the regulation deviations and the environmental data coupling mode to obtain the regulation constraints of the environmental data of each dimension in the target greenhouse. The processing module is also used to acquire environmental disturbance information of the target greenhouse, and determine the disturbance constraint conditions of the target greenhouse during environmental control based on the environmental disturbance information and the historical multi-dimensional environmental data of the target greenhouse. The execution module is used to optimize the parameters of the greenhouse environment control equipment in the target greenhouse during the control process by using all the control constraints and the disturbance constraints.

9. A computer device, characterized in that, The computer device includes a memory and a processor, the memory storing code, and the processor being configured to retrieve the code and execute the greenhouse environment control parameter optimization method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the greenhouse environment control parameter optimization method as described in any one of claims 1 to 7.

Images