Greenhouse environment regulation and control method and system for plant cultivation

Abstract

The invention relates to the technical field of agricultural facility control, and discloses a greenhouse environment regulation and control method and system for plant cultivation. The method comprises the following steps: initializing an environmental parameter benchmark based on a plant growth model, wherein the plant growth model is predefined according to a plant type and a growth cycle; collecting multi-source environment sensor data in the greenhouse in real time; performing time sequence smoothing processing on the multi-source environment sensor data to obtain a smooth environment data sequence; calculating a deviation degree between the smooth environment data sequence and an environment parameter reference, wherein the deviation degree is a weighted sum of parameter deviations; identifying a potential environmental anomaly when the degree of deviation exceeds an adaptive threshold; analyzing the duration and the change trend of the potential environmental anomaly, and confirming a real environmental anomaly event; the occurrence frequency and the influence range of the real environment abnormal event are counted, and an environment risk index is calculated; and dynamically adjusting the environment monitoring frequency and the control strategy according to the environment risk index.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of agricultural facility control, in particular to a greenhouse environment regulation method and system for plant cultivation. BACKGROUND

[0002] Current greenhouse environment regulation mainly adopts fixed threshold alarm and manual intervention. The existing technology relies on single sensor independent detection for environmental parameter monitoring, lacks multi-parameter collaborative analysis capability. The benchmark setting method is static and fixed, which cannot meet the specific needs of different plant species and growth stages. The data processing process is simple, and sensor noise and transient fluctuation interference are not effectively filtered out. The abnormal judgment mechanism is rigid, usually based on fixed threshold binary judgment, which cannot identify gradual environmental deterioration. The response strategy lacks adaptability, and the monitoring frequency and control intensity cannot be dynamically adjusted according to the risk level. The existing method needs to solve the key technical problems of multi-source data fusion, dynamic benchmark setting, intelligent abnormal identification and adaptive regulation.

[0003] Traditional greenhouse environment regulation system has obvious shortcomings in intelligence level and precise control. The environmental parameter benchmark setting is empirical, and no direct correlation with the plant growth model is established. The data acquisition frequency is fixed, which cannot balance the monitoring accuracy and system energy consumption. The smoothing filter algorithm is simple, which is difficult to effectively separate the real environmental change and the measurement noise. The deviation calculation weight is fixed, which does not consider the different influences of different environmental factors on plant growth. The adaptive threshold setting lacks theoretical guidance, and the false alarm and missed alarm risk is high. The abnormal confirmation method is subjective, and the duration threshold and trend judgment standard are set randomly. The risk index calculation dimension is single, which cannot comprehensively evaluate the spatio-temporal distribution characteristics of the abnormality. The regulation strategy generation is linear, which lacks multi-objective optimization mechanism. The existing technology needs to establish a whole-process intelligent regulation scheme from data acquisition to strategy generation. SUMMARY

[0004] The purpose of the present application is to provide a greenhouse environment regulation method and system for plant cultivation to solve the problems raised in the background.

[0005] To achieve the above purpose, the present application provides a greenhouse environment regulation method for plant cultivation, which comprises:

[0006] initializing the environmental parameter benchmark based on the plant growth model, the plant growth model being predefined according to the plant type and growth cycle;

[0007] real-time acquisition of multi-source environmental sensor data inside the greenhouse, the multi-source environmental sensor data including temperature, humidity, carbon dioxide concentration and light intensity;

[0008] time series smoothing processing of the multi-source environmental sensor data to obtain a smoothed environmental data sequence;

[0009] calculating a deviation degree of the smoothed environment data sequence from the environment parameter benchmark, the deviation degree being a weighted sum of deviations of respective parameters;

[0010] identifying a potential environment anomaly when the deviation degree exceeds an adaptive threshold;

[0011] analyzing a duration and a change trend of the potential environment anomaly to confirm a real environment anomaly event;

[0012] counting a frequency of occurrence and an influence range of the real environment anomaly event to calculate an environment risk index;

[0013] dynamically adjusting an environment monitoring frequency and a control strategy according to the environment risk index.

[0014] Preferably, when initializing the environment parameter benchmark based on the plant growth model, the method comprises:

[0015] obtaining plant growth stage information, the plant growth stage information being extracted from a planting plan;

[0016] querying a standard environment parameter library according to the plant growth stage information to obtain target parameter values of respective stages;

[0017] correcting the target parameter values in combination with greenhouse structure parameters and historical climate data to generate the environment parameter benchmark;

[0018] wherein the greenhouse structure parameters include a greenhouse area and a height, and the historical climate data includes seasonal average temperature and humidity.

[0019] Preferably, when performing time series smoothing processing on the multi-source environment sensor data, the method comprises:

[0020] filtering original sensor data by using a sliding window algorithm, a size of the sliding window being dynamically adjusted according to the environment risk index, and a moving average value of data in the window being calculated as a smoothed environment data sequence;

[0021] when the environment risk index increases, reducing the size of the sliding window to improve response speed; and when the environment risk index decreases, increasing the size of the sliding window to improve stability.

[0022] Preferably, when calculating the deviation degree of the smoothed environment data sequence from the environment parameter benchmark, the method comprises:

[0023] assigning a weight coefficient to each environment parameter, the weight coefficient being determined based on an influence degree of the parameter on plant growth;

[0024] calculating an absolute deviation of a current value of each parameter from a corresponding value in the environment parameter benchmark, summing the absolute deviations multiplied by the weight coefficients to obtain the deviation degree;

[0025] The adaptive threshold is dynamically calculated according to historical deviation data and plant growth stages.

[0026] Preferably, the analysis of the duration and change trend of the potential environmental anomaly comprises:

[0027] Extracting data points in the time period of the potential environmental anomaly, calculating the duration of the anomaly, fitting the change trend of the anomaly data by using a linear regression method to obtain a trend slope;

[0028] When the duration of the anomaly exceeds a preset duration threshold and the absolute value of the trend slope is greater than a trend threshold, the real environmental anomaly event is confirmed.

[0029] Preferably, the statistics of the occurrence frequency and the impact range of the real environmental anomaly event comprises:

[0030] Recording the type and occurrence time of each real environmental anomaly event, calculating the number of anomaly events in a unit time as the occurrence frequency, and evaluating the parameter deviation range caused by the anomaly event as the impact range;

[0031] The occurrence frequency and the impact range are normalized and then combined with a weight to obtain an environmental risk index.

[0032] Preferably, the environmental monitoring frequency is dynamically adjusted according to the environmental risk index, comprising:

[0033] Setting a basic monitoring frequency, the basic monitoring frequency being a fixed value;

[0034] Calculating a frequency adjustment factor according to the environmental risk index, the frequency adjustment factor being positively correlated with the environmental risk index, multiplying the basic monitoring frequency by the frequency adjustment factor to obtain an adjusted environmental monitoring frequency;

[0035] Controlling the sensor data collection interval according to the adjusted environmental monitoring frequency.

[0036] Preferably, the control strategy is dynamically adjusted according to the environmental risk index, comprising:

[0037] When the environmental risk index is lower than a low risk threshold, a conservative control strategy is adopted, and only major deviations are adjusted;

[0038] When the environmental risk index is between the low risk threshold and a high risk threshold, an active control strategy is adopted, and the environmental parameters are real-time fine-tuned;

[0039] When the environmental risk index is higher than the high risk threshold, an aggressive control strategy is adopted, and all standby environmental devices are immediately started.

[0040] Preferably, the method further comprises the following steps:

[0041] According to the environmental risk index, future environmental trends are predicted, preventive regulation instructions are generated, the preventive regulation instructions are fused with real-time control strategies, comprehensive control signals are output, and all data in the regulation process are recorded for updating the plant growth model and the environmental parameter benchmark.

[0042] Preferably, the present application also includes a greenhouse environment regulation system for plant cultivation, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of the above-mentioned greenhouse environment regulation method for plant cultivation when executing the computer program.

[0043] Compared with the prior art, the present application has the following beneficial effects:

[0044] The deviation degree of the smoothed environmental data sequence and the environmental parameter benchmark is calculated, and the deviation degree is the weighted sum of the parameter deviations. The smoothed environmental data sequence is generated by moving average or exponential smoothing method to eliminate random fluctuations and measurement noise. The environmental parameter benchmark is dynamically set according to the plant growth model, reflecting the optimal environmental conditions at different growth stages. The parameter deviation calculation uses the absolute value or square difference method to quantify the difference between the actual value and the benchmark value. The weighted sum calculation considers the relative importance of temperature, humidity, carbon dioxide concentration and light intensity on plant growth. The weight coefficient is obtained by expert knowledge or historical data training, reflecting the influence degree of different environmental factors. The deviation degree value is normalized for cross-parameter comparison and comprehensive evaluation. When the current deviation degree exceeds the adaptive threshold, potential environmental abnormalities are identified. The adaptive threshold is dynamically adjusted according to the environmental stability requirements and plant tolerance. The threshold updating mechanism considers factors such as seasonal changes, weather conditions and plant growth status. The potential abnormality identification adopts a soft decision method, providing risk warning rather than absolute alarm. The identification process is carried out in real time to ensure the timeliness of abnormality discovery. Through deviation degree calculation and adaptive threshold judgment, multi-parameter comprehensive evaluation of environmental abnormalities is realized. The weighted sum integrates multi-dimensional information to avoid single parameter misjudgment; the adaptive threshold improves the judgment flexibility and reduces the false alarm probability.

[0045] The occurrence frequency and influence range of statistical real environment abnormal events are calculated to calculate the environment risk index. The occurrence frequency statistics adopts a sliding time window method to record the number of abnormal events in a unit time. The influence range evaluation determines the geographical distribution area of abnormal influence through spatial interpolation analysis. The risk index calculation integrates the frequency and range dimensions, using weighted geometric mean or fuzzy reasoning method. The index value quantifies the potential threat degree of environmental abnormalities to plant growth. The risk assessment considers the dynamic characteristics such as abnormal duration, intensity change and recovery speed. The index is graded into multiple risk levels, corresponding to different response strategies. According to the environmental risk index, the environmental monitoring frequency and control strategy are dynamically adjusted. The monitoring frequency adjustment adopts an adaptive sampling algorithm, which increases the sampling rate in high-risk situations and reduces the sampling rate in low-risk situations to save energy. The control strategy optimization includes the coordinated configuration of actuator response speed, adjustment amplitude and action time. In high-risk situations, active preventive control is adopted, and in low-risk situations, responsive adjustment is adopted. The strategy adjustment process is smooth transition to avoid system oscillation. The dynamic adjustment mechanism realizes resource optimization configuration and improves system energy efficiency. Through the coordinated action of abnormality statistics, risk quantification and dynamic adjustment, intelligent control of greenhouse environment is realized. Frequency statistics identify abnormal rules, influence range evaluation determines severity, risk index quantifies comprehensive threat, and dynamic adjustment realizes precise response. This closed-loop control method significantly improves the fine and intelligent level of greenhouse environment management. BRIEF DESCRIPTION OF DRAWINGS

[0046] Figure 1 A working principle diagram of the greenhouse environment regulation method for plant cultivation described in the present application;

[0047] Figure 2 A flowchart for initializing environment parameter benchmarks based on plant growth models;

[0048] Figure 3 A flowchart for calculating the deviation of smooth environment data sequence from environment parameter benchmarks;

[0049] Figure 4 A diagram for analyzing the occurrence frequency and influence range of greenhouse environment abnormal events;

[0050] Figure 5 A comparison analysis diagram of predicted and actual values of greenhouse environment risk index. DETAILED DESCRIPTION

[0051] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0052] Please see Figure 1 This invention provides a greenhouse environment control method and system for plant cultivation. The method includes: initializing environmental parameter benchmarks based on a plant growth model, which is predefined according to plant type and growth cycle to ensure that the benchmark parameters meet the needs of each stage of plant growth; real-time acquisition of multi-source environmental sensor data inside the greenhouse, including key parameters such as temperature, humidity, carbon dioxide concentration, and light intensity, transmitted to a processing unit at fixed intervals via a sensor network; time-series smoothing of the acquired multi-source environmental sensor data, using a sliding window algorithm to filter noise and generate a smoothed environmental data sequence to improve data reliability and stability; calculating the deviation of the smoothed environmental data sequence from the environmental parameter benchmark, where the deviation is defined as the weighted sum of the deviations of each parameter, and the weighting coefficients are dynamically allocated based on the degree of influence of each parameter on plant growth; when the deviation exceeds an adaptive threshold, the system identifies a potential environmental anomaly, which is adaptively calculated based on historical data and plant growth stages to avoid misjudgment; analyzing the duration and trend of potential environmental anomalies, and using statistical methods to confirm actual environmental anomaly events, ensuring that only persistent and clearly trending anomalies are addressed. The frequency and impact range of real-world environmental anomalies are statistically analyzed to calculate an environmental risk index, which comprehensively reflects environmental stability. Environmental monitoring frequency and control strategies are dynamically adjusted based on the environmental risk index; monitoring frequency is increased and proactive control measures are adopted when the risk is high, while the frequency is reduced to conserve resources when the risk is low.

[0053] Example 1: See Figure 2 In practical implementation, obtaining plant growth stage information is the initial step. This information is extracted from a pre-defined planting plan, which is structured data stored in the system database as a digital file. This plan includes key time nodes such as plant variety identifiers, sowing dates, expected germination periods, vegetative growth periods, flowering periods, and maturity periods. The system dynamically determines the specific growth stage of the plant by parsing the planting plan file and combining it with real-time clock data. For example, it determines whether the plant is in the seedling stage or the rapid growth stage. This process is implemented using a date comparison algorithm to ensure the accuracy of growth stage division. The system then queries a standard environmental parameter database based on the plant growth stage information. This database is a pre-built knowledge base that stores ideal environmental parameter ranges for various typical plants at different growth stages, verified by agricultural experts. The query operation is performed using a database query language. The input parameters are the plant species code and the growth stage code. The output is a set of target parameter values ​​for the corresponding stage. These target parameter values ​​include, but are not limited to, target values ​​for temperature, humidity, carbon dioxide concentration, and light intensity. Each parameter is typically represented as a target range or optimal value, such as the suitable daytime temperature range or the minimum nighttime humidity requirement. The standard environmental parameter library supports version management, allowing for updates and maintenance based on the latest research findings.

[0054] It's understandable that the target parameter values ​​obtained from the query need to be localized to adapt to the unique microclimate conditions of a specific greenhouse. A key step is to adjust the target parameter values ​​by combining greenhouse structural parameters and historical climate data. Greenhouse structural parameters are static data describing the physical characteristics of the greenhouse, including its floor area, internal vertical height, building orientation, type and transmittance of covering materials, and ventilation system configuration. These parameters directly affect heat accumulation, airflow, and light distribution within the greenhouse. Historical climate data are long-term statistical data obtained from local weather stations or greenhouse historical records, including seasonal average temperature, average humidity, typical sunshine hours, and the frequency and intensity of extreme weather events. The adjustment process uses a weighted adjustment algorithm. The algorithm calculates a correction coefficient for each target parameter value based on the greenhouse structural parameters and historical climate data. For example, for the temperature target value, it will be adjusted upwards or downwards based on the greenhouse's insulation performance and the local seasonal average temperature, generating an environmental parameter benchmark that better reflects the actual application scenario.

[0055] In practice, the process of generating environmental parameter baselines is systematic. The corrected target parameter values ​​are organized into a time-series data structure, where each data point corresponds to a specific day or key growth milestone in the plant growth cycle. Environmental parameter baseline files are saved in a system configuration file format, containing metadata such as parameter name, baseline value, valid time range, and data source identifier. The system automatically triggers the environmental parameter baseline initialization process upon startup or when a planting plan change event is detected. The initialization process includes an integrity verification step, checking that all necessary parameters have been correctly assigned values ​​to avoid null or out-of-bounds values. After environmental parameter baseline initialization is complete, the system records an initialization log, including the baseline version number, generation timestamp, and the planting plan identifier used for auditing and traceability. Optionally, during the environmental parameter baseline initialization phase, the system can integrate real-time sensor calibration data to further improve the accuracy of the baseline. Multi-source environmental sensors deployed in the greenhouse environment perform a self-check and calibration process after system startup. The calibration data includes the sensor's zero-point offset, sensitivity coefficient, etc. The system incorporates calibration data as an input factor in the correction calculation of target parameter values. For example, if the light intensity sensor has a known positive measurement bias, corresponding compensation will be made when setting the light intensity benchmark, thereby reducing system errors and achieving higher consistency between the environmental parameter benchmark and the actual physical measurement values. This integrated calibration mechanism ensures that the environmental parameter benchmark not only relies on theoretical models and historical data but also closely integrates with the characteristics of the actual measurement system.

[0056] In some embodiments, the initialization process of the environmental parameter baseline is designed to be repeatable and dynamically fine-tuned. After the system has been running for a period of time, if it receives updated planting plan instructions or detects a significant change in the external climate pattern, the system can restart the initialization process and generate a new version of the environmental parameter baseline. The dynamic fine-tuning function allows the system to make small adjustments to individual parameters in the environmental parameter baseline based on feedback from short-term environmental regulation effects without system downtime. The fine-tuning logic is based on preset rules; for example, if the actual growth rate of plants deviates from the expected model multiple times during a certain growth stage, the light or temperature baseline values ​​for that stage are automatically fine-tuned. It is understood that the storage and access method of the environmental parameter baseline has a direct impact on system performance. The generated environmental parameter baseline is usually loaded into the system's high-speed memory cache to reduce data access latency during subsequent real-time comparison calculations. The baseline data is organized in the cache as key-value pairs or array structures, where the key is a time index or growth stage code, and the value is the corresponding set of parameters. The system sets up an access interface for the environmental parameter baseline, and other processing modules obtain the environmental parameter baseline values ​​at the current time or a specified growth stage by calling the interface. The interface design ensures data consistency and thread safety. Meanwhile, a complete copy of the baseline will be persistently stored in non-volatile memory to prevent data loss due to system power failure or restart.

[0057] In practice, the environmental parameter baseline initialization module has clear data dependencies on other modules of the system. The initialization module relies on the planting plan management module for plant growth stage information, the basic information database module for greenhouse structural parameters and historical climate data, and interacts with the sensor management module to obtain calibration data. Successful execution of the initialization process is a prerequisite for subsequent environmental monitoring, deviation calculation, and control strategy application. The system status monitor continuously checks the status of the environmental parameter baseline. If invalid or expired baseline data is detected, an alarm is triggered and a re-initialization attempt is made, thus ensuring the reliability of the entire environmental control chain. The entire initialization process emphasizes automation and data-driven approaches, minimizing the need for manual intervention and improving the efficiency and accuracy of intelligent greenhouse environmental control.

[0058] Optionally, for large-scale or zoned greenhouse clusters, environmental parameter baseline initialization supports zone-specific configuration. The system can independently initialize environmental parameter baselines for different areas of the greenhouse, with each area associated with different planting plans or possessing unique structural parameters. Zone initialization allows for refined and differentiated environmental management of different crops within the same greenhouse or different growth stages of the same crop. The system maintains a zone mapping table, associating physical sensor nodes with logical zone identifiers. During initialization, it retrieves the corresponding planting plan information and structural parameters based on the zone identifier, generating a set of parallel and independent environmental parameter baselines. This zone management capability significantly improves the flexibility and targeting of environmental control in complex greenhouse scenarios.

[0059] Example 2: See Figure 3 In practical implementation, when performing time-series smoothing on multi-source environmental sensor data, the system uses a sliding window algorithm to filter the raw sensor data. The size of the sliding window is dynamically adjusted according to the real-time calculated environmental risk index. The environmental risk index is a numerical indicator reflecting the stability of the greenhouse environment. When the environmental risk index increases, it indicates that environmental fluctuations are intensifying, and the system will reduce the sliding window size to improve the agility of data response, for example, reducing the window size from the default 15 data points to 8 data points. Conversely, when the environmental risk index decreases, it indicates that the environment is becoming more stable, and the system will increase the sliding window size to 25 data points or more to enhance the smoothing effect of the data. The sliding window algorithm manages the data flow in the form of a queue. When a new data point enters the window, the oldest data point is removed to maintain the freshness of the data within the window. The moving average of the data within the window is calculated as the smoothing environment data sequence. The moving average is calculated using the arithmetic mean method, which involves summing the values ​​of all data points within the window and dividing by the window size. For certain parameters, such as light intensity, if the data distribution is skewed, a weighted moving average method is used, assigning higher weights to more recent data points. The smoothing environment data sequence is stored in a circular buffer, the size of which matches the maximum possible sliding window size, ensuring uninterrupted data continuity. During the smoothing process, the system integrates an outlier detection mechanism, using a standard deviation-based Z-score method to identify and remove obvious outliers. The Z-score threshold is set to 3, meaning data points exceeding three times the standard deviation of the mean are considered noise and filtered out to prevent outliers from distorting the smoothing results.

[0060] In some embodiments, the dynamic adjustment logic of the sliding window size is implemented through a mapping function. The function takes the environmental risk index as input and outputs the recommended window size value. The mapping function uses a piecewise linear interpolation method, predefining several key points of the environmental risk index and their corresponding window sizes. For example, the window size is 30 when the environmental risk index is 0, 15 when the environmental risk index is 0.5, and 5 when the environmental risk index is 1. The system calculates the actual window size based on the current environmental risk index value through linear interpolation, ensuring a smooth adjustment process without abrupt changes. Window size adjustment events trigger data reprocessing. The system clears the current window and re-accumulates data points based on the new window size for smoothing calculations, while recording adjustment logs for auditing. It is understood that the quality of the smoothed environmental data sequence directly affects the accuracy of subsequent deviation calculations. Therefore, the system monitors stability indicators of the smoothing process, such as the variance of the moving average. If the variance remains too high, a calibration check is triggered.

[0061] When calculating the deviation of the smoothed environmental data sequence from the environmental parameter baseline, the system assigns a weight coefficient to each environmental parameter. The weight coefficient is determined based on the parameter's influence on plant growth, with the influence data derived from a plant physiological model. For example, during the active photosynthetic period, the weight coefficient for light intensity is set to 0.4, for temperature to 0.3, for humidity to 0.2, and for carbon dioxide concentration to 0.1. These weight coefficients are stored in a configurable weight table and dynamically updated as the plant grows. The update event is activated by a growth stage switching trigger. To ensure dimensional consistency, the relative deviation of the current smoothed value of each parameter from the corresponding value in the environmental parameter baseline is calculated. The relative deviation is the difference between the current smoothed value and the baseline value, divided by the baseline value, and the absolute value is taken to obtain a dimensionless percentage. The overall deviation is obtained by multiplying the relative deviation of each parameter by its weight coefficient and summing the results. The deviation calculation formula is as follows:

[0062]

[0063] in: Indicates the degree of deviation. Indicates the number of environmental parameters. Indicates the first The weighting coefficients of each parameter, Indicates the first The current smoothing value of each parameter. Indicates the first The environmental parameter baseline values ​​for each parameter are calculated. The deviation calculation process is executed periodically, with the calculation frequency synchronized with the data acquisition frequency.

[0064] In some embodiments, the calculation of the adaptive threshold relies on historical deviation data and current plant growth stage information. Historical deviation data refers to a sequence of deviation values ​​calculated over a past period, typically with a time window length of 24 hours or a complete growth cycle. The system uses moving average statistical methods to analyze the historical sequence, such as calculating the mean and standard deviation of historical deviations. The adaptive threshold is set to the historical mean plus K times the standard deviation, with the K value adjusted according to the plant growth stage. During sensitive stages such as the seedling stage, the K value is set to 1.5 to lower the threshold and increase sensitivity, while during the maturity stage, the K value is set to 2.5 to increase the threshold and reduce false alarms. Plant growth stage information is obtained from the planting plan module and used to modulate the K value selection logic. The adaptive threshold update cycle is set to once per hour to ensure that the threshold keeps pace with environmental changes. Optionally, the system also introduces a minimum threshold guarantee mechanism to prevent oversensitivity caused by an excessively low threshold. The minimum threshold is based on a fixed deviation percentage setting, for example, setting the minimum adaptive threshold to 0.05 (i.e., a 5% relative deviation baseline).

[0065] It is understandable that deviation calculation and adaptive threshold judgment are continuous pipeline processes. The calculated deviation is immediately compared with the current adaptive threshold. If the deviation exceeds the threshold, it is marked as a potential environmental anomaly, and the deviation value is appended to the historical deviation database for subsequent threshold updates. The system maintains an independent relative deviation calculation pipeline for each environmental parameter, but the overall deviation is the result of aggregating the relative deviations of all parameters. This allows the system to focus on both the overall environmental state and trace the contribution of individual parameters. In specific implementation, the allocation of weight coefficients considers the coupling effect between parameters. For example, when temperature and high humidity occur simultaneously, they may cause superimposed stress on plants. Therefore, the system defines an interaction weight item in the weight table, but for the sake of simplifying the initial implementation, the interaction item is temporarily set to zero and can be optimized through machine learning models in the future. Both the smoothed environmental data sequence and the deviation value are timestamped and recorded in the time series database, supporting subsequent trend analysis and backtracking queries. Optionally, for resource-constrained embedded systems, smoothing and deviation calculations can use fixed-point arithmetic operations to improve efficiency while ensuring that the calculation accuracy meets the needs of agricultural applications.

[0066] Example 3: In specific implementation, when analyzing the duration and trend of potential environmental anomalies, the system starts operating from the moment marked as a potential environmental anomaly, extracting all data points within the time period of the potential environmental anomaly. The exact starting point of the time period is the sampling timestamp when the deviation first exceeds the adaptive threshold, and the ending point of the time period is the first sampling timestamp after the deviation continuously falls back below the adaptive threshold and remains stable. The system extracts these time-ordered data point sequences from a circular buffer, which is specifically used to store the most recent smoothed environmental data sequence and the corresponding deviation calculation results. The duration of the anomaly is calculated directly by comparing the difference between the end timestamp and the start timestamp of the time period. The unit of the time difference can be seconds, minutes, or hours depending on the system configuration. For example, a potential temperature anomaly that starts at 10:05:00 and ends at 10:15:30 has an anomaly duration of 10 minutes and 30 seconds. The system records the anomaly duration as a key attribute in a temporary event object.

[0067] The system uses linear regression to fit the changing trends of outlier data. The extracted data point sequence is used as input. The X-axis represents the elapsed time relative to the outlier's origin, and the Y-axis represents the corresponding deviation or outlier parameter value. The linear regression algorithm calculates the best-fit line for these data points using the least squares method. The final output is the trend slope, which is the slope of the fitted line. The trend slope is a signed value; a positive trend slope indicates an upward trend in deviation or parameter value during the period of the outlier, while a negative trend slope indicates a downward trend. The system also calculates a goodness-of-fit index for linear regression, such as the R-squared value, to assess the reliability of the trend analysis, but the R-squared value is not directly used in the decision-making logic. When the duration of an anomaly exceeds a preset duration threshold and the absolute value of the trend slope is greater than the trend threshold, the system will confirm the potential environmental anomaly as a real environmental anomaly. The preset duration threshold is a fixed value set for different types of environmental parameters. For example, the preset duration threshold for temperature parameters may be set to 5 minutes, while the preset duration threshold for humidity parameters may be set to 10 minutes. The trend threshold also varies depending on the parameter and is an empirical constant used to filter out fluctuations that, although they last a long time, have slight changes.

[0068] In practical implementation, after confirming a real-world environmental anomaly, the system creates a structured record of the event. This record includes a unique event identifier, anomaly parameter type, event start timestamp, event end timestamp, anomaly duration, trend slope value, maximum deviation value, and the specific numerical sequence of parameters that triggered the event. This record is persistently stored in a dedicated event log database, which is indexed for subsequent quick queries and analysis by time and type. The event confirmation logic is managed by a state machine, which monitors the entire state transition from potential anomaly to confirmed anomaly, ensuring that the lifecycle of each event is fully tracked. When calculating the frequency and impact of real-world environmental anomalies, the system periodically scans the event log database, counting the number of anomalies per unit time as the frequency. The length of the unit time window is configurable, for example, it can be set to 1 hour, 4 hours, or 24 hours. The system uses a sliding time window to count the number of real-world environmental anomalies that end within the window, for example, counting how many real-world temperature anomalies occurred in the past hour. The frequency is an integer value. The range of parameter deviations caused by abnormal events is assessed as the impact range. The impact range is calculated for each real-world abnormal event. It is represented by the maximum absolute percentage deviation between the actual value of the abnormal parameter and the baseline value of the environmental parameter during the duration of the event. For example, in a temperature abnormal event, the temperature reaches a maximum of 30°C, while the baseline value is 25°C. The maximum absolute deviation is 5°C, and the deviation percentage is (5 / 25)*100%=20%. This percentage is the impact range value of the event. The system records the impact range for each event.

[0069] The Environmental Risk Index (ERI) is obtained by weighting and combining the normalized frequency and impact range. Normalization maps the raw values ​​of frequency and impact range to a scale between 0 and 1. Frequency normalization uses a linear normalization method, dividing by the theoretically maximum number of events possible within a statistical period. The theoretical maximum is set based on historical extreme cases. Impact range normalization also linearly maps the actual percentage to the 0-1 interval, where 0% is mapped to 0, and 100% or a set maximum reasonable deviation percentage is mapped to 1. The normalized frequency is denoted as F_norm, and the normalized impact range is denoted as I_norm. The Environmental Risk Index (ERI) is calculated using the following formula:

[0070]

[0071] in: This represents the environmental risk index, a value between 0 and 1. It is the normalized frequency of occurrence; This is the normalized range of influence; and These are weighting coefficients, satisfying... The weighting coefficients α and β can be adjusted based on plant species and growth stage. For example, during sensitive growth periods, a higher weight β might be assigned to the influence range I_norm to better reflect the severity of abnormal events. The environmental risk index is recalculated periodically, with the update cycle aligned with the statistical unit time window.

[0072] In some embodiments, the frequency statistics can be further refined to distinguish different types of abnormal events. For example, temperature anomalies and humidity anomalies can be counted separately, and then a weighted sum can be calculated as the overall frequency of occurrence. The weights for different types of anomalies can be different. It is understood that the calculation of the environmental risk index is to quantify the overall instability of the greenhouse environment. A higher index value indicates a greater risk to environmental control, requiring more proactive intervention. The system records the calculated environmental risk index along with the current timestamp and publishes it to the system's message bus for subscription by the environmental monitoring frequency adjustment module and the control strategy adjustment module. Optionally, for the calculation of the impact range, in addition to using the maximum absolute deviation percentage, the system can also use the average deviation percentage or the integral value of the deviation area as alternative indicators to more comprehensively reflect the overall impact intensity of abnormal events. The event log database is designed to support advanced queries, such as querying the frequency distribution of specific types of anomalies at specific growth stages. This aggregated data can be used for long-term trend analysis and model optimization. Historical data of the environmental risk index will form a time series. The system can perform simple trend analysis on this time series, such as calculating a moving average, to determine whether environmental risk is increasing or decreasing, providing input for predictive regulation.

[0073] In some embodiments, the statistical process needs to consider the uniqueness of events to avoid duplicate counting. For example, if a long-duration anomalous event spans two statistical time windows, the system is configured to attribute it entirely to the time window at the end of the event, ensuring statistical accuracy. The environmental risk index calculation module has a fault-tolerant mechanism; if no real environmental anomaly occurs within the statistical time window, the occurrence frequency is... If the impact of all events is small, then the value is 0. It may be close to 0, at which point the Environmental Risk Index (ERI) will be at a low level, reflecting a good environmental condition.

[0074] See Figure 4This chart presents key data visualization results of greenhouse environmental control methods and systems used for plant cultivation, focusing on the statistical analysis of the frequency and impact range of real-world environmental anomalies. The chart categorizes anomalies into temperature, humidity, CO2 concentration, light intensity, and combined anomalies, using blue bars to show the frequency of each type of anomaly, reflecting the occurrence frequency of different environmental factors within a unit of time. Red lines and node markings represent the impact range, quantifying the degree to which various anomalies cause environmental parameters to deviate from baselines. This chart provides direct data support for calculating the environmental risk index. By intuitively comparing the occurrence patterns and impact intensity of different types of anomalies, it helps the system accurately determine the environmental risk level, thus providing a basis for dynamically adjusting environmental monitoring frequency and control strategies. It addresses the technical pain points of traditional greenhouse environmental control, such as the single statistical dimension of anomalies and the lack of intuitive assessment, promoting the transformation of greenhouse environmental control from experience-based to data-driven intelligent control, and laying a data visualization foundation for achieving multi-parameter collaborative intelligent management of the greenhouse environment.

[0075] Example 4: In specific implementation, when dynamically adjusting the environmental monitoring frequency based on the environmental risk index, the system sets a basic monitoring frequency. This basic monitoring frequency is a fixed value, for example, collecting sensor data once every 300 seconds. This value is a conservative value pre-set based on hardware capabilities, energy consumption considerations, and general monitoring needs. The basic monitoring frequency is stored in the system configuration file. A frequency adjustment factor is calculated based on the environmental risk index. The frequency adjustment factor is positively correlated with the environmental risk index and is calculated using a linear function. The function expression is:

[0076]

[0077] in: Represents the frequency adjustment factor. It is a proportionality constant greater than zero, and its value determines the strength of the influence of the environmental risk index on the adjustment factor. This represents the environmental risk index, with a value between 0 and 1. When the environmental risk index E is 0, the frequency adjustment factor... A value of 1 indicates no adjustment is needed; when the environmental risk index E is 1, the frequency adjustment factor... The maximum value is 1+k. The adjusted environmental monitoring frequency is obtained by multiplying the base monitoring frequency by the frequency adjustment factor. For example, if the base monitoring frequency is 300 seconds, the current environmental risk index is 0.6, and the proportionality constant k is set to 1, then the frequency adjustment factor... The adjusted environmental monitoring frequency is 1.6. This means the sensor data acquisition interval has been shortened to approximately 188 seconds. The system controls the sensor data acquisition interval according to the adjusted environmental monitoring frequency. Frequency control is achieved through a programmable timer, whose period is dynamically reloaded based on the calculated new frequency value, triggering a data acquisition interrupt and thus precisely controlling the time interval between sensor readings.

[0078] In some embodiments, the value of the proportionality constant k can be configured according to the greenhouse operation strategy. For example, in the refined management mode, the k value can be set to 1.5 to enhance responsiveness, while in the energy-saving priority mode, the k value can be set to 0.8 to reduce energy consumption. The calculation cycle of the frequency adjustment factor is consistent with the update cycle of the environmental risk index to ensure that the monitoring frequency can respond promptly to changes in environmental risk. The system records historical logs of monitoring frequency adjustments, including the adjustment time, the frequency before adjustment, the frequency after adjustment, and the environmental risk index value that triggered the adjustment, for subsequent analysis and auditing. To avoid system instability caused by frequent switching of monitoring frequencies, the system sets a minimum adjustment interval, for example, at least 5 minutes between two frequency adjustments, unless there is a drastic jump in the environmental risk index.

[0079] When dynamically adjusting control strategies based on the environmental risk index, the system presets two key thresholds: a low-risk threshold and a high-risk threshold. These two thresholds divide the environmental risk index range into three intervals, each corresponding to a different control strategy level. The low-risk threshold is typically set to a lower value, such as 0.3, while the high-risk threshold is set to a higher value, such as 0.7. The system maintains a control strategy lookup table, mapping environmental risk index intervals to specific control strategy instruction sets. When the environmental risk index is below the low-risk threshold, the system adopts a conservative control strategy. The conservative control strategy is characterized by a high trigger threshold for control actions, a long response delay, and mild execution. Adjustments are only made for significant deviations exceeding the tolerance range. For example, heating or cooling equipment is only activated when the temperature deviation consistently exceeds ±3°C for more than 10 minutes, and the equipment operates at lower power. The generation cycle for control instructions is also longer, for example, an assessment is conducted every 15 minutes to determine if action is necessary.

[0080] When the environmental risk index falls between the low-risk and high-risk thresholds, the system employs an active control strategy. The core of this strategy is real-time fine-tuning of environmental parameters. The system frequently checks the deviation of environmental parameters from the baseline value and uses a proportional-integral-derivative controller to calculate precise control quantities. For example, based on the current temperature deviation and its trend, it finely adjusts the opening of ventilation windows or the percentage of heater power output. The adjustment amplitude is proportional to the magnitude of the deviation, aiming to stably maintain environmental parameters near the target value. When the environmental risk index exceeds the high-risk threshold, the system adopts an aggressive control strategy. This strategy prioritizes rapid environmental stabilization, immediately activating all available backup environmental control devices in parallel. For example, it simultaneously turns on high-power fans, auxiliary humidifiers, carbon dioxide replenishment systems, and shading nets. Control commands have the highest priority, skipping complex control algorithm calculations and directly outputting the maximum or preset emergency control signal, ignoring energy consumption and equipment wear factors, until the environmental risk index falls below the high-risk threshold.

[0081] It can be understood that the switching of control strategies is managed through a finite state machine, whose states include "conservative control state," "active control state," and "aggressive control state." State transitions are triggered by a comparison between the environmental risk index and a threshold. To avoid frequent strategy switching (jitter) due to small fluctuations in the environmental risk index near the threshold, the system introduces a hysteresis mechanism. For example, switching from a conservative state to an active state requires an environmental risk index exceeding 0.3, but switching back from an active state to a conservative state requires an environmental risk index below 0.25. See Table 1, which shows the main characteristics of the control strategy:

[0082] Table 1: Comparison Table of Control Strategy Characteristics

[0083]

[0084] Optionally, under an aggressive control strategy, the system can send high-level alarm notifications to the user, prompting the need for manual attention or intervention. The control strategy module outputs arbitrated integrated control signals. These digital or analog signals are sent to specific actuators, such as frequency converters, solenoid valves, and relays, via industrial buses or I / O modules to drive physical equipment such as fans, pumps, and heaters. The system continuously monitors the environmental improvement effect after the control strategy is implemented and uses the feedback to evaluate the effectiveness of the control strategy, but this evaluation result is not directly used for the calculation of the environmental risk index. In some embodiments, different threshold pairs can be set for different environmental parameters, thereby achieving fine-grained control strategy adjustments based on parameter levels. For example, temperature control may enter the active control state earlier than humidity control.

[0085] Example 5: In specific implementation, when predicting future environmental trends based on the environmental risk index, the system employs a time series analysis-based method. The input data is a historical environmental risk index sequence. The sequence data is collected at fixed time intervals and stored in a circular buffer, for example, storing environmental risk index values ​​calculated every 15 minutes over the past 24 hours, forming a time series containing 96 data points. The prediction model uses an exponential smoothing method, and its core formula is:

[0086]

[0087] in: This represents the predicted value of the environmental risk index at time point t to the next time point t+1. This represents the environmental risk index actually calculated at time point t. This represents the predicted value at time t-1 for time t. The smoothing coefficient λ, with a value between 0 and 1, determines the weight of the latest observation in the prediction. The smoothing coefficient λ can be adaptively adjusted based on historical prediction errors, with an initial value typically set to 0.2. At the end of each calculation cycle, the system uses the latest obtained environmental risk index. Update forecast values This predicted value This is considered an estimate of environmental risk trends over a future cycle.

[0088] The generation of preventative control instructions is based on predicted values. The system performs a logical judgment process, pre-setting one or more preventative control thresholds. When the predicted value... If the value exceeds a certain threshold, a corresponding preventative control instruction is generated. For example, if the preventative control threshold is set to 0.6, and the predicted value... When the value is greater than 0.6, the system infers a risk of future environmental deterioration and generates a "prepare to activate enhanced ventilation" command. Preventative control commands include information such as command type, target equipment, recommended action intensity, and estimated execution time. These commands are placed in a lower-priority queue of preparatory commands, awaiting arbitration.

[0089] The fusion of preventative control commands and real-time control strategies is achieved through a priority arbitration module. The real-time control strategy, described in Example 4, consists of immediate control commands directly generated by the dynamic control strategy adjustment module based on the current environmental risk index, and thus has a high real-time priority. The arbitration module follows the principle that real-time control commands typically have a higher execution priority than preventative control commands. The fusion process involves checking whether preventative control commands in the pre-execution command queue conflict with currently executing or about-to-be-executed real-time control commands in terms of objectives or effects. If there is no conflict and the system control resources are redundant, the arbitration module will merge the preventative control commands and real-time control commands, outputting a comprehensive control signal. If a conflict exists, the execution of real-time control commands is prioritized, and preventative control commands will be postponed or discarded. For example, if the current real-time control strategy is executing a command to lower the temperature, while the preventative control command is preparing to lower the humidity, these two commands do not conflict and may be merged for execution. However, if the preventative command is preparing to raise the temperature, it conflicts with the real-time command and will be suppressed by the arbitration module.

[0090] The output integrated control signal converts all control commands determined after arbitration into a standard signal format recognizable by the actuators. Signal types include digital signals, analog signals, or pulse-width modulated signals. This integrated control signal is sent to the corresponding environmental control equipment driver via a specified communication protocol, thereby driving actuators such as variable frequency fans, supplementary lighting, and solenoid valves. The system records all data during the control process, including raw sensor readings, smoothed environmental data sequences, calculated environmental risk indices, and generated predicted values. This includes all generated preventative control commands and real-time control strategy commands, arbitration decision logs, and the history of the final output integrated control signals. This data, indexed by timestamps, is persistently stored in the system's non-volatile memory, forming a complete control process data chain.

[0091] In some embodiments, the recorded data is used to update plant growth models and environmental parameter benchmarks. The update process is not real-time, but rather initiated as a batch task over a longer period. This task analyzes environmental data, control commands, and concurrent plant growth status observations recorded over a period of time. Through regression analysis or machine learning algorithms, it assesses the accuracy of parameter settings in the current plant growth model and fine-tunes any unreasonable parts. For example, if data indicates that plant growth indicators remain good at a certain growth stage despite frequent temperature deviations from the benchmark, the environmental parameter benchmark range for that stage may be appropriately widened. Similarly, target values ​​in the environmental parameter benchmarks may be recalibrated based on seasonal variations in historical climate data.

[0092] It is understandable that the addition of predictive control functionality enables the system to possess feedforward control capabilities, no longer relying entirely on feedback responses to environmental deviations, thus helping to reduce system overshoot and improve environmental stability. The entire process constitutes a complete intelligent control closed loop encompassing perception, prediction, decision-making, execution, and learning. Optionally, the smoothing coefficient λ can be designed not as a fixed value, but dynamically adjusted based on the recent rate of change of the environmental risk index. When the environmental risk index changes drastically, increasing the value of λ makes the prediction model more sensitive to recent changes; when the environmental risk index is stable, decreasing the value of λ leverages the smoothing effect of historical data to make predictions more robust. In some embodiments, the generation logic of preventative control instructions can be more complex, not only based on the predicted value of the environmental risk index, but also combining independent prediction trends of specific environmental parameters for comprehensive judgment, thereby generating more targeted preparatory actions.

[0093] See Figure 5 This chart is a core data visualization result of greenhouse environmental control methods and systems used for plant cultivation, focusing on the comparative analysis of predicted and actual environmental risk indices. Based on historical environmental risk index time series, it uses an exponential smoothing method to generate predicted risk indices, and quantifies prediction accuracy using RMSE through dynamic comparison with actual risk indices. This chart directly reflects the technical link of predicting future environmental trends based on environmental risk indices and generating preventative control instructions, solving the technical pain points of traditional greenhouse environmental control that lack foresight and rely solely on real-time feedback. By intuitively presenting the deviation between predicted and actual values, it provides data support for the system to generate preventative control instructions, promoting the transformation of greenhouse environmental control from responsive to predictive, and upgrading from single feedback control to intelligent control integrating prediction and feedback. It is the core data carrier for the prediction link in realizing the entire intelligent control closed loop from data acquisition to strategy generation, helping the system to predict environmental trends in advance, generate accurate preventative control instructions, thereby improving the stability and control efficiency of the greenhouse environment and providing more forward-looking environmental protection for plant cultivation.

[0094] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0095] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A method for controlling the greenhouse environment for plant cultivation, characterized in that, Includes the following steps: The environmental parameter baseline is initialized based on a plant growth model, which is predefined according to plant type and growth cycle. Real-time acquisition of multi-source environmental sensor data inside the greenhouse, including temperature, humidity, carbon dioxide concentration, and light intensity; The multi-source environmental sensor data is subjected to time series smoothing to obtain a smoothed environmental data sequence; Calculate the deviation of the smoothed environmental data sequence from the environmental parameter benchmark, wherein the deviation is the weighted sum of the deviations of each parameter; When the deviation exceeds the adaptive threshold, a potential environmental anomaly is identified. Analyze the duration and trends of potential environmental anomalies to confirm actual environmental anomaly events; Statistically analyze the frequency and impact of real-world environmental anomalies, and calculate the environmental risk index; The frequency of environmental monitoring and control strategies are dynamically adjusted based on the environmental risk index.

2. The greenhouse environment control method for plant cultivation according to claim 1, characterized in that: The initialization of environmental parameter baselines based on plant growth models includes: Obtain plant growth stage information, which is extracted from the planting plan; By querying the standard environmental parameter database based on plant growth stage information, the target parameter values ​​for each stage can be obtained; By combining greenhouse structural parameters and historical climate data, the target parameter values ​​are corrected to generate environmental parameter benchmarks; Among them, greenhouse structural parameters include greenhouse area and height, and historical climate data include seasonal average temperature and humidity.

3. The greenhouse environment control method for plant cultivation according to claim 2, characterized in that: The time-series smoothing process for the multi-source environmental sensor data includes: The original sensor data is filtered using a sliding window algorithm. The size of the sliding window is dynamically adjusted according to the environmental risk index. The moving average of the data within the window is calculated as a smoothed environmental data sequence. When the environmental risk index increases, the sliding window size is reduced to improve response speed; when the environmental risk index decreases, the sliding window size is increased to improve stability.

4. The greenhouse environment control method for plant cultivation according to claim 3, characterized in that: The calculation of the deviation between the smoothed environmental data sequence and the environmental parameter benchmark includes: Each environmental parameter is assigned a weighting coefficient, which is determined based on the degree of influence of the parameter on plant growth. Calculate the absolute deviation between the current value of each parameter and the corresponding value in the environmental parameter baseline, multiply the absolute deviation by the weighting coefficient, and sum them to obtain the deviation degree; The adaptive threshold is dynamically calculated based on historical deviation data and plant growth stage.

5. The greenhouse environment control method for plant cultivation according to claim 4, characterized in that: The analysis of the duration and trends of potential environmental anomalies includes: Extract data points within the time period of potential environmental anomalies, calculate the duration of the anomalies, and use linear regression to fit the changing trend of the anomaly data to obtain the trend slope. When the duration of the anomaly exceeds a preset duration threshold and the absolute value of the trend slope is greater than the trend threshold, it is confirmed as a real environmental anomaly event.

6. The greenhouse environment control method for plant cultivation according to claim 5, characterized in that: When calculating the frequency and scope of impact of abnormal events in the real environment, the following are included: Record the type and occurrence time of each real-world abnormal event, calculate the number of abnormal events per unit time as the occurrence frequency, and assess the range of parameter deviations caused by the abnormal events as the impact range; The environmental risk index is obtained by normalizing the frequency and scope of occurrence and then weighting the results.

7. The greenhouse environment control method for plant cultivation according to claim 6, characterized in that: When dynamically adjusting the environmental monitoring frequency based on the environmental risk index, the following is included: Set a basic monitoring frequency, which is a fixed value; The frequency adjustment factor is calculated based on the environmental risk index. The frequency adjustment factor is positively correlated with the environmental risk index. The adjusted environmental monitoring frequency is obtained by multiplying the basic monitoring frequency by the frequency adjustment factor. The sensor data acquisition interval is controlled according to the adjusted environmental monitoring frequency.

8. The greenhouse environment control method for plant cultivation according to claim 7, characterized in that: When dynamically adjusting the control strategy based on the environmental risk index, the following are included: When the environmental risk index is below the low-risk threshold, a conservative control strategy is adopted, and adjustments are made only for major deviations. When the environmental risk index is between the low-risk threshold and the high-risk threshold, an active control strategy is adopted to fine-tune environmental parameters in real time. When the environmental risk index exceeds the high-risk threshold, an aggressive control strategy is adopted, and all backup environmental equipment is immediately activated.

9. The greenhouse environment control method for plant cultivation according to claim 8, characterized in that: It also includes the following steps: Based on the environmental risk index, future environmental trends are predicted, and preventive control instructions are generated. These preventive control instructions are then integrated with real-time control strategies to output a comprehensive control signal. All data during the control process are recorded and used to update plant growth models and environmental parameter benchmarks.

10. A greenhouse environment control system for plant cultivation, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the greenhouse environment control method for plant cultivation as described in any one of claims 1 to 9.

Images