Greenhouse environment adaptive regulation and control system based on artificial intelligence

Abstract

The invention relates to the technical field of agricultural internet of things and environment intelligent control, in particular to a greenhouse environment adaptive regulation and control system based on artificial intelligence, which comprises an environment acquisition module used for acquiring multi-dimensional environment data in real time through a distributed multi-source sensor; the central controller is used for generating an optimized regulation and control strategy; the regulation and control execution module is used for driving execution equipment to carry out regulation; the central controller comprises a multi-source data fusion unit, an AI decision-making unit and a dynamic optimization engine which are respectively responsible for data filtering and fusion, generating an initial regulation and control strategy based on a space-time joint AI model, and reconstructing and optimizing the initial regulation and control strategy through a multi-target optimization algorithm. According to the method, the response real-time performance is improved through multi-source sensing and data fusion, predictive regulation and control and multi-parameter cooperation are achieved through the AI model, balance of energy consumption, growth and carbon emission is achieved in combination with multi-target optimization, and long-term self-adaption and strategy iteration of the system are supported.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of agricultural Internet of Things and environmental intelligent control technology, and particularly relates to a greenhouse environment self-adaptive regulation and control system based on artificial intelligence. BACKGROUND

[0002] In modern facility agriculture, greenhouses create suitable microenvironments for crop growth through artificial regulation and control, which plays a key role in improving the yield and quality of agricultural products. With the wide application of sensor technology and automatic control systems, the regulation and control of greenhouse environments is gradually changing from relying on traditional experience to data-driven intelligent decision-making. However, the existing regulation and control systems still have obvious shortcomings in dynamic environment adaptation, multi-parameter collaborative optimization, and long-term stable operation, which limits the further development of modern agriculture towards high efficiency and intelligence. The existing technology mainly has the following problems: 1) Significant lag in environmental regulation: The current common system adopts a regulation and control mechanism with fixed threshold triggering, which only starts the corresponding equipment when a single parameter such as temperature or humidity exceeds the preset range. This passive control method cannot cope with dynamic environmental changes such as sudden changes in light and air disturbance, resulting in a significant lag in regulation and control response to the actual needs of crops. Especially in large greenhouses, uneven distribution of environmental parameters further leads to problems such as overcooling, overheating, or humidity imbalance in local areas, causing stress to crop growth.

[0003] 2) Lack of multi-dimensional coordination in control strategy: Most systems still use rule-based control methods, such as simply associating temperature with ventilation and humidity with irrigation. This strategy fails to fully consider the coupling relationship between environmental parameters (e.g., temperature rise causing humidity to drop, and light supplementation increasing leaf transpiration) and ignores the characteristics of crops at different growth stages. As a result, the execution equipment is frequently started and stopped, resource utilization efficiency is low, and the special environmental needs of crops at different growth stages (such as seedling stage and fruit enlargement stage) cannot be met.

[0004] 3) Imbalance between energy efficiency management and growth regulation: Existing systems often separate environmental control and energy management. In order to quickly adjust temperature and humidity, high-power equipment is often used for continuous operation, resulting in high energy consumption. While emphasizing energy saving can affect environmental stability and is not conducive to crop growth, which reflects the lack of multi-objective optimization capability of the system, making it difficult to achieve the goal of green and low-carbon production.

[0005] 4) Poor long-term adaptability: Traditional systems usually rely on the initial set control logic, which cannot be optimized autonomously according to crop growth feedback, equipment performance degradation or seasonal climate changes. When facing the introduction of new varieties or extreme weather events, manual experience is required to re-adjust parameters, which is complex and requires high professional skills. This static architecture makes the system control effect decline over time, which cannot meet the development needs of the continuous upgrading of facility agriculture.

[0006] The above reasons make it difficult for the prior art to achieve precise, efficient and sustainable control of the greenhouse environment. SUMMARY

[0007] To solve the above technical problems, the present application provides a greenhouse environment adaptive control system based on artificial intelligence.

[0008] The technical problems solved by the present application can be realized by the following technical solutions: a greenhouse environment adaptive control system based on artificial intelligence, comprising: an environment acquisition module for real-time acquisition of multi-dimensional environment data in the greenhouse by distributed deployment of multi-source sensors; a central controller connected to the environment acquisition module for receiving the multi-dimensional environment data and generating an optimized control strategy; a control execution module connected to the central controller for receiving the optimized control strategy and driving the execution equipment to adjust the environment; wherein the central controller comprises: a multi-source data fusion unit for filtering and fusion processing of the multi-dimensional environment data to obtain an environment feature matrix; an AI decision unit connected to the multi-source data fusion unit for extracting and analyzing the spatio-temporal variation characteristics of the environment feature matrix through a spatio-temporal joint AI model to generate an initial predictive control strategy; a dynamic optimization engine connected to the AI decision unit for reconstructing and optimizing the initial predictive control strategy through a multi-objective optimization algorithm to generate an optimized environment control strategy; wherein the optimization objectives of the multi-objective optimization algorithm include device energy consumption, crop growth demand satisfaction degree and carbon emission intensity.

[0009] Preferably, the multi-source data fusion unit comprises: an outlier filtering subunit for real-time detection and elimination of outliers in the multi-dimensional environment data based on a preset dynamic threshold rule; a Kalman filtering subunit connected to the outlier filtering subunit for fusing redundant data of the multi-source sensors and eliminating environmental noise using an improved Kalman filtering algorithm; a time series alignment subunit connected to the Kalman filtering subunit for synchronizing the timestamps of the multi-source sensors to the central controller clock and generating the environment feature matrix.

[0010] Preferably, the AI decision unit comprises: a spatial feature extraction subunit configured to process the environmental spatial distribution features in the environmental feature matrix through a three-dimensional convolutional neural network; a time sequence feature extraction subunit configured to process the environmental time sequence evolution rules in the environmental feature matrix through a gated recurrent unit; and a feature fusion subunit connected to the spatial feature extraction subunit and the time sequence feature extraction subunit, and configured to generate the initial predictive regulation strategy by weighting and fusing the environmental spatial distribution features and the environmental time sequence evolution rules through a multi-head attention mechanism.

[0011] Preferably, the spatio-temporal joint AI model in the AI decision unit is constructed through a model training module, and the model training module is configured to perform the following operations: constructing a cross-season training data set covering multiple complete crop growth cycles, the cross-season training data set comprising greenhouse environmental time sequence data, outdoor weather station data, crop hyperspectral images, and yield and quality record data; designing a multi-task loss function, the loss function simultaneously optimizing an environmental parameter stability index, a crop accumulated temperature satisfaction rate, and a water resource utilization efficiency; training the spatio-temporal joint AI model using a distributed training framework, and completing model convergence within a preset iteration period; and verifying the trained spatio-temporal joint AI model through a verification set.

[0012] Preferably, the dynamic optimization engine performs the following operations: establishing a multi-objective function based on a device energy consumption model, a crop growth demand model, and a carbon emission intensity factor; taking a constraint condition that a daily cumulative light amount of crops is not less than a crop light saturation point; solving the initial predictive regulation strategy using a non-dominated sorting genetic algorithm to generate a Pareto optimal solution set; and selecting an optimal solution from the Pareto optimal solution set according to a preset preference weight to generate the optimized regulation strategy.

[0013] Preferably, the central controller further comprises a model evolution unit, and the model evolution unit comprises: an incremental data set construction subunit configured to periodically collect crop physiological indexes and construct an incremental data set in combination with historical regulation strategy execution records; and a model optimization subunit connected to the incremental data set construction subunit and configured to fine-tune and optimize the spatio-temporal joint AI model based on online transfer learning technology and using the incremental data set.

[0014] Preferably, the regulation execution module comprises: an instruction compiling unit configured to compile policy parameters in the optimized environment regulation strategy into industrial Internet of Things executable code; a security coding and checking unit connected to the instruction compiling unit and configured to add a time stamp and a cyclic redundancy check code to the executable code and encapsulate the executable code into a control instruction package; an instruction synchronization issuing unit connected to the security coding and checking unit and configured to issue the control instruction package to each execution device through a time stamp synchronization mechanism; and an execution feedback and monitoring unit connected to the instruction synchronization issuing unit and configured to receive and analyze feedback signals of the execution device through a double buffering mechanism and compare the feedback signals with the control instruction package in real time.

[0015] Preferably, the system further comprises an edge intelligent gateway module connected to the environment collecting module and the regulation execution module, wherein the edge intelligent gateway module comprises: a lightweight anomaly detection unit configured to perform real-time anomaly detection on the multi-dimensional environment data based on a lightweight neural network model and generate an emergency signal when an anomaly is identified; and an emergency regulation unit connected to the lightweight anomaly detection unit and configured to start a local emergency regulation protocol to drive the execution device to intervene and upload an event diagnosis report to the central controller after receiving the emergency signal.

[0016] Preferably, the system further comprises an augmented reality interaction terminal connected to the regulation execution module, wherein the augmented reality interaction terminal comprises: a digital twin visualization unit configured to dynamically render an environment parameter cloud map and a virtual state of the execution device based on a three-dimensional model of the greenhouse; and a gesture recognition and interaction unit connected to the digital twin visualization unit and configured to capture and recognize a user's predefined gesture action, generate an artificial correction instruction for controlling the virtual execution device according to a preset mapping rule, and trigger a multi-expert decision voting mechanism and generate a strategy evaluation report when a deviation between the artificial correction instruction and the optimized regulation strategy exceeds a safety threshold.

[0017] Preferably, the system further comprises a fault diagnosis and self-recovery module connected to the environment collecting module and the regulation execution module, wherein the fault diagnosis and self-recovery module comprises: a device health monitoring unit configured to monitor working state parameters of the sensor group and the execution device; an intelligent compensation and redundancy switching unit connected to the device health monitoring unit and configured to automatically start a data compensation strategy based on multi-source information fusion or a device switching strategy based on hardware redundancy when detecting abnormal sensor data or execution device failure; and an operation and maintenance unit connected to the intelligent compensation and redundancy switching unit and configured to automatically generate a device maintenance work order according to the fault device information and push the device maintenance work order to a remote management terminal.

[0018] Beneficial effects: through real-time collection and data fusion of distributed multi-source sensors, the comprehensiveness and real-time response of environmental perception are improved; through extraction of environmental space-time change characteristics by a space-time joint AI model, predictive regulation and multi-parameter collaborative optimization are realized; through collaborative optimization of energy consumption, growth demand and carbon emission by a multi-objective optimization algorithm, the balance of energy efficiency and regulation is realized; through the combination of the space-time joint AI model and the multi-objective optimization algorithm, long-term self-adaptation and strategy iteration of the system are realized. BRIEF DESCRIPTION OF DRAWINGS

[0019] Figure 1 is a system architecture diagram of the present application; Figure 2 is a system module schematic diagram of the present application; Figure 3 is a block diagram of the central controller 200 of the present application; Figure 4 is a block diagram of the multi-source data fusion unit 210 of the present application; Figure 5 is a block diagram of the AI decision unit 220 of the present application; Figure 6 is a block diagram of the model evolution unit 240 of the present application; Figure 7 is a block diagram of the regulation execution module 300 of the present application; Figure 8 is a block diagram of the edge intelligent gateway module 500 of the present application; Figure 9 is a block diagram of the augmented reality interactive terminal 600 of the present application; Figure 10 is a block diagram of the fault diagnosis and self-recovery module 700 of the present application; Figure 11 is a system closed-loop regulation flowchart of the present application. DETAILED DESCRIPTION

[0020] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments. 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.

[0021] It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict.

[0022] The present application will be further described below with reference to the drawings and specific embodiments, but not as a limitation of the present application.

[0023] Reference Figures 1 to 3The application provides a greenhouse environment self-adaptive regulation and control system 10 based on artificial intelligence, comprising: an environment acquisition module 100, configured to acquire multi-dimensional environment data in the greenhouse in real time through distributed deployment of multi-source sensors; a central controller 200 connected to the environment acquisition module 100, configured to receive the multi-dimensional environment data and generate an optimized regulation and control strategy; and a regulation and control execution module 300 connected to the central controller 200, configured to receive the optimized regulation and control strategy and drive an execution device to perform environment adjustment; wherein the central controller 200 comprises: a multi-source data fusion unit 210, configured to filter and fuse the multi-dimensional environment data to obtain an environment feature matrix; an AI decision unit 220 connected to the multi-source data fusion unit 210, configured to extract and analyze the spatio-temporal variation characteristics of the environment feature matrix through a spatio-temporal joint AI model to generate an initial predictive regulation and control strategy; and a dynamic optimization engine 230 connected to the AI decision unit 220, configured to reconstruct and optimize the initial predictive regulation and control strategy through a multi-objective optimization algorithm to generate an optimized environment regulation and control strategy; wherein the optimization objectives of the multi-objective optimization algorithm include device energy consumption, crop growth demand satisfaction degree and carbon emission intensity.

[0024] Specifically, in the embodiment of the application, in order to effectively solve the problems of environment regulation lag, lack of multi-parameter coordination, imbalance between energy efficiency and growth, and poor long-term adaptability of the system, the AI decision unit with spatio-temporal perception ability and the dynamic multi-objective optimization engine are introduced, the dynamic changes of environment parameters, crop growth stage characteristics, device energy consumption and carbon emission intensity are included in the unified optimization framework, and the advanced prediction and collaborative control of the greenhouse environment are realized. The system can generate an optimized strategy that takes into account response speed, resource efficiency and low-carbon target based on real-time sensing data and historical operation experience, thereby avoiding the problems of response delay, strategy rigidity and high energy consumption in traditional methods, and significantly improving the precision, efficiency and sustainability of greenhouse environment regulation.

[0025] Specifically, in the above technical solution, a plurality of high-precision sensors are distributedly deployed in the greenhouse to acquire multi-dimensional environment data in real time, including but not limited to air temperature and humidity sensors, photosynthetic active radiation sensors, carbon dioxide concentration sensors, soil multi-parameter composite sensors and leaf microenvironment monitors, wherein the sampling frequency is not less than 1 time / minute.

[0026] The following is a specific embodiment: Embodiment 1: Environment data acquisition In a 400 square meter standard greenhouse, a high-density sensor network composed of 32 monitoring nodes is deployed, and the nodes are uniformly distributed to fully capture environmental variations. Each node is integrated with multiple high-precision sensors to continuously collect multi-dimensional environment data at a sampling frequency of not less than once per minute. Specifically, it includes: Air temperature and humidity monitoring: PT1000 temperature sensors and capacitive humidity sensors installed at 1.5 meters from the ground, data acquisition every 30 seconds, temperature measurement accuracy up to ±0.3 degrees Celsius, humidity range covers 0 to 100% RH.

[0027] Light monitoring: Quantum-type photosynthetically active radiation sensors suspended from the greenhouse roof, accurately capturing photosynthetically active radiation intensity in the 400 to 700 nanometer spectral range, data output in units of micromoles per square meter per second (μmol / m² / s).

[0028] Carbon dioxide concentration monitoring: monitored by a non-dispersive infrared sensor (NDIR carbon dioxide sensor), with a range of 0 to 5000 ppm.

[0029] Soil environment monitoring: sensed by FDR three-in-one probes (capacitive multi-parameter composite sensors) buried in the crop root zone, installation depth of 10 cm, can simultaneously detect soil volume moisture content (unit %), temperature (unit ℃) and conductivity (unit mS / cm) at depths of 5 to 20 cm.

[0030] Crop monitoring: microenvironment monitors clamped on tomato leaves, recording stomatal conductance and leaf condensation status every 5 minutes, data in units of millimoles per square meter per second (mmol / m² / s).

[0031] The entire sensing network integrates air, light, gas, soil, and crop physiological multi-dimensional data sources, forming a real-time, high-precision, and comprehensive greenhouse environment sensing system, providing a reliable data foundation for subsequent intelligent decision-making.

[0032] As a preferred embodiment of the present application, with reference to Figure 4 , the multi-source data fusion unit 210 includes: an outlier filtering subunit 211 for detecting and removing outliers in multi-dimensional environmental data in real time based on a pre-set dynamic threshold rule; a Kalman filtering subunit 212 connected to the outlier filtering subunit 211 for fusing redundant data of multi-source sensors and eliminating environmental noise using an improved Kalman filtering algorithm; a time alignment subunit 213 connected to the Kalman filtering subunit 212 for synchronizing the timestamps of multi-source sensors to the central controller clock and generating an environmental feature matrix.

[0033] Specifically, in the embodiments of the present application, in order to effectively improve the reliability and consistency of environmental data and provide high-quality input for subsequent AI decision-making, the multi-source data fusion unit 210 of the central controller adopts a systematic data purification and fusion process. The specific implementation steps are as follows: Firstly, the original data stream is monitored in real time based on a dynamic threshold rule, for example, if it is monitored that the temperature value of a node abnormally jumps more than ±5℃ within 10 seconds, it is automatically determined that the sensor fails or is temporarily disturbed, and the monitoring data of the spatial adjacent node is immediately used for interpolation replacement, effectively avoiding the pollution of invalid or error data to the system.

[0034] Then, an improved Kalman filtering algorithm is used to deeply fuse and eliminate noise of the cleaned multi-source sensor data with spatial redundancy; the algorithm calculates and gives different confidence weights to the data of adjacent sensors (for example, three adjacent temperature and humidity probes), and performs weighted average fusion, thereby significantly improving the estimation accuracy and anti-interference ability of key environmental parameters (such as temperature and humidity).

[0035] Finally, the timestamps of all heterogeneous sensors are uniformly synchronized to the high-precision clock of the central controller, solving the problem of asynchronous data caused by slight differences in sampling time, and finally generating a normalized environmental feature matrix with a period of 10 minutes, which completely contains the fusion information of six dimensions of temperature, humidity, light, soil moisture, electrical conductivity and stomatal conductance.

[0036] As can be seen, the multi-source data fusion unit 210 constructs a complete preprocessing chain from data cleaning, noise suppression to space-time alignment, which fundamentally guarantees the data quality of the input AI model. Not only does it enhance the fault tolerance of the system to sensor failure and transient anomaly through dynamic threshold and data interpolation mechanism, but also significantly improves the accuracy and stability of the monitoring data through the improved Kalman filtering algorithm using data redundancy, while time alignment ensures the consistency of multi-source data on the time axis, laying a solid and reliable data foundation for the subsequent spatio-temporal joint AI model for accurate prediction and decision-making, and finally improving the regulation precision and reliability of the whole system.

[0037] As a preferred embodiment of the present application, with reference to Figure 5 , the AI decision unit 220 includes: a spatial feature extraction sub-unit 221 for processing environmental spatial distribution features in the environmental feature matrix through a three-dimensional convolutional neural network; a time sequence feature extraction sub-unit 222 for processing environmental time sequence evolution rules in the environmental feature matrix through a gated recurrent unit; and a feature fusion sub-unit 223 connected with the spatial feature extraction sub-unit 221 and the time sequence feature extraction sub-unit 222, for generating an initial predictive regulation strategy by weighted fusion of environmental spatial distribution features and environmental time sequence evolution rules through a multi-head attention mechanism.

[0038] Specifically, in the embodiment of the present application, the AI decision unit 220 adopts a deep deterministic policy gradient framework as the learning basis, and the environmental feature matrix is mapped and compressed in high dimensions via a three-layer fully connected network to provide structured representation for subsequent spatio-temporal analysis. The spatio-temporal joint architecture design of this unit contains two parallel processing paths, which specifically include: the spatial feature extraction subunit 221 adopts a three-dimensional convolutional neural network to process a 10x10 spatial grid constructed by 20 monitoring points, and extract three-dimensional spatial distribution features of parameters such as temperature field and humidity field layer by layer through a 3x3x3 convolution kernel, which can effectively identify complex spatial patterns such as persistent low-temperature area in greenhouse corner and high-humidity layer near ground surface; the time series feature extraction subunit 222 relies on a gated recurrent unit network to analyze historical light intensity and CO2 concentration data for 240 consecutive hours, and uses its gating mechanism to remember long-term dependencies to accurately capture dynamic patterns such as diurnal light cycle changes and CO2 concentration daily consumption patterns caused by crop photosynthesis.

[0039] Further, the high-dimensional features extracted by the dual-channel are adaptively weighted and fused by the feature fusion subunit 223 through a multi-head attention mechanism, usually with a weight of 0.6 for spatial features and a weight of 0.4 for time series features, to highlight the dominant role of spatial heterogeneity while taking into account the evolution trend, and finally generate a fine-grained device control instruction sequence with a unit of minutes, for example: 08:30 open the east side sunshade curtain to 40%, 09:15 start 1-zone drip irrigation for 120 seconds, and the instruction time resolution reaches 15 seconds.

[0040] The following is a specific embodiment: Embodiment 2: Environmental Spatio-Temporal Feature Analysis 1) Input data preparation stage: The historical environmental data for 240 consecutive hours (i.e., 10 days) is organized into a tensor structure with a dimension of 60x32x6 according to the time sequence, which contains 60 time points, 32 monitoring nodes, and 6 environmental parameters on each node.

[0041] 2) Spatio-temporal joint model running stage: The three-dimensional convolutional network in the spatial feature extraction subunit 221 uses a 3x3x3 convolution kernel system to scan the data cube, effectively identifying the spatial correlation and abnormal areas of environmental parameters, for example, finding that there is a significant spatial correlation between the low-temperature area in the northwest corner and the high-humidity area in the southeast corner; the gating recurrent unit in the time sequence feature extraction subunit 222 analyzes the data by time step, learns and remembers the key time pattern, for example, accurately capturing the rule that the light intensity reaches the peak at 14 o'clock every day; in the feature fusion subunit 223, the system assigns a weight of 0.6 to the spatial features and a weight of 0.4 to the time features for weighted fusion, and finally outputs a vector containing four key decision values: [target temperature, target humidity, light intensity, irrigation amount] = [25.3℃, 70%RH, 180μmol / m² / s, 12L / m²], which constitutes the current period's environmental regulation target based on multi-dimensional prediction.

[0042] As can be seen, through the parallel processing and deep fusion of the spatial and time sequence dual channels, the AI decision unit 220 can not only perceive the global spatial heterogeneity of the greenhouse environment in real time, but also deeply understand the dynamic evolution law of environmental factors, thereby achieving accurate description and advanced prediction of the environmental state. The weighted fusion strategy based on the attention mechanism can dynamically adjust the focus of the decision basis according to different situations, so that the generated control strategy has spatial specificity, time foresight and multi-device collaboration, significantly improving the accuracy, response speed and resource utilization efficiency of environmental regulation, and creating a more stable and suitable growth environment for crops.

[0043] As a preferred embodiment of the present application, the spatio-temporal joint AI model in the AI decision unit 220 is constructed by the model training module 400, which is used to perform the following operations: constructing a cross-season training data set covering multiple complete crop growth periods, the cross-season training data set including greenhouse environment time series data, outdoor weather station data, crop hyperspectral images and yield quality record data; designing a multi-task loss function, the loss function simultaneously optimizing the environmental parameter stability index, the crop accumulated temperature satisfaction rate and the water resource utilization efficiency; using a distributed training framework to train the spatio-temporal joint AI model, completing model convergence within a preset iteration period; verifying the trained spatio-temporal joint AI model through a validation set.

[0044] Specifically, in the embodiment of the present application, the training process of the AI decision unit 220 is based on a cross-season multi-source data set covering five years of complete crop growth period, which deeply fuses environmental data such as temperature, humidity and wind speed provided by outdoor weather stations, crop hyperspectral images regularly collected by unmanned aerial vehicles (NDVI index and other vegetation characteristics are obtained every ten days), and key quality parameters such as fruit sugar content and single fruit weight recorded in the harvesting link.

[0045] Correspondingly, the training process innovatively defines a multi-task loss function that simultaneously optimizes three core objectives, including: an environmental stability term that evaluates the stability of regulation by calculating the root mean square error between actual temperature and humidity and the optimal interval of crops; an accumulated temperature satisfaction term that ensures the growth rhythm by evaluating the matching degree of daily effective accumulated temperature (i.e., the cumulative value of periods above 10℃) and the physiological needs of crops; and a water efficiency term that optimizes water resource utilization efficiency by counting the water consumption per unit of output.

[0046] Further, at the hardware level, a server equipped with 4 Tesla V100 GPUs is used, and a data parallel distributed training framework is set up with a batch size of 256. After sufficient training for 200 iterations, the model converges efficiently and achieves an environmental control accuracy of 94.3% on the validation set, meaning that all environmental parameters are accurately maintained within the optimal growth interval of crops for 94.3% of the time.

[0047] This training process, by integrating cross-season and multi-modal agricultural big data and designing multi-task optimization objectives that are tailored to the actual production of agriculture, enables the trained spatio-temporal AI model not only to have high environmental prediction and control accuracy, but also to deeply understand the complex coupling relationship between crop growth and development and environmental factors. Ultimately, it significantly improves the stability of greenhouse environmental regulation, the precise controllability of growth progress, and the efficiency of resource utilization, providing a core intelligent driving force for achieving the production goals of high yield, high quality, and low consumption of crops.

[0048] As a preferred embodiment of the present application, the dynamic optimization engine 230 performs the following operations: establishing a multi-objective function based on a device energy consumption model, a crop growth demand model, and a carbon emission intensity factor; setting the constraint condition that the daily cumulative light intensity of crops is not less than the light saturation point of crops; using a non-dominated sorting genetic algorithm to solve the initial predictive regulation strategy and generate a Pareto optimal solution set; and selecting the optimal solution from the Pareto optimal solution set according to the preset preference weight to generate the optimized regulation strategy.

[0049] Specifically, in the embodiments of the present application, the dynamic optimization engine 230 combines future 72-hour weather forecasts and current crop growth stage models to output high-precision environmental regulation strategies. For example, for the growth requirement of maintaining a daily temperature of 23-26℃ during the flowering period of tomatoes, the engine can generate zoned temperature control target values with a control accuracy of ±0.5℃, set the upper limit of humidity fluctuation to 85% RH, dynamically adjust the spectral formula of LED supplemental light to optimize the red-to-blue light ratio, and develop an irrigation decision table that precisely allocates water according to the depth of crop root systems.

[0050] Further specifically, the dynamic optimization engine 230 takes a multi-objective function as the core, in which the device energy consumption item is collected in real time by the smart meter, the carbon emission item is converted according to 0.86 kg CO2 per kWh, and the crop growth priority item is set differently according to the key growth period (such as the fruit setting period, with a weight of 0.7). Under the physiological constraint of ensuring that the daily cumulative photosynthetic photon flux is not less than 12 mol / m2, the NSGA-II algorithm is used to solve the Pareto optimal solution set, realizing the coordinated reduction of energy consumption and emissions.

[0051] The actual optimization effect shows that the daily average running time of the ventilation equipment can be reduced from 8 hours to 5.2 hours, with a reduction of 35%; the peak power of the irrigation system is also reduced from 8.5 kW to 6.2 kW, with a reduction of 27%. This not only greatly reduces the system operation cost and carbon emission intensity, but also fully meets the environmental needs of high-quality crop growth, reflecting the high integration of intelligent decision-making and green production.

[0052] The following is a specific embodiment: Embodiment 3: Multi-objective strategy optimization 1) Establish a target function system covering three core optimization objectives: Device energy consumption = ventilation power x time + water pump power x flow; Growth quality = (actual temperature - target temperature)² + (actual humidity - target humidity)²; Carbon emissions = total electricity consumption x 0.86 (kg CO2 / kWh).

[0053] 2) Use the non-dominated sorting genetic algorithm (NSGA-II) for multi-objective optimization solution: The algorithm first generates 100 groups of candidate control strategies with differences, and the strategy parameters include ventilation time (such as increasing by 0.5 hours in the range of 4 to 8 hours) and irrigation amount, etc. key variables; then, the system calculates the device energy consumption, crop growth quality score and carbon emission amount of each strategy; then, the algorithm strictly implements the constraint condition, automatically eliminates invalid schemes whose crop growth quality score exceeds the set threshold or device energy consumption is higher than the allowed upper limit, to ensure that all candidate strategies meet the basic needs of crop growth and system operation limitations.

[0054] 3) Multi-objective Pareto sorting analysis of candidate strategies screened by constraints: Based on the performance in the three dimensions of device energy consumption, growth quality and carbon emissions, identify those non-dominated solutions that are better in any target and not worse in other targets, forming a Pareto optimal solution set.

[0055] 4) Output optimal solution: The system selects the regulation strategy with the best overall performance from the Pareto optimal solution set according to the preset comprehensive evaluation criteria, for example: ventilation duration 5.2 hours, irrigation amount 10.5 L / m².

[0056] The optimization result shows that the strategy significantly improves the resource utilization efficiency while ensuring the environmental regulation accuracy, and realizes the multi-party balance of energy consumption, emission and crop growth demand.

[0057] As a preferred embodiment of the present application, with reference to Figure 3 , Figure 6 and Figure 11 , the central controller 200 further comprises a model evolution unit 240, which comprises: an incremental data set construction sub-unit 241 for periodically collecting crop physiological indicators and constructing an incremental data set in combination with historical regulation strategy execution records; and a model optimization sub-unit 242 connected to the incremental data set construction sub-unit 241, for fine-tuning and optimizing the spatio-temporal joint AI model based on online transfer learning technology.

[0058] Specifically, in the embodiment of the present application, the central controller 200 integrates the model evolution unit 240, which significantly improves the long-term adaptability and regulation accuracy of the system through a continuous learning mechanism. The model evolution unit 240 operates regularly, collects key physiological indicators of crops including stem flow rate and chlorophyll fluorescence index every month through high-precision sensors (such as stem flow meters with a measurement accuracy of ±0.1 ml / min and chlorophyll fluorometers that can detect photosystem II quantum efficiency), and combines these data with historical environmental regulation strategies and their execution records to construct an incremental data set for model iteration.

[0059] Subsequently, the model optimization sub-unit 242 fine-tunes and optimizes the spatio-temporal joint AI decision model based on online transfer learning technology using the incremental data. This process uses a feature decoupling transfer learning method, and the specific optimization process is as follows: the three-dimensional convolutional network weights responsible for extracting spatial features in the model are frozen to retain their existing strong feature extraction ability and prior knowledge, and only the last two layers of network parameters of the gated recurrent unit are fine-tuned. The optimization process is guided by environmental regulation errors and crop physiological index deviations, specifically by fusing 70% of the environmental errors and 30% of the physiological index deviations to construct a loss function, and using a small batch gradient descent algorithm with a learning rate of 0.001 for training, and deploying a new model when the test set accuracy breaks through 85%.

[0060] This operation brings significant benefits: it enables the system to have excellent evolutionary learning and self-adaptive ability. The system can continuously optimize its decision model using the continuously collected crop physiological response data, so that it can quickly adjust the strategy when facing the introduction of new varieties or long-term changes in the environment.

[0061] A typical case is that the system only needs to use 72 hours of continuous monitoring data (5-minute sampling interval) for incremental learning to complete the adjustment and adaptation of the newly introduced strawberry varieties, which greatly shortens the two-week adaptation period required by traditional methods to three days, and the initial control accuracy reaches 89%. This not only greatly improves the adaptability of the system to different crops and growth stages, but also realizes the deep and accurate coupling between the environmental control strategy and the internal physiological response of the crop, ensuring the forward-looking and scientific nature of the control strategy.

[0062] As a preferred embodiment of the present application, with reference to Figure 7 , the control execution module 300 comprises: an instruction compiling unit 310, configured to compile the strategy parameters in the optimized environmental control strategy into industrial Internet of Things executable code; a security coding and verification unit 320 connected to the instruction compiling unit 310, configured to add a time stamp and a cyclic redundancy check code to the executable code, and encapsulate it into a control instruction package; wherein the control instruction package contains sunshade curtain opening and closing angle control code, drip irrigation solenoid valve opening and closing time sequence code, ventilation unit speed curve code and heating sheet duty cycle parameters; an instruction synchronization issuing unit 330 connected to the security coding and verification unit 320, configured to issue the control instruction package to each execution device through a time stamp synchronization mechanism; and an execution feedback and monitoring unit 340 connected to the instruction synchronization issuing unit 330, configured to receive and analyze the feedback signals of the execution device through a double buffering mechanism, and compare the consistency of the feedback signals and the control instruction package in real time.

[0063] Specifically, in the embodiment of the present application, the control execution module 300 has the following specific working process: The instruction compiling unit 310 first converts the parameters in the optimized strategy into industrial Internet of Things executable code, for example: the target opening and closing angle of the sunshade curtain is encoded into an 8-bit binary control code, wherein 01011011 corresponds to 70% opening; at the same time, the opening and closing time sequence of the drip irrigation solenoid valve is converted into a hexadecimal instruction conforming to the RS485 communication protocol, such as 0x3A01, which represents that the control of the No. 1 valve is opened for 120 seconds.

[0064] The security coding and verification unit 320 then adds a high-precision time stamp to these instruction data packages and calculates the CRC-16 cyclic redundancy check code, and the polynomial used is 0x8005, which ensures the integrity and security of the instructions during transmission.

[0065] The instruction synchronization issuing unit 330 uses a time stamp synchronization mechanism to ensure that all control instruction packages are synchronized and issued to the execution devices distributed in each area of the greenhouse within 50 milliseconds, and the instruction content covers complex control commands such as the speed curve code of the ventilation unit and the duty cycle parameters of the heating sheet.

[0066] The execution feedback and monitoring unit 340 receives and analyzes the feedback signals of each execution device in real time through a double buffering mechanism, and continuously compares the actual feedback of the valve state, curtain position, etc. with the consistency of the control instruction package.

[0067] The following is a specific embodiment: Embodiment 4: Device instruction compilation and delivery 1) Instruction conversion stage: The control of the sunshade curtain is given in the form of opening percentage, which is linearly mapped by the system into an 8-bit binary control code, with 0% corresponding to 00000000 and 100% corresponding to 11111111. The control instruction of the drip irrigation system is calculated based on the target irrigation amount. According to the formula "opening time (seconds) = (irrigation amount × area) / single valve flow", the time that the electromagnetic valve needs to be kept open is calculated, for example, to achieve an irrigation amount of 10.5 L / m², under the condition of a total area of 400 square meters and a single valve flow of 2.5 L / s, the electromagnetic valve needs to be kept open for 1680 seconds. For the ventilation equipment, the system uses a PID control algorithm to convert the target temperature into real-time fan speed adjustment instructions, and the calculation formula is: Speed adjustment proportion = Kp × temperature difference + Ki × cumulative temperature difference + Kd × temperature difference rate, where Kp, Ki, and Kd are pre-adjusted empirical parameters with values of 0.8, 0.05, and 0.1, respectively.

[0068] 2) Instruction safety and delivery stage: The system adds a CRC-16 cyclic redundancy check code based on the 0x8005 polynomial to each instruction and encapsulates the instruction data into a specific format of data packet for broadcast through industrial Ethernet. The data packet format is as follows: [Header flag 0xA5] [Device ID] [Instruction code] [Timestamp] [CRC check] [Tail flag 0xAA]; After receiving the instruction, the execution device replies with an acknowledgment signal within 200 milliseconds. If the central controller 200 does not receive the acknowledgment within the specified time, it will automatically trigger the instruction retransmission mechanism, ensuring the reliable delivery and execution of the control instruction.

[0069] This technical solution significantly improves the reliability, synchronization, and safety of system execution through multi-level cooperation of compilation, verification, synchronization, and feedback monitoring. Its beneficial effects are as follows: on the one hand, the use of industrial-level communication protocol and CRC verification mechanism effectively prevents instruction transmission errors or interference, ensuring the accuracy of control; on the other hand, the strict 50-millisecond-level synchronization delivery mechanism combined with double buffering feedback monitoring significantly reduces the risk of time difference and state inconsistency in multi-device execution, ensuring the real-time and uniformity of greenhouse environment regulation, thereby creating a highly stable and reliable microenvironment for crop growth.

[0070] As a preferred embodiment of the present application, with reference to Figure 1 、 Figure 2 and Figure 8 , an edge intelligent gateway module 500 is further included, which is connected with the environment acquisition module 100 and the regulation and execution module 300, and includes: a lightweight anomaly detection unit 510, configured to perform real-time anomaly detection on multi-dimensional environment data based on a lightweight neural network model, and generate an emergency signal when an anomaly is identified; and an emergency regulation unit 520 connected with the lightweight anomaly detection unit 510, configured to start a local emergency regulation protocol after receiving the emergency signal, drive an execution device to intervene, and upload an event diagnosis report to the central controller 200.

[0071] Specifically, in the embodiment of the present application, the module is deployed in a greenhouse on-site control cabinet, directly connected with the environment acquisition module 100 and the regulation and execution module 300, and constitutes an independent edge intelligent closed-loop control node. The core function is to run an optimized MobileNetV2 neural network model (the model volume is only 8 MB, deployed on a Jetson Nano embedded platform) through the lightweight anomaly detection unit 510 to perform millisecond-level real-time analysis on the incoming multi-dimensional environment data, so as to realize instantaneous perception of abnormal conditions. Once an abnormal mode such as a local area temperature drop of more than 5℃ within 10 minutes (indicating that there may be cold wind penetration), or a humidity difference between adjacent monitoring points continuously exceeding 20%RH is identified, the lightweight anomaly detection unit 510 generates an emergency signal immediately.

[0072] Correspondingly, the emergency regulation unit 520 starts the preset local emergency regulation protocol immediately after receiving the signal. The unit can drive the execution mechanism to respond within 50 milliseconds, for example, quickly closing the ventilation window of the abnormal area and simultaneously starting the standby heater to the preset power (such as 50%), so as to effectively suppress the spread of environmental deterioration and realize rapid physical intervention of the scene.

[0073] At the same time, the module does not operate in isolation. It will automatically generate a structured event diagnosis report at the same time of intervention. The report not only contains key abnormal data segments, but also provides preliminary diagnosis suggestions (such as “East area temperature anomaly, code E102” or “sensor may be blocked”), and uploads the report to the central controller and the cloud platform at the same time, so as to realize full-link, second-level closed-loop response from edge perception, rapid blocking to cloud warning and tracing.

[0074] Therefore, the edge intelligent gateway module 500 greatly improves the response speed of the system to local sudden abnormalities, shortens the response of the traditional decision-making relying on the central controller 200 to seconds or even minutes to milliseconds, effectively avoids the instantaneous damage to crops caused by the spread of abnormal environment, in addition, the independent processing capability of the edge side reduces the computing load of the central controller 200, so that it can focus more on global optimization tasks, and even in the case of temporary network interruption, the local can still perform key protection actions, greatly enhancing the reliability and robustness of the entire system; in addition, the accurate event report generated by it provides clear fault location and diagnosis basis for operation and maintenance personnel, simplifies the subsequent maintenance process, realizes the unification of intelligent early warning, rapid intervention and efficient operation.

[0075] As a preferred embodiment of the present application, with reference to Figure 1 、 Figure 2 and Figure 9 , it further comprises an augmented reality interactive terminal 600 connected to the regulation and execution module 300, which comprises a digital twin visualization unit 610 for dynamically rendering environmental parameter cloud maps and virtual device states based on a greenhouse three-dimensional model; a gesture recognition and interaction unit 620 connected to the digital twin visualization unit 610 for capturing and recognizing user pre-defined gesture actions, generating artificial correction instructions for virtual execution device control according to pre-set mapping rules; wherein when the deviation of the artificial correction instruction and the optimized regulation and control strategy exceeds the safety threshold, the augmented reality interactive terminal triggers a multi-expert decision voting mechanism and generates a strategy evaluation report.

[0076] Specifically, in the embodiment of the present application, the augmented reality interactive terminal 600 fuses and renders the real-time collected environmental data in the high-precision greenhouse three-dimensional model constructed by the Unity3D engine through its digital twin visualization unit 610, generates intuitive environmental parameter cloud maps and virtual device states, and projects them in the form of holographic images into the user's field of view through Hololens2 glasses, realizing immersive monitoring of the global running state of the greenhouse.

[0077] The user can interact with the virtual environment through natural gestures by using the gesture recognition and interaction unit 620. The system predefines intuitive gesture mapping rules, for example, a horizontal sliding action can be used to adjust the opening degree of the virtual sunshade, and is set to correspond to a 5% opening degree change for every 10 centimeters of sliding, the user can confirm and finally issue the control instruction through a double-click gesture.

[0078] One of the core benefits of the terminal is its intelligent safety coordination mechanism. When the deviation between the manual correction instruction issued by the operator and the AI optimization strategy generated by the central controller exceeds the preset safety threshold (for example, the difference between the manually set temperature target and the system recommended value is greater than 3 degrees Celsius), the system will not immediately execute or simply reject the instruction, but will automatically trigger the built-in multi-expert decision voting mechanism. This mechanism will call the crop growth model recommended value, the embedded planting expert knowledge base suggestion, and the optimal regulation and control scheme in the same period in the past three years to make a comprehensive comparison and collaborative decision, and automatically generate a detailed strategy evaluation report. This report not only gives decision suggestions, but also provides specific risk warnings, such as "increasing the temperature setting will increase the probability of powdery mildew by 23%", thereby deeply integrating the operator's local experience with the system's global optimization and expert knowledge.

[0079] This design greatly improves the intelligence level and decision reliability of human-computer interaction. On the one hand, it reduces the operation threshold of complex systems through augmented reality technology, achieving intuitive and convenient visual control. On the other hand, by introducing a safety threshold and a multi-expert voting mechanism, it effectively avoids the systemic risks caused by individual experience misjudgment, combining human subjective initiative with objective rational analysis of data, while respecting the operator's intentions and ensuring the scientificity of regulation and control decisions and the safety of crop growth environment.

[0080] The following is a specific embodiment: Example 5: AR interaction operation process When the administrator views the holographic greenhouse model through Hololens, he can interact through specific gestures: pushing the virtual temperature up with the palm (every 10 cm gesture displacement corresponds to an increase of 1℃), and confirming the instruction to the execution device with a fist gesture.

[0081] When the deviation between the manually set temperature and the AI recommended value exceeds 3℃, the system automatically starts the conflict resolution mechanism: first, query the knowledge base to get the temperature upper limit of the current tomato flowering period (26℃), then retrieve the optimal temperature control scheme in the same period in the past three years (for example, 25.5℃), and finally generate a quantitative risk assessment report (such as "setting 28℃ will cause a 18% decrease in fruit setting rate"), providing data support for the administrator's decision.

[0082] As a preferred embodiment of the present application, reference is made to Figure 2 , Figure 10 and Figure 11Further comprising a fault diagnosis and self-recovery module 700 connected to the environment acquisition module 100 and the regulation and execution module 300, comprising: a device health monitoring unit 710 for monitoring the working state parameters of the sensor group and the execution device; an intelligent compensation and redundancy switching unit 720 connected to the device health monitoring unit 710, for automatically starting a data compensation strategy based on multi-source information fusion or a device switching strategy based on hardware redundancy when detecting sensor data anomalies or execution device failures; an operation and maintenance unit 730 connected to the intelligent compensation and redundancy switching unit 720, for automatically generating a device maintenance work order according to the fault device information and pushing it to a remote management terminal.

[0083] Specifically, in the embodiment of the present application, the fault diagnosis and self-recovery module 700 collects the voltage, current, response time and other state parameters of the sensors and execution devices in real time through the device health monitoring unit 710, and performs dynamic evaluation based on the pre-set health model; when the intelligent compensation and redundancy switching unit 720 identifies light sensor data anomalies or irrigation valve response timeout and other failures, it immediately starts a multi-source data fusion algorithm to calculate missing parameters or switches to redundant hardware links to ensure system control continuity; at the same time, the operation and maintenance unit 730 automatically generates a work order containing the fault location, device model and maintenance suggestions, and pushes it to the management personnel's mobile terminal in real time, thereby realizing the full-process automatic closed-loop management from fault perception, intelligent fault tolerance to maintenance response, and significantly improving the reliability and operation efficiency of the system.

[0084] The following is a specific embodiment: Embodiment 6: Fault diagnosis and recovery 1) When the light sensor fails, automatically start the data compensation process: the system automatically calls the fisheye camera to shoot the sky image, uses image segmentation technology to accurately quantify the cloud coverage, and converts it into a quantitative index of 0 to 100%; combined with historical light data, according to the established "light intensity = sunny baseline value × (1- cloud coverage × 0.8)" model, dynamically estimate the current photosynthetically active radiation value, realize continuous and reliable perception of light parameters.

[0085] 2) If the irrigation valve is found to be stuck, and the water flow sensor response delay is more than 5 seconds (normal threshold < 2 seconds), a quick switching mechanism based on hardware redundancy is immediately triggered: the control relay switches the waterway to the standby pipeline within 100 milliseconds, ensuring uninterrupted irrigation operation; at the same time, the operation and maintenance unit 730 automatically records the fault device ID and detailed information, generates a detailed maintenance work order containing the specific model of the replacement spare parts, and pushes an alarm SMS to the management personnel's mobile APP terminal in real time, such as "B area 3 valve fault, standby line enabled", thereby realizing the full-process intelligent closed-loop processing from fault detection, automatic switching to operation and maintenance notification.

[0086] In addition, the system also has perfect intelligent diagnosis and self-recovery mechanism for other types of equipment failure. For example, when the system detects that the indoor carbon dioxide sensor has permanent drift or abnormal reading, the intelligent compensation and redundancy switching unit 720 will immediately start the soft compensation strategy based on multi-source data fusion. This strategy dynamically calculates a more reliable indoor carbon dioxide concentration reference value by analyzing the current ventilation rate, crop photosynthesis intensity (which can be estimated according to light intensity and growth stage) and outdoor carbon dioxide concentration in real time, to maintain the continuous and stable operation of the gas fertilizer regulation function.

[0087] If the key execution equipment such as the circulating fan fails to start or is overloaded, the intelligent compensation and redundancy switching unit 720 will complete the diagnosis and automatically enable the standby fan within seconds, while marking the original fan as a fault state. At the same time, the operation and maintenance unit 730 will generate a maintenance work order simultaneously, which not only contains the equipment number and fault type, but also intelligently recommends possible spare parts (such as bearings or capacitors) according to historical maintenance records, and automatically pushes the information to the operation and maintenance personnel's handheld terminal, significantly shortening the troubleshooting and repair time, and improving the availability and maintenance efficiency of the system.

[0088] As can be seen, this technical solution greatly improves the availability and robustness of the system through real-time health monitoring, intelligent fault compensation and redundancy switching closed-loop management, effectively avoiding the overall environmental imbalance or production interruption caused by local equipment failure; at the same time, the automated operation and maintenance process greatly reduces the dependence on manual inspection, improves the maintenance efficiency, and realizes the intelligentization and precision of fault perception to repair response, providing a solid guarantee for the long-term stable and unmanned operation of the greenhouse.

[0089] As a preferred embodiment of the present application, reference is made to Figure 1 and Figure 11The system adopts a three-layer architecture, including a perception layer (an environment acquisition module 100), a decision layer (a central controller 200) and an execution layer (a regulation and execution module 300), forming a full-closed-loop regulation and control system of "perception-decision-execution-evolution", and realizing a technical breakthrough of greenhouse environment adaptive management. Specifically, in the perception layer, a distributed multi-source sensor network fuses air, soil and crop physiological parameters, and combines Kalman filtering to dynamically eliminate environmental noise, providing a high-reliability data foundation for decision-making; in the decision layer, a spatio-temporal joint AI model uses a three-dimensional convolution network to analyze the spatial distribution characteristics of the greenhouse, couples a gate recurrent unit to capture the temporal evolution law of the environment, and generates a predictive regulation and control strategy through an attention mechanism, fundamentally overcoming the response lag defect of traditional threshold triggering; at the same time, through a multi-objective Pareto optimization engine, the device energy consumption, crop demand and carbon emission factor are coordinated and weighed, and the initial strategy is dynamically reconstructed to achieve optimal allocation of resources; in the execution layer, an industrial Internet of Things instruction compiling unit converts the strategy parameters into device executable code, and combines an edge computing node to realize millisecond-level emergency response, ensuring precise synchronization of regulation and control actions; in the evolution layer, an online transfer learning mechanism based on incremental data continuously absorbs crop physiological feedback and climate characteristics, enabling the system to have cross-species and cross-season adaptive capability; supplemented by an augmented reality human-computer interaction and multi-expert decision voting mechanism, a visual operation channel and risk warning support are provided for manual intervention, ultimately forming a smart greenhouse management and control paradigm of precise and stable environment control, efficient and intensive resource utilization, and long-term autonomous evolution.

[0090] The above merely describes preferred embodiments of the present application and is not intended to limit the embodiments and protection scope of the present application. Those skilled in the art should realize that equivalent replacements and obvious changes made according to the content of the present application description and drawings should be included in the protection scope of the present application.

Claims

1. An artificial intelligence-based greenhouse environment adaptive control system, characterized in that: include: The environmental acquisition module is used to obtain multi-dimensional environmental data in the greenhouse in real time through distributed multi-source sensors; A central controller, connected to the environment acquisition module, configured to receive the multi-dimensional environment data and generate an optimization control strategy; A control execution module, connected to the central controller, is used to receive the optimized control strategy and drive the execution equipment to perform environmental adjustment; wherein, the central controller includes: a multi-source data fusion unit, which is used to filter and fuse the multi-dimensional environmental data to obtain an environmental feature matrix; an AI decision unit, connected to the multi-source data fusion unit, which is used to extract and analyze the spatiotemporal change characteristics of the environmental feature matrix through a spatiotemporal joint AI model to generate an initial predictive control strategy; a dynamic optimization engine, connected to the AI ​​decision unit, which is used to reconstruct and optimize the initial predictive control strategy through a multi-objective optimization algorithm to generate an optimized environmental control strategy; wherein, the optimization objectives of the multi-objective optimization algorithm include equipment energy consumption, crop growth demand satisfaction, and carbon emission intensity.

2. The artificial intelligence-based greenhouse environment adaptive control system according to claim 1, characterized in that: The multi-source data fusion unit includes: an outlier filtering subunit, which is used to detect and eliminate outliers in the multi-dimensional environmental data in real time based on a preset dynamic threshold rule; a Kalman filtering subunit, which is connected to the outlier filtering subunit and is used to use an improved Kalman filtering algorithm to fuse the redundant data of the multi-source sensors and eliminate environmental noise; a timing alignment subunit, which is connected to the Kalman filtering subunit and is used to synchronize the timestamps of the multi-source sensors to the central controller clock and generate the environmental feature matrix.

3. The greenhouse environment adaptive control system based on artificial intelligence according to claim 1 is characterized in that: The AI ​​decision-making unit includes: a spatial feature extraction subunit, which is used to process the environmental spatial distribution characteristics in the environmental feature matrix through a three-dimensional convolutional neural network; a temporal feature extraction subunit, which is used to process the environmental temporal evolution law in the environmental feature matrix through a gated recurrent unit; a feature fusion subunit, which connects the spatial feature extraction subunit and the temporal feature extraction subunit, and is used to weightedly fuse the environmental spatial distribution characteristics and the environmental temporal evolution law through a multi-head attention mechanism to generate the initial predictive control strategy.

4. The artificial intelligence-based greenhouse environment adaptive control system according to claim 3 is characterized in that: The spatiotemporal joint AI model in the AI ​​decision-making unit is constructed through a model training module, which is used to perform the following operations: construct a cross-season training dataset covering multiple complete crop growth cycles, and the cross-season training dataset includes greenhouse environment time series data, outdoor weather station data, crop hyperspectral images, and yield quality record data; design a multi-task loss function, which simultaneously optimizes the environmental parameter stability index, crop accumulated temperature satisfaction rate, and water resource utilization efficiency; use a distributed training framework to train the spatiotemporal joint AI model and complete model convergence within a preset iteration cycle; and verify the trained spatiotemporal joint AI model through a validation set.

5. The greenhouse environment adaptive control system based on artificial intelligence according to claim 3 is characterized in that: The dynamic optimization engine performs the following operations: establishing a multi-objective function based on an equipment energy consumption model, a crop growth demand model, and a carbon emission intensity factor; taking the daily cumulative sunlight amount of the crop as not less than the light saturation point of the crop as a constraint condition; using a non-dominated sorting genetic algorithm to solve the initial predictive control strategy to generate a Pareto optimal solution set; and selecting the optimal solution from the Pareto optimal solution set based on preset preference weights to generate the optimized control strategy.

6. The greenhouse environment adaptive control system based on artificial intelligence according to claim 1 is characterized in that: The central controller also includes a model evolution unit, which includes: an incremental data set construction subunit, which is used to regularly collect crop physiological indicators and construct an incremental data set in combination with historical control strategy execution records; a model optimization subunit, which is connected to the incremental data set construction subunit and is used to fine-tune and optimize the spatiotemporal joint AI model based on online transfer learning technology using the incremental data set.

7. The greenhouse environment adaptive control system based on artificial intelligence according to claim 1 is characterized in that: The control execution module includes: an instruction compilation unit, which is used to compile the policy parameters in the optimization environment control strategy into an industrial Internet of Things executable code; a security coding and verification unit, which is connected to the instruction compilation unit, and is used to add a timestamp and a cyclic redundancy check code to the executable code, and encapsulate it into a control instruction package; an instruction synchronization and issuance unit, which is connected to the security coding and verification unit, and is used to issue the control instruction package to each execution device through a timestamp synchronization mechanism; an execution feedback and monitoring unit, which is connected to the instruction synchronization and issuance unit, and is used to receive and parse the feedback signal of the execution device through a double buffering mechanism, and compare the consistency of the feedback signal with the control instruction package in real time.

8. The greenhouse environment adaptive control system based on artificial intelligence according to claim 1 is characterized in that: It also includes an edge intelligent gateway module, which is connected to the environment acquisition module and the control execution module, and includes: a lightweight anomaly detection unit, which is used to perform real-time anomaly detection on the multi-dimensional environmental data based on a lightweight neural network model, and generate an emergency signal when an anomaly is identified; an emergency control unit, which is connected to the lightweight anomaly detection unit, and is used to start the local emergency control protocol after receiving the emergency signal, drive the execution device to intervene, and upload an event diagnosis report to the central controller.

9. The greenhouse environment adaptive control system based on artificial intelligence according to claim 1 is characterized in that: It also includes an augmented reality interaction terminal, which is connected to the control execution module and includes: a digital twin visualization unit, which is used to dynamically render an environmental parameter cloud map and a virtual state of the equipment based on the greenhouse three-dimensional model; a gesture recognition and interaction unit, which is connected to the digital twin visualization unit and is used to capture and recognize user predefined gestures, and generate manual correction instructions for the control of the virtual execution equipment according to preset mapping rules; wherein, when the deviation between the manual correction instructions and the optimized control strategy exceeds a safety threshold, the augmented reality interaction terminal triggers a multi-expert decision voting mechanism and generates a strategy evaluation report.

10. The artificial intelligence-based greenhouse environment adaptive control system according to claim 1, characterized in that: It also includes a fault diagnosis and self-recovery module, which is connected to the environment acquisition module and the control execution module, and includes: an equipment health monitoring unit, which is used to monitor the working status parameters of the sensor group and the execution equipment; an intelligent compensation and redundancy switching unit, which is connected to the equipment health monitoring unit, and is used to automatically start a data compensation strategy based on multi-source information fusion or an equipment switching strategy based on hardware redundancy when sensor data abnormalities or execution equipment failures are detected; an operation and maintenance management unit, which is connected to the intelligent compensation and redundancy switching unit, and is used to automatically generate an equipment maintenance work order based on the faulty equipment information and push it to the remote management terminal.

Images