Greenhouse environment accurate regulation and control system based on artificial intelligence

Abstract

The invention discloses a greenhouse environment precise regulation and control system based on artificial intelligence, and the system is characterized in that the system comprises a data collection module, a local controller, a control center, and an environment adjustment module. According to the greenhouse environment precise regulation and control system based on artificial intelligence, environmental data are monitored in real time by deploying temperature and humidity sensors, illumination sensors and the like, crop requirements and external conditions (such as weather prediction) are analyzed in combination with an AI algorithm, ventilation equipment, sunshade equipment, irrigation equipment and the like are automatically adjusted, the temperature and humidity fluctuation is smaller than or equal to + / -1 DEG C, and the water and fertilizer utilization rate is increased by 30%. Meanwhile, the image recognition technology is used for early warning diseases and insect pests, energy consumption is dynamically optimized, finally the crop yield is increased by 20% or above, and manual intervention and resource waste are reduced.

Description

Technical Field

[0001] This invention relates to a system that combines artificial intelligence with a greenhouse environment control system. Background Technology

[0002] Traditional greenhouse environment control has long relied on manual experience and fixed threshold control, which has three major bottlenecks:

[0003] First, the monitoring accuracy of environmental parameters (temperature, humidity, CO2 concentration) is low (the error often exceeds ±2℃), and the equipment linkage is lagging, resulting in large fluctuations in day and night temperature and uneven crop growth.

[0004] Second, water and fertilizer management is extensive, and irrigation relies on a timed and quantitative model, resulting in a resource waste rate of over 40%.

[0005] Third, the delayed identification of pests and diseases, and reliance on manual inspections, can easily lead to missed detections and the loss of the best window for prevention and control.

[0006] Furthermore, traditional systems struggle to dynamically respond to extreme weather and changes in crop growth stages, hindering yield and quality improvement. There is an urgent need for intelligent technologies to achieve data-driven precision control. Summary of the Invention

[0007] The technical problem this invention aims to solve is that traditional greenhouse environment control has long relied on human experience and fixed threshold control.

[0008] To address the aforementioned technical problems, the present invention discloses a precise greenhouse environment control system based on artificial intelligence, characterized by comprising:

[0009] The data acquisition module is used for environmental monitoring and is part of a multimodal Internet of Things (IoT) sensor network composed of various sensors.

[0010] The local controller, as an edge computing node, has data preprocessing, local storage, and command forwarding functions, and corresponds one-to-one with each data acquisition module / environmental control module. On the one hand, the local controller uploads the data collected by the data acquisition module to the control center in real time through the transport layer; on the other hand, the local controller forwards the commands generated by the control center to the environmental control module in real time through the transport layer.

[0011] The control center integrates a human-machine interface, data visualization, parameter setting, fuzzy control algorithm, and communication module. It supports parameter preset and strategy optimization for crop growth stages and has remote diagnostic and strategy update functions. The control center uses a fuzzy control algorithm to generate instructions for controlling the environmental adjustment module in real time based on the data collected by the data acquisition module uploaded by the local controller. The instructions are then fed back to the local controller, which controls the environmental adjustment module according to the instructions.

[0012] The environmental regulation module is a multi-equipment linkage subsystem for "wind-cotton-water-fertilizer-pesticide". For example, the fan, wet curtain and shade net can be started and stopped synchronously. Based on the soil EC value and crop water requirement, the water and fertilizer ratio error can be ≤5% through drip irrigation / sprinkler irrigation system, and the water and fertilizer saving rate can exceed 30%. It can link the fan, wet curtain and supplemental lighting. For example, when the temperature is high, the shade net and side ventilation can be turned on at the same time, and the temperature can be reduced by 3-5℃ within 5 minutes, realizing the synergy of fan / wet curtain / drip irrigation / shade net.

[0013] Preferably, the sensors used in the data acquisition module include a DHT11 digital temperature and humidity sensor, a DS18B20+HS1101 combined sensor, a TSL235 light sensor, and a CO2 sensor using NDIR technology.

[0014] Preferably, the data acquisition module also uses 360° camera visual recognition, drone aerial photography and weather station data to identify pests and diseases, and simultaneously acquire crop growth status and changes in the external environment.

[0015] Preferably, the transmission layer adopts the 5G / WiFi / NB-IoT protocol.

[0016] Preferably, the control center uses machine learning to analyze the correlation between historical environmental data and crop growth, constructs a dynamic regulation model, predicts the optimal temperature and humidity thresholds, and generates dynamic regulation strategies. At the same time, the control center uses fuzzy PID control technology to adjust the output power of ventilation, shading, and irrigation equipment based on real-time feedback.

[0017] Preferably, the fuzzy PID control technology employs a hierarchical-linkage control mechanism, humidity hierarchical control, and dynamic adjustment rules, wherein:

[0018] Humidity grading control is shown in the table below:

[0019] Humidity level Temperature control strategy Executive agency combination high Prioritize cooling Skylight + evaporative cooling pad + fan middle dynamic equilibrium Circulating fan + air conditioner Low Mainly for heat preservation Internal insulation + supplemental lighting

[0020] The dynamic adjustment rule is as follows:

[0021] When environmental parameter deviation > threshold:

[0022] If the detected value is less than the set value, the control quantity is increased linearly.

[0023] If the detected value is greater than the set value, then the exponential decay adjustment will be applied.

[0024] When the environmental parameter deviation is less than or equal to the threshold:

[0025] The PID fuzzy algorithm is used to generate the control quantity by combining the deviation and the rate of change.

[0026] Preferably, the control center uses a convolutional neural network to analyze leaf images and automatically generates instructions to trigger biological control or targeted pesticide application.

[0027] Preferably, the control center generates relevant start-stop commands through reinforcement learning to optimize the equipment start-stop timing. At the same time, it establishes a water and fertilizer demand model matching the growth stage based on the data collected by the data acquisition module, and generates water and fertilizer release commands according to the current growth stage.

[0028] Preferably, the control center can also automatically generate data reports based on historical trend analysis. Users can obtain the data reports through the corresponding user terminal based on the feedback interface. At the same time, it can perform intelligent alarms and remote control, and generate multi-level early warnings.

[0029] Preferably, the environmental control module employs intelligent valves and a photovoltaic-energy storage synergistic energy management module, further including a ventilation subsystem, a shading subsystem, a temperature control subsystem, a supplemental lighting subsystem, and a CO2 control subsystem, all uniformly controlled by a controlled switch group, wherein:

[0030] The ventilation subsystem includes a roof window / evaporative cooling curtain outward-opening window / fan unit; the shading subsystem includes a double-layer structure of external shading + internal shading; the temperature control subsystem includes air conditioning / internal insulation / circulating fan; the supplementary lighting subsystem includes dimmable LED supplementary lighting; and the CO2 control subsystem includes a generator linked with ventilation.

[0031] The artificial intelligence-based greenhouse environment precision control system disclosed in this invention monitors environmental data in real time by deploying sensors for temperature, humidity, and light intensity. Combined with AI algorithms, it analyzes crop needs and external conditions (such as weather forecasts) and automatically adjusts ventilation, shading, and irrigation equipment to achieve temperature and humidity fluctuations ≤ ±1℃ and improve water and fertilizer utilization by 30%. Simultaneously, this invention utilizes image recognition technology to provide early warnings of pests and diseases, dynamically optimizes energy consumption, and ultimately increases crop yield by more than 20% while reducing human intervention and resource waste. Attached Figure Description

[0032] Figure 1 This illustrates the control architecture used in this invention. Detailed Implementation

[0033] Various aspects and features of the present invention are described herein with reference to the accompanying drawings.

[0034] It should be understood that various modifications can be made to the embodiments described herein. Therefore, the above description should not be considered as limiting, but merely as an example of embodiments. Other modifications within the scope and spirit of this disclosure will be apparent to those skilled in the art.

[0035] The accompanying drawings, which are included in and form part of this specification, illustrate embodiments of the invention and, together with the general description of the invention given above and the detailed description of the embodiments given below, serve to explain the principles of the invention.

[0036] These and other features of the invention will become apparent from the following description of preferred forms of embodiments given as non-limiting examples, with reference to the accompanying drawings.

[0037] It should also be understood that although the invention has been described with reference to some specific examples, those skilled in the art can certainly implement many other equivalent forms of the invention, which have the features described in the claims and are therefore all within the scope of protection defined herein.

[0038] The above and other aspects, features and advantages of the invention will become more apparent when taken in conjunction with the accompanying drawings and in view of the following detailed description.

[0039] Specific embodiments of the invention are described below with reference to the accompanying drawings; however, it should be understood that the claimed embodiments are merely examples of the invention, which may be implemented in various ways. Well-known and / or repeated functions and structures are not described in detail to avoid unnecessary or redundant details that would obscure this disclosure. Therefore, the specific structural and functional details claimed in this invention are not intended to be limiting, but are merely intended as the basis and representative basis for the claims to teach those skilled in the art to use this disclosure in a variety of substantially any suitable detailed structures.

[0040] This specification may use the phrases “in one embodiment,” “in another embodiment,” “in yet another embodiment,” or “in still another embodiment,” all of which may refer to one or more of the same or different embodiments according to this disclosure.

[0041] like Figure 1 As shown, the artificial intelligence-based greenhouse environment precision control system disclosed in this embodiment of the invention adopts a distributed control architecture, including:

[0042] The data acquisition module is used for environmental monitoring. It is a multimodal IoT sensor network composed of various sensors. By deploying sensors for temperature, humidity, light intensity, CO2 concentration, and soil moisture, it reduces temperature monitoring accuracy from ±2℃ to ±0.5℃, light intensity to Lux level, humidity error to ≤3% RH, CO2 to ±50ppm, and soil moisture error to 0.1%, achieving second-level acquisition of environmental parameters and reducing data acquisition error by 50%.

[0043] In a preferred embodiment of the present invention, the data acquisition module uses sensors including a DHT11 digital temperature and humidity sensor (for measuring air parameters), a DS18B20+HS1101 combined sensor (for measuring soil parameters), a TSL235 light sensor, and a CO2 sensor using NDIR technology (S-100 module).

[0044] Furthermore, in another preferred embodiment of the present invention, the data acquisition module also uses 360° camera visual recognition, drone aerial photography and weather station data to identify pests and diseases, and simultaneously acquire crop growth status and changes in the external environment.

[0045] The local controller, as an edge computing node, has the functions of data preprocessing, local storage and command forwarding, and corresponds one-to-one with each data acquisition module / environment adjustment module.

[0046] The local controller uploads data collected by the data acquisition module to the control center in real time via the transport layer. Simultaneously, it forwards commands generated by the control center to the environmental control module in real time via the same transport layer. The local controller supports RS-232 / RS-485 and Ethernet communication, and has a reserved Modbus / TCP protocol interface for device expansion.

[0047] In one preferred embodiment of the present invention, the transmission layer adopts the 5G / WiFi / NB-IoT protocol, with a latency of <100ms and a data transmission efficiency improvement of 60%.

[0048] The control center integrates a human-machine interface, data visualization, parameter setting, fuzzy control algorithm, and communication module. It supports parameter preset and strategy optimization for crop growth stages and has remote diagnostic and strategy update functions.

[0049] The control center uses a fuzzy control algorithm to generate commands for controlling the environmental regulation module in real time based on the data collected by the data acquisition module uploaded by the local controller. The commands are then fed back to the local controller, which controls the environmental regulation module according to the commands.

[0050] In one preferred embodiment of the invention, the control center uses machine learning to analyze the correlation between historical environmental data and crop growth, constructs a dynamic regulation model, predicts optimal temperature and humidity thresholds, and generates dynamic regulation strategies, such as activating cooling equipment two hours in advance to cope with high temperature peaks. Simultaneously, the control center employs fuzzy PID control technology to adjust the output power of ventilation, shading, and irrigation equipment based on real-time feedback, improving fluctuation control accuracy by 40%.

[0051] Furthermore, in another preferred embodiment of the present invention, the fuzzy PID control technology employs a hierarchical-linkage control mechanism, humidity hierarchical control, and dynamic adjustment rules.

[0052] The humidity gradation control employed by fuzzy PID control technology is shown in the table below:

[0053] Humidity level Temperature control strategy Executive agency combination high Prioritize cooling Skylight + evaporative cooling pad + fan middle dynamic equilibrium Circulating fan + air conditioner Low Mainly for heat preservation Internal insulation + supplemental lighting

[0054] The dynamic adjustment rule used in fuzzy PID control technology is as follows:

[0055] When environmental parameter deviation > threshold:

[0056] If the detected value is less than the set value, the control quantity is increased linearly.

[0057] If the detected value is greater than the set value, then the exponential decay adjustment will be applied.

[0058] When the environmental parameter deviation is less than or equal to the threshold:

[0059] The PID fuzzy algorithm is used to generate the control quantity by combining the deviation (E) and the rate of change (Ec).

[0060] In another preferred embodiment of the present invention, the control center uses a convolutional neural network (CNN) to analyze leaf images, achieving a pest and disease identification accuracy of 92%, and automatically generates instructions to trigger biological control or targeted pesticide application.

[0061] In another preferred embodiment of the present invention, the control center generates relevant start-stop commands through reinforcement learning, optimizes the start-stop timing of equipment, reduces the overall energy consumption of the system by 15%-20%, and extends the service life of key components.

[0062] In another preferred embodiment of the present invention, the control center establishes a water and fertilizer demand model matching the growth stage based on the data collected by the data acquisition module, and generates water and fertilizer release instructions according to the current growth stage, thereby reducing the corresponding resource waste by 40%.

[0063] In another preferred embodiment of the present invention, the control center can also automatically generate data reports based on historical trend analysis. Users can obtain the data reports through the corresponding user terminal (such as mobile phone, computer, etc.) based on the feedback interface, thereby improving management efficiency by 40%.

[0064] In another preferred embodiment of the present invention, the control center can also perform intelligent alarms and remote control, generate multi-level warnings, and push them to users in the form of sound and light / SMS / APP.

[0065] In the aforementioned technical solution, the control center integrates weather station forecasts, drone aerial photography, and 360° visual recognition data to enhance the foresight of environmental regulation. Through a closed-loop "perception-decision-execution" process, it reduces the fluctuation range of greenhouse environmental parameters by 60% and increases crop yield by an average of 25%. This technical system breaks through the static control model of traditional agriculture, constructing a data-driven closed-loop control framework that increases greenhouse yield by 20%-25% and resource utilization by over 30%. Simultaneously, the control center and local controllers achieve edge-cloud collaboration, realizing edge computing (real-time response) + cloud deep learning (model optimization), thereby improving computing resource utilization by 35% and balancing efficiency and computing power requirements.

[0066] The environmental control module is a multi-equipment linkage subsystem for "wind-cotton-water-fertilizer-pesticide". For example, the simultaneous start and stop of fans, wet curtains and shade nets, based on soil EC value and crop water requirement patterns, achieves water and fertilizer ratio error ≤5% through drip irrigation / sprinkler irrigation system, and saves water and fertilizer rate of over 30%. It links fans, wet curtains, supplemental lighting and other equipment. For example, when the temperature is high, the shade net and side ventilation are turned on simultaneously, and the temperature drops by 3-5℃ within 5 minutes, realizing the coordination of fans / wet curtains / drip irrigation / shade nets (5-minute response).

[0067] In a preferred embodiment of the present invention, the environmental regulation module employs a smart valve with an accuracy of 0.1 L / s and an energy management module that integrates photovoltaic and energy storage (solar power priority), thereby improving environmental regulation efficiency by 50% and reducing grid dependence by 30%. The module further includes a ventilation subsystem, a shading subsystem, a temperature control subsystem, a supplementary lighting subsystem, and a CO2 regulation subsystem, all uniformly controlled by a controlled switch group.

[0068] The ventilation subsystem includes a roof window / evaporative cooling curtain outward-opening window / fan unit; the shading subsystem includes a double-layer structure of external shading + internal shading; the temperature control subsystem includes air conditioning / internal insulation / circulating fan; the supplementary lighting subsystem includes dimmable LED supplementary lighting; and the CO2 control subsystem includes a generator linked with ventilation.

[0069] When the aforementioned greenhouse environment precision control system is applied, it collects environmental data such as water level and moisture content, temperature, and plant leaf color through a multimodal Internet of Things sensor network (sensors include probe-type, infrared, and camera-type sensors). This data is then transmitted to the transmission layer for real-time synchronization, juxtaposing data from the same time point. While some data may have different collection frequencies due to their specific characteristics, all collected data is started at a unified time, i.e., midnight, and recorded synchronously and juxtaposed at each precise hour.

[0070] All data can be extracted and used individually for analysis, or selected data can be compared and analyzed. Simultaneous data from other points serve as the primary basis, supplementing other data on periodic fluctuations to determine trends, and alerts are issued for special cases, such as exceeding specified values ​​for high temperature and humidity, or high temperature and low humidity.

[0071] The control center analyzes the data, using algorithms based on past experience and fluctuation data to make operational decisions for the equipment system. It proposes strategies such as adding liquid or cooling (activating the evaporative cooling pad). Data is monitored and collected after these operations are performed. The entire operation process is communicated with management personnel through data and control panels to ensure timely feedback and adjustments.

[0072] In the above process, various types of sensors are set up for each key indicator, and the sensor value ranges are configured. When the values ​​exceed or fall below the corresponding ranges, appropriate actions are taken. Simultaneously, the key indicators are compared uniformly. While the collection frequency for some indicators varies, data is collected uniformly at the top of the hour and half-hour intervals to align the data. Furthermore, the changes in data within a time period are analyzed, and trends are used to predict future data fluctuations.

[0073] For temperature control: using temperature and humidity sensors + PLC controller, the fan / evaporative cooling pad / heater is automatically started and stopped, and the temperature is precisely controlled within ±0.5℃.

[0074] For humidity control: humidity sensor + solenoid valve, intelligent spray / dehumidifier linkage, humidity control accuracy of ±3%RH.

[0075] For lighting control: Based on the data monitored by the photosensitive sensor and the illuminance sensor, the automatic roller blind, supplementary light, LED growth light, etc. are dimmed, with stepless adjustment from 0-100%.

[0076] For CO2 concentration control: Based on CO2 sensor monitoring data, the system can intelligently control ventilation or CO2 generator, with a range of 800-1200ppm.

[0077] The performance indicators of the system disclosed in the embodiments of the present invention are shown in the table below.

[0078]

[0079]

[0080] The above description is merely a preferred embodiment of the present invention and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of disclosure in this invention is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this invention.

Claims

1. A precise greenhouse environment control system based on artificial intelligence, characterized in that, include: The data acquisition module is used for environmental monitoring and is part of a multimodal Internet of Things (IoT) sensor network composed of various sensors. The local controller, as an edge computing node, has data preprocessing, local storage, and command forwarding functions, and corresponds one-to-one with each data acquisition module / environmental control module. On the one hand, the local controller uploads the data collected by the data acquisition module to the control center in real time through the transport layer; on the other hand, the local controller forwards the commands generated by the control center to the environmental control module in real time through the transport layer. The control center integrates a human-machine interface, data visualization, parameter setting, fuzzy control algorithm, and communication module. It supports parameter preset and strategy optimization for crop growth stages and has remote diagnostic and strategy update functions. The control center uses a fuzzy control algorithm to generate instructions for controlling the environmental adjustment module in real time based on the data collected by the data acquisition module uploaded by the local controller. The instructions are then fed back to the local controller, which controls the environmental adjustment module according to the instructions. The environmental regulation module is a multi-equipment linkage subsystem for "wind-cotton-water-fertilizer-pesticide". For example, the simultaneous start and stop of the fan, wet curtain and shade net. Based on the soil EC value and crop water requirement, the water and fertilizer ratio error is ≤5% through the drip irrigation / sprinkler irrigation system, and the water and fertilizer saving rate exceeds 30%. It links the fan, wet curtain and supplemental lighting. For example, when the temperature is high, the shade net and side ventilation are turned on at the same time, and the temperature drops by 3-5℃ within 5 minutes, realizing the synergy of fan / wet curtain / drip irrigation / shade net.

2. The artificial intelligence-based greenhouse environment precision control system as described in claim 1, characterized in that, The sensors used in the data acquisition module include a DHT11 digital temperature and humidity sensor, a DS18B20+HS1101 combined sensor, a TSL235 light sensor, and a CO2 sensor using NDIR technology.

3. The artificial intelligence-based greenhouse environment precision control system as described in claim 1, characterized in that, The data acquisition module also uses 360° camera visual recognition, drone aerial photography and weather station data to identify pests and diseases, and simultaneously acquire crop growth status and changes in the external environment.

4. The artificial intelligence-based greenhouse environment precision control system as described in claim 1, characterized in that, The transport layer adopts the 5G / WiFi / NB-IoT protocol.

5. The artificial intelligence-based greenhouse environment precision control system as described in claim 1, characterized in that, The control center uses machine learning to analyze the correlation between historical environmental data and crop growth, constructs a dynamic regulation model, predicts the optimal temperature and humidity thresholds, and generates dynamic regulation strategies. At the same time, the control center uses fuzzy PID control technology to adjust the output power of ventilation, shading, and irrigation equipment based on real-time feedback.

6. The artificial intelligence-based greenhouse environment precision control system as described in claim 5, characterized in that, The fuzzy PID control technology employs a hierarchical-linkage control mechanism, humidity hierarchical control, and dynamic adjustment rules, wherein: Humidity grading control is shown in the table below: The dynamic adjustment rule is as follows: When environmental parameter deviation > threshold: If the detected value is less than the set value, the control quantity is increased linearly. If the detected value is greater than the set value, then the exponential decay adjustment will be applied. When the environmental parameter deviation is less than or equal to the threshold: The PID fuzzy algorithm is used to generate the control quantity by combining the deviation and the rate of change.

7. The artificial intelligence-based greenhouse environment precision control system as described in claim 1, characterized in that, The control center uses convolutional neural networks to analyze leaf images and automatically generates instructions to trigger biological control or targeted pesticide application.

8. The artificial intelligence-based greenhouse environment precision control system as described in claim 1, characterized in that, The control center generates relevant start-stop commands through reinforcement learning, optimizes the start-stop timing of equipment, and establishes a water and fertilizer demand model matching the growth stage based on the data collected by the data acquisition module, and generates water and fertilizer release commands according to the current growth stage.

9. The artificial intelligence-based greenhouse environment precision control system as described in claim 1, characterized in that, The control center can also automatically generate data reports based on historical trend analysis. Users can obtain these data reports through the corresponding user terminal via the feedback interface. At the same time, it can perform intelligent alarms and remote control, generating multi-level early warnings.

10. The artificial intelligence-based greenhouse environment precision control system as described in claim 1, characterized in that, The environmental control module employs intelligent valves and a photovoltaic-energy storage collaborative energy management module, further including a ventilation subsystem, a shading subsystem, a temperature control subsystem, a supplemental lighting subsystem, and a CO2 regulation subsystem, all uniformly controlled by a controlled switch group. The ventilation subsystem includes a roof window / evaporative cooling curtain outward-opening window / fan unit; the shading subsystem includes a double-layer structure of external shading + internal shading; the temperature control subsystem includes air conditioning / internal insulation / circulating fan; the supplementary lighting subsystem includes dimmable LED supplementary lighting; and the CO2 control subsystem includes a generator linked with ventilation.

Images