Intelligent thermal management control system for plant factory

Abstract

The invention provides an intelligent thermal management control system for a plant factory, which is characterized in that a target heat source is embedded in an interlayer space between a wall body and a roof of the plant factory by adopting external modularization, and is tightly attached to a heat dissipation substrate on the inner wall of an interlayer through heat conduction silica gel; the other side in the interlayer space is composed of a strip-shaped guide vane array with an adjustable inclination angle, ventilation and heat dissipation holes leading to the outside are formed in the top of the interlayer, and the strip-shaped guide vane array and the ventilation and heat dissipation holes are driven by a servo motor; collecting heat source temperature, environment parameters and crop canopy phenotype data in real time; and according to the received heat source temperature, environment parameters and crop canopy phenotype data, a self-adaptive environment regulation and control scheme is constructed through a reinforcement learning algorithm, and the blade inclination angle of the strip-shaped guide blade array, the operation frequency of the axial flow fan and the power of the heat pump are dynamically adjusted based on the environment regulation and control scheme. Therefore, the energy efficiency bottleneck of a split type heat dissipation framework can be broken through, and the problem of high energy consumption caused by heat dissipation of the LED driving power supply is solved; meanwhile, the thermal inertia defect of a phase change / fluid system is overcome, and the thermal management efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of plant production temperature management, and in particular to an intelligent thermal management control system for a plant factory. Background Art

[0002] In the field of thermal management of plant factories, existing technologies mainly deal with the heat dissipation problem of LED light source driver power supply through the following methods:

[0003] 1. Canopy ventilation and heat dissipation technology: This technology typically deploys axial fans or fan arrays above or to the sides of the plant canopy, removing surface heat from the crop through forced air flow. The core principle of this technology is to use convection heat transfer to reduce canopy temperature. The specific implementation steps are: fan ducts are installed in the indoor space, and the control system activates the fans to blow air in a targeted manner through the canopy, dissipating heat into the indoor environment through air flow.

[0004] 2. Phase change cold plate and circulating water cooling technology: The former is to attach a cold plate containing phase change material to the surface of the LED driver power supply, use the heat absorption property of the phase change material when melting to absorb the heat generated by the power supply, and slowly release it through the heat conduction of the solid medium; the latter is to arrange water cooling pipes around the driver power supply, drive the coolant to circulate through the pump, transfer the heat to the outdoor heat exchanger for cooling, forming a "heat absorption-medium transfer-external release" heat dissipation cycle.

[0005] However, the method provided by the prior art has the following problems:

[0006] 1. Lack of core heat source treatment: Existing technologies either only perform surface cooling on the crop canopy (such as ventilation heat dissipation), or process the heat of the driving power supply through passive energy storage / transfer methods (such as phase change cold plates, circulating water cooling), and none of them directly build a dedicated heat dissipation channel for the driving power supply as the main heat source. For example, the canopy air does not touch the heat source itself, resulting in the inability to fundamentally solve the problem of overall indoor temperature rise; phase change / water cooling technology relies on heat conduction or transfer of fixed media, and the heat dissipation efficiency is limited by material properties or pipeline layout, and cannot be dynamically adjusted according to real-time heat load. The essential reason is that the heat dissipation design of the core heat source has not been combined with the active control mechanism. The heat source and the heat dissipation system are in a separated state, resulting in low heat accumulation and discharge efficiency.

[0007] 2. Lack of dynamic control capabilities: Existing control strategies only trigger heat dissipation equipment based on a single environmental parameter (such as canopy temperature or power surface temperature), and lack the fusion analysis of crop growth phenotypic data (such as canopy images, leaf area index, plant height and canopy temperature, etc.) and real-time heat load. For example, the heat dissipation rate of the phase change cold plate is determined by the physical properties of the phase change material, and the response of the circulating water cooling system lags behind the actual heat load changes, making it impossible to achieve "heat dissipation on demand". The fundamental problem is that the control logic has not established a synergistic relationship between the heat source heat dissipation needs and the physiological needs of crops. It has neither formed a dynamic heat conduction path based on biological information nor lacked precise control of heat dissipation equipment (such as fans and guide vanes). As a result, the thermal environment control is lagging and extensive, making it difficult to meet the high-precision requirements of plant factories for temperature and humidity parameters (such as ±1°C error control).

[0008] That is, the core deficiency of the existing technology is that the heat dissipation design of the core heat source (driving power supply) remains at the "passive response" level, and an integrated mechanism of "heat source positioning-intelligent perception-active regulation" has not been established. Moreover, the control strategy is divorced from the actual needs of crop growth, which ultimately leads to the inability to balance heat dissipation efficiency and environmental control accuracy. Summary of the Invention

[0009] In view of the above-mentioned defects, the purpose of the present invention is to provide an intelligent thermal management and control system for a plant factory, which is used to achieve precise heat dissipation of the core heat source and dynamic regulation of the indoor microenvironment.

[0010] In order to achieve the above technical effects, the present invention provides a plant factory intelligent thermal management control system, including a heat source embedded layout module, a multi-dimensional data perception module and an intelligent control module; wherein:

[0011] The heat source embedded layout module uses external modularization to embed the target heat source in the interlayer space between the wall and roof of the plant factory, and is tightly attached to the heat dissipation substrate on the inner wall of the interlayer through thermal conductive silicone. The other side of the interlayer space relative to the inner wall of the interlayer is composed of an array of strip guide blades with adjustable inclination angles. The top of the interlayer is provided with ventilation and heat dissipation holes. The strip guide blade array and ventilation and heat dissipation holes are driven by a servo motor.

[0012] The multi-dimensional data perception module includes a temperature sensor deployed on the surface of the target heat source, a number of indoor and outdoor environmental monitoring sensors, and a crop inspection device deployed indoors, which are respectively used to collect heat source temperature, environmental parameters and crop canopy phenotypic data in real time;

[0013] The intelligent control module is used to construct an adaptive environmental control scheme through a reinforcement learning algorithm based on the received heat source temperature, environmental parameters and crop canopy phenotypic data, and dynamically adjust the blade inclination angle of the strip guide blade array, the operating frequency of the axial fan and the heat pump power based on the environmental control scheme.

[0014] Optionally, the interlayer space has a thickness of 10 to 15 cm and is composed of thermal insulation material and insulation boards; an axial flow fan is installed at the end of the interlayer to discharge hot air through the top outlet or introduce it into the room.

[0015] Optionally, the guide blade array spacing is 10 cm, and the blade inclination angle range is 0° to 90°.

[0016] Optionally, the multi-dimensional data perception module also includes an Internet of Things sensor for real-time monitoring of the opening and closing angles of the blades.

[0017] Optionally, the crop phenotypic data includes canopy images, leaf area index, plant height and canopy temperature; the intelligent control module is used to automatically increase the opening and closing angle of the guide vanes to balance the heat dissipation demand when the crop phenotypic data meets preset conditions.

[0018] Optionally, the intelligent control module periodically updates control parameters through machine learning and optimizes blade angles and equipment start and stop strategies based on historical operating data.

[0019] Optionally, the crop inspection device is equipped with an RGB-D camera (a depth camera in RGB color mode) and an infrared thermal imager to periodically scan the canopy phenotype of indoor crops and generate a growth status thermal map.

[0020] Optionally, the intelligent control module is also used to preferentially utilize the waste heat of the driving power supply for heating under low temperature conditions according to a reinforcement learning algorithm.

[0021] Optionally, the intelligent control module is specifically used to input the received heat source temperature, environmental parameters and crop canopy phenotypic data into a pre-trained reinforcement learning model, so as to predict indoor temperature changes through the reinforcement learning model and determine the optimal environmental control scheme based on the predicted indoor temperature change analysis, output control parameters determined based on the environmental control scheme, and then dynamically adjust the blade inclination angle of the strip guide blade array, the operating frequency of the axial fan and the heat pump power according to the control parameters.

[0022] The plant factory intelligent thermal management control system provided by the present invention can address the problem of a single heat dissipation path for existing LED light source driver power modules and achieve efficient thermal management through multi-module collaboration. The system integrates a crop inspection device, a distributed Internet of Things sensor network, and a heat exchange channel architecture, innovatively optimizes the heat dissipation path of the LED driver power supply, embeds it into the interlayer of the building envelope structure, and combines it with a variable-angle guide vane array to construct a dynamic heat conduction path. At the same time, based on a data-driven intelligent decision-making center, the system integrates crop canopy imaging data, environmental parameters, and crop phenotypic perception models, and uses a reinforcement learning optimization algorithm to analyze the synergistic relationship between the driver power supply heat dissipation requirements and crop growth requirements in real time, dynamically adjust the opening and closing angles and heat dissipation cycles of the strip guide vanes, and achieve directional migration of hot air and precise control of the microenvironment. In this way, the present invention breaks through the traditional single-dimensional temperature control mode, forming a closed-loop thermal management paradigm with deep coupling of building structures, electromechanical equipment, and biological needs, significantly improving heat dissipation efficiency and the stability of the crop growth environment, and providing plant factories with an intelligent thermal environment solution that combines energy efficiency optimization with biological adaptability. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 A schematic block diagram of the structure of the plant factory intelligent thermal management control system provided by one embodiment of the present invention;

[0024] Figure 2 A schematic diagram of the architectural structure of a plant factory to which the plant factory intelligent thermal management control system provided in one embodiment of the present invention is applied;

[0025] Figure 3 A schematic diagram of a multi-dimensional data perception decision algorithm used by the plant factory intelligent thermal management control system provided by one embodiment of the present invention;

[0026] Figure 4 A collaborative logic diagram of the control algorithm system adopted by the plant factory intelligent thermal management control system provided in one embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0028] It should be noted that references to "one embodiment," "an embodiment," "an example embodiment," etc., in this specification indicate that the described embodiment may include specific features, structures, or characteristics, but not every embodiment must include these specific features, structures, or characteristics. Furthermore, such references do not necessarily refer to the same embodiment. Furthermore, when specific features, structures, or characteristics are described in conjunction with an embodiment, whether or not explicitly described, it is understood that incorporating such features, structures, or characteristics into other embodiments is within the knowledge of those skilled in the art.

[0029] In addition, certain words are used in the specification and subsequent claims to refer to specific components or parts. It should be understood by those with ordinary knowledge in the relevant field that manufacturers may use different nouns or terms to refer to the same component or part. This specification and subsequent claims do not use differences in names as a way to distinguish components or parts, but rather use differences in the functions of components or parts as the criteria for distinction. The words "including" and "comprising" mentioned throughout the specification and subsequent claims are open-ended terms and should be interpreted as "including but not limited to". In addition, the word "connect" here includes any direct and indirect electrical connection means. Indirect electrical connection means include connection through other devices.

[0030] Before describing the embodiments of this application in detail, we first briefly describe the technical concept of this application: The plant factory intelligent thermal management control system provided by this application specifically achieves precise heat dissipation of the core heat source and dynamic regulation of the indoor microenvironment through a three-layer architecture of "heat source positioning-intelligent conduction-demand coordination"; through the collaborative design of "heat source-building structure-crop growth" demand, the heat flow transfer path is reconstructed, and the driving power supply is converted from a passive heat dissipation object to a controllable thermal regulation node, achieving dynamic matching of the heat flux density field in the interlayer of the building envelope structure with phenotypes such as crop canopy temperature, eliminating energy dissipation conflicts between systems. In addition, through an intelligent heat exchange mechanism and a multi-mode collaborative control strategy, dynamic switching of heat dissipation modes and efficient heat transmission are achieved, significantly improving thermal management efficiency.

[0031] The specific principles of the plant factory intelligent thermal management control system of the present application are described below in conjunction with specific embodiments.

[0032] Figure 1 The plant factory intelligent thermal management control system 100 provided by one embodiment of the present invention includes a heat source embedded layout module 10, a multi-dimensional data perception module 20, and an intelligent control module 30; wherein:

[0033] The heat source embedded layout module 10 embeds the target heat source in the interlayer space between the wall and roof of the plant factory by adopting external modularization, and is tightly fitted with the heat dissipation substrate of the inner wall of the interlayer through thermal conductive silicone; the other side of the interlayer space relative to the inner wall of the interlayer is composed of a strip guide blade array with adjustable inclination, and a heat dissipation vent is provided on the top of the interlayer, and the strip guide blade array and the heat dissipation vent are driven by a servo motor; the multi-dimensional data perception module 20 includes a temperature sensor deployed on the surface of the target heat source, a number of indoor and outdoor environmental monitoring sensors, and a crop inspection device deployed indoors, which are respectively used to collect heat source temperature, environmental parameters and crop canopy phenotypic data in real time; the intelligent control module 30 is used to construct an adaptive environmental control scheme through a reinforcement learning algorithm based on the received heat source temperature, environmental parameters and crop canopy phenotypic data, and dynamically adjust the blade inclination of the strip guide blade array, the operating frequency of the axial fan and the heat pump power based on the environmental control scheme.

[0034] The target heat source is specifically the LED driver power supply in the plant factory, that is, the LED driver power supply is embedded in the interlayer space between the wall and roof of the plant factory, and then tightly fitted with the aluminum heat dissipation substrate on the inner wall of the interlayer through thermal conductive silicone.

[0035] The side of the mezzanine space close to the outdoors is the inner wall of the mezzanine, on which is provided a heat dissipation substrate and a modular target heat source, such as an LED driver power supply; the other side of the mezzanine space close to the indoors is composed of a strip guide blade array, the blades on which can be opened and closed synchronously or asynchronously. When the blade inclination angle is 0°, the blades are in a closed state, and the gap between the blades is the smallest. At this time, most of the heat generated by the target heat source will be blocked by the blades from entering the room; when the blade inclination angle is greater than 0°, the blades are in an open state. At this time, the gap between the blades increases with the increase of the inclination angle, and the heat generated by the target heat source will radiate into the room through the gap between the blades.

[0036] The interlayer space in this embodiment is 10-15 cm thick and is constructed from insulation material and thermal insulation panels. An axial flow fan is installed at the end of the interlayer to exhaust hot air through a top outlet or direct it into the room. When the axial flow fan is activated, the heat generated by the target heat source within the interlayer space is rapidly exhausted outdoors through a pre-set air outlet (in high-temperature conditions) or discharged into the room through the gaps between the blades (in low-temperature conditions). High-temperature conditions refer to conditions where indoor plants in a factory are exposed to high temperatures and require cooling, while low-temperature conditions refer to conditions where indoor plants in a factory are exposed to low temperatures and require heating.

[0037] The servo motor can control the opening and closing of the heat dissipation vents. When the heat dissipation vents are open, excess heat can be discharged outdoors through the fan circulation. When the heat dissipation vents are closed, excess heat can be prevented from being discharged outdoors.

[0038] See also Figure 2 (The left side of the figure is a transparent front view, and the right side is a transparent side view). In a specific embodiment, an LED driving power supply 7 is embedded in the mezzanine space of the roof 1, and a strip guide blade array 2 with an adjustable inclination is provided on the inner wall of the mezzanine. The strip guide blade array 2 is arranged with a number of blades with adjustable inclinations at intervals. An air exchange port 6 is also provided on the side wall 5 of the mezzanine space. The LED driving power supply 7 is connected to the heat dissipation substrate 3. The figure mark 4 is a front view of the axial flow fan, and the figure mark 8 is a side view of the axial flow fan. In this embodiment, the LED driving power supply 7 is evenly placed along the roof and the wall, and a single power supply module is tightly fitted with the aluminum heat dissipation substrate on the inner wall of the mezzanine through thermal conductive silicone, thereby forming an efficient heat conduction interface. At the same time, the fluid in the guide channel is also optimized: the inner wall of the interlayer is preset with a strip guide blade array 2 corresponding to the position of the target heat source (LED driving power supply 7), and the blades are driven by a servo motor to open and close. Different opening and closing angles will produce different thermal insulation effects. When the blade inclination angle is the largest, the thermal insulation effect is the smallest. At this time, most of the heat generated by the target heat source will be radiated through the blades to the indoor side for indoor heating; when the blade inclination angle is the smallest, the thermal insulation effect is the largest. At this time, the heat generated by the target heat source will be blocked by the closed blades, thereby preventing it from radiating to the indoor side.

[0039] In an optional embodiment, the guide vane array has a spacing of 10 cm, and the blade inclination angle ranges from 0° to 90°. Specifically, when the blade inclination angle is 0°, the blades of the guide vane array are closed, blocking the target heat source. This achieves the best insulation effect and forms a through-type heat dissipation channel, allowing the axial fan to exhaust hot air from the exhaust port in the interlayer to the outside for cooling. When the blade inclination angle is 90°, the blades of the guide vane array are fully extended, and the heat energy generated by the target heat source is radiated into the room through the gaps between the blades of the guide vane array, thereby increasing the temperature.

[0040] The multi-dimensional data perception module 20 also includes an Internet of Things sensor for real-time monitoring of the blade opening and closing angle. The Internet of Things sensor monitors the blade opening and closing angle in real time and feeds back to the intelligent control module 30. The monitoring accuracy of the blade opening and closing angle is ±1°.

[0041] In specific implementation, a temperature sensor (accuracy of ±0.2°C) is deployed on the surface of the LED driver power supply to collect the core temperature of the heat source in real time; multiple sets of environmental monitoring points are arranged indoors, and each environmental monitoring point is equipped with one or more corresponding environmental monitoring sensors (such as temperature and humidity sensors, CO2 concentration sensors, light intensity sensors, etc.); multiple sets of outdoor meteorological sensors are arranged on the roof and exterior walls to monitor ambient temperature, wind speed, and sunlight intensity, etc.; the crop inspection device is equipped with an RGB-D camera and an infrared thermal imager to periodically (such as every hour) scan the indoor crop canopy phenotype (such as plant height, leaf area index, etc.) to generate a growth status thermodynamic map; the above-mentioned collected heat source temperature, environmental parameters and crop canopy phenotype data will be fed back to the intelligent control module 30 for processing.

[0042] The intelligent control module 30 determines the current working condition (high temperature working condition or low temperature working condition) based on the received data information, and executes corresponding control strategies for different working conditions.

[0043] The intelligent control module 30 is specifically used to input the received heat source temperature, environmental parameters and crop canopy phenotypic data into a pre-trained reinforcement learning model, so as to predict indoor temperature changes through the reinforcement learning model and determine the optimal environmental control scheme based on the predicted indoor temperature change analysis, output control parameters determined based on the environmental control scheme, and then dynamically adjust the blade inclination angle of the strip guide blade array, the operating frequency of the axial fan and the heat pump power according to the control parameters, thereby realizing the leap from "passive response" to "active intelligence" in the thermal management of plant factories, and providing a replicable engineering paradigm for efficient and energy-saving facility agriculture.

[0044] The perception and execution of the reinforcement learning intelligent decision-making adopted in this embodiment are as follows Figures 3-4 As shown, the reinforcement learning model is an intelligent agent that can perceive the environment, perform actions, and learn the optimal behavior strategy based on the reward signal fed back by the environment. It perceives the crop phenotypic data and environmental status to make control actions such as blade angle adjustment and fan frequency adjustment. This embodiment realizes the intelligent allocation of internal and external air temperature through the design of air-side economizer and the environmental parameter optimization algorithm based on predictive control, ensuring the stability and accuracy of the indoor microenvironment and providing the best conditions for crop growth; through the Internet of Things distributed control system and machine learning algorithm, the coordinated operation of each subsystem and the continuous optimization of the control strategy are realized, significantly improving the intelligence level and adaptive ability of the system; through the multi-objective optimization model, the heat dissipation, heating and ventilation requirements are coordinated, the system operation strategy is optimized, the operating cost is significantly reduced, and the economic efficiency of the plant factory is improved.

[0045] The crop phenotypic data includes canopy images, leaf area index, plant height, and canopy temperature. The intelligent control module 30 is configured to automatically increase the guide vane opening and closing angle to balance heat dissipation requirements when the crop phenotypic data meets preset conditions (e.g., canopy temperature greater than a corresponding temperature threshold, or growth rate less than a corresponding rate threshold). The processing measures of the intelligent control module 30 specifically include the following two implementations:

[0046] 1. Forced heat dissipation mode under high temperature conditions

[0047] When the driving power supply temperature is ≥45°C and the indoor temperature is ≥28°C (i.e., exceeding the suitable range for crop growth), the control algorithm of the intelligent control module 30 predicts through the reinforcement learning model: if the current state is maintained, the indoor temperature will rise to 32°C in 30 minutes, triggering the high-temperature heat dissipation strategy.

[0048] The intelligent control module 30 triggers the execution of the following functional operations according to the high-temperature heat dissipation strategy:

[0049] Blade angle adjustment: The servo motor drives the strip guide blade array in the wall and roof interlayer to rotate synchronously to 0° (minimum ventilation angle), thereby isolating the target heat source while forming a through-type heat dissipation channel.

[0050] Axial flow fan start: Several axial flow fans (total air volume 5000m 3 / h) runs at 80% power, and quickly discharges the hot air (about 35°C) generated by the driving power supply to the outside through the air outlet on the top.

[0051] Preferably, a gravity heat pipe is also included, with its evaporation section attached to the heat dissipation substrate and its condensation section exposed to the outside, to assist in heat conduction. For example, multiple sets of gravity heat pipes (with their evaporation section attached to the heat dissipation substrate and their condensation section exposed to the outside) are deployed between the drive power supply and the interlayer exterior wall to dissipate some of the heat directly to the outside through phase change conduction, which can improve heat dissipation efficiency by 30%.

[0052] 2. Heat recovery mode under low temperature conditions

[0053] When the driving power supply temperature is ≤35°C and the indoor temperature is ≤20°C (lower than the suitable range for crop growth), the intelligent control module 30 identifies that the current scene is a "heat recovery scene" and triggers a low-temperature heat recovery strategy.

[0054] The intelligent control module 30 triggers the execution of the following functional operations according to the heat recovery strategy:

[0055] Blade angle adjustment: The guide blades rotate to 30° (diversion angle), blocking the direct entry of cold air from outside, while allowing the warm air in the interlayer (about 25°C) to slowly flow into the room through the gaps between the blades.

[0056] Fresh air pretreatment: After passing through the primary filter, the outdoor fresh air first flows through the heat exchange module at the bottom of the interlayer (for sensible heat exchange with the warm air in the interlayer), and the fresh air temperature is preheated to 18°C ​​before being sent into the room, reducing heating energy consumption.

[0057] Heat pump assisted control: When natural convection cannot meet the heating demand, the reversible heat pump is started (based on the waste heat of the driving power supply as a low-level heat source), and the heat pump power is adjusted through frequency conversion control to achieve precise heating (control accuracy ±1°C).

[0058] Furthermore, the intelligent control module is also configured to prioritize the use of waste heat from the driver power supply for heating in low-temperature conditions based on a reinforcement learning algorithm. For example, the control algorithm calculates that if the outdoor temperature is 10°C and the indoor temperature needs to be raised to 22°C, waste heat from the driver power supply will be prioritized for heating.

[0059] The input variables of the model used by the intelligent control module 30 of this embodiment are: key phenotypic parameters such as the real-time temperature of the driving power supply, the indoor and outdoor temperature difference, the crop canopy temperature, and the outdoor wind speed; its output variables are: the opening and closing angle of the guide vanes, the fan operating frequency, the heat pump power, etc.; the algorithm logic of the model adopts a reinforcement learning algorithm to minimize heat dissipation energy consumption while satisfying the constraint of the crop growth temperature range (22-26°C).

[0060] The system provided in this embodiment can also perform dynamic strategy optimization. Specifically, the intelligent control module 30 periodically updates control parameters through machine learning and optimizes blade angles and equipment start-stop strategies based on historical operating data. For example, the control parameters are updated once every ten minutes using a random forest algorithm, and blade angles and equipment start-stop strategies are optimized based on historical operating data (e.g., containing 100,000 sets of operating condition samples), gradually reducing energy consumption. In this way, through a period of self-learning, the system can significantly reduce the fan operating time under the same operating conditions, and significantly reduce the energy consumption of the heat pump.

[0061] In summary, this embodiment breaks through the traditional "separation of heat source and building" model through the integrated heat dissipation design of the heat source and the building structure, embeds the driving power supply into the interlayer of the enclosure structure, and constructs an exclusive heat dissipation / heat recovery channel through the guide vanes and heat pipes, so that the heat dissipation efficiency of the heat source is improved without the need for additional energy storage equipment. In addition, for the first time, crop phenotypic data (such as canopy image phenotype, canopy temperature) is incorporated into thermal management decisions. For example, when phenotypic indicators such as canopy temperature are higher than the preset threshold, the opening and closing angles of the guide vanes are automatically increased to balance the heat dissipation demand. The three modes of natural convection, forced heat dissipation, and waste heat recovery are integrated and switched in real time through intelligent algorithms, so that the overall energy consumption of the plant factory is lower than that of the traditional solution. A closed-loop control mechanism of "data collection-intelligent decision-making-precise execution" is established to form an integrated solution from heat source positioning to microenvironment control. Through the above technical solution, the present invention realizes the leap from "passive response" to "active intelligence" in the thermal management of plant factories, providing a replicable engineering paradigm for efficient and energy-saving facility agriculture.

[0062] It should be noted that, in this article, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present invention is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in the opposite order according to the functions involved. For example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0063] Of course, the present invention may have many other embodiments. Without departing from the spirit and essence of the present invention, those skilled in the art may make various corresponding changes and modifications based on the present invention, but these corresponding changes and modifications should all fall within the scope of protection of the claims attached to the present invention.

Claims

1. A plant factory intelligent thermal management control system, characterized in that: It includes a heat source embedded layout module, a multi-dimensional data perception module, and an intelligent control module; among which: The heat source embedded layout module uses external modularization to embed the target heat source in the interlayer space between the wall and roof of the plant factory, and is tightly attached to the heat dissipation substrate on the inner wall of the interlayer through thermal conductive silicone. The other side of the interlayer space relative to the inner wall of the interlayer is composed of an array of strip guide blades with adjustable inclination angles. The top of the interlayer is provided with ventilation and heat dissipation holes. The strip guide blade array and ventilation and heat dissipation holes are driven by a servo motor. The multi-dimensional data perception module includes a temperature sensor deployed on the surface of the target heat source, a number of indoor and outdoor environmental monitoring sensors, and a crop inspection device deployed indoors, which are respectively used to collect heat source temperature, environmental parameters and crop canopy phenotypic data in real time; The intelligent control module is used to construct an adaptive environmental control scheme through a reinforcement learning algorithm based on the received heat source temperature, environmental parameters and crop canopy phenotypic data, and dynamically adjust the blade inclination angle of the strip guide blade array, the operating frequency of the axial fan and the heat pump power based on the environmental control scheme.

2. The plant factory intelligent thermal management control system according to claim 1, characterized in that: The interlayer space has a thickness of 10 to 15 cm and is composed of thermal insulation materials and heat insulation boards; an axial flow fan is installed at the end of the interlayer to discharge hot air through the top outlet or introduce it into the room.

3. The plant factory intelligent thermal management control system according to claim 1, characterized in that: The guide blade array spacing is 10 cm, and the blade inclination angle ranges from 0° to 90°.

4. The plant factory intelligent thermal management control system according to claim 3, characterized in that: The multi-dimensional data perception module also includes an Internet of Things sensor for real-time monitoring of the opening and closing angles of the blades.

5. The plant factory intelligent thermal management control system according to claim 1, characterized in that: The crop phenotypic data includes canopy images, leaf area index, plant height and canopy temperature; the intelligent control module is used to automatically increase the opening and closing angle of the guide vanes to balance the heat dissipation demand when the crop phenotypic data meets preset conditions.

6. The plant factory intelligent thermal management control system according to claim 1, characterized in that: The intelligent control module periodically updates control parameters through machine learning and optimizes blade angles and equipment start-stop strategies based on historical operating data.

7. The plant factory intelligent thermal management control system according to claim 1, characterized in that: The crop inspection device is equipped with an RGB-D camera and an infrared thermal imager to periodically scan the phenotype of indoor crop canopies and generate a thermal map of the growth status.

8. The plant factory intelligent thermal management control system according to claim 1, characterized in that: The intelligent control module is also used to preferentially utilize the waste heat of the driving power supply for temperature increase under low temperature conditions according to the reinforcement learning algorithm.

9. The plant factory intelligent thermal management control system according to any one of claims 1 to 8, characterized in that: The intelligent control module is specifically used to input the received heat source temperature, environmental parameters and crop canopy phenotypic data into a pre-trained reinforcement learning model, so as to predict indoor temperature changes through the reinforcement learning model and determine the optimal environmental control scheme based on the predicted indoor temperature change analysis, output control parameters determined based on the environmental control scheme, and then dynamically adjust the blade inclination angle of the strip guide vane array, the operating frequency of the axial fan and the heat pump power according to the control parameters.

Images