Air treatment system of air conditioning unit and control method of air treatment system

Abstract

The invention discloses an air handling system of an air conditioning unit and a control method of the air handling system, and belongs to the technical field of air conditioning systems, and the system constructs an intelligent agent with sensing, predicting, decision-making and optimizing capabilities by fusing a physical entity, edge control and a cloud platform. The core of the method is that the AI technology is utilized to predict building load and personnel change, system-level simulation optimization is performed through digital twinning, air supply parameters and fresh air volume are dynamically set, and a variable air volume control mode is adaptively switched. According to the method, the hysteresis of traditional feedback control is overcome, conversion from passive response to active intervention is achieved, the energy efficiency, comfort and adaptability of the system are remarkably improved, and the method is suitable for modern intelligent buildings with high-standard requirements for indoor environment quality and energy consumption.

Description

Technical Field

[0001] This invention relates to the technical field of air conditioning systems, and in particular to a variable air volume air handling system and its control method that integrates artificial intelligence prediction, digital twin simulation and multi-parameter collaborative control. Background Technology

[0002] An air handling unit's air preparation system is a comprehensive system that uses mechanical or electrical methods to regulate air temperature (such as heating or cooling), control humidity (such as humidification or dehumidification), filter and purify air (such as removing dust, bacteria, and other pollutants), and organize airflow (such as supply air, return air, and exhaust air). Its core components typically include a surface cooler / heater, humidifier, air filter, fan, and dampers. It can process air according to multiple parameters based on environmental needs, providing regulated air that meets hygiene standards and comfort requirements for indoor spaces. This device is widely used in HVAC systems in commercial, industrial, and residential buildings.

[0003] Central ventilation and air conditioning systems are among the major energy-consuming devices in large public buildings. Variable air volume (VAV) systems adapt to changes in indoor load by adjusting the supply air volume, offering significant energy-saving potential compared to constant air volume (CAV) systems. Traditional control methods for VAV air handling systems, such as constant static pressure (CSP), variable static pressure (VSP), and total air volume demand (TOD) methods, primarily rely on real-time feedback control.

[0004] For example, Chinese patent document CN210135648U discloses a variable air volume fresh air system based on human feedback adjustment, which includes: an air supply duct with an air inlet located at a suitable air intake point on the exterior facade of the building; multiple air supply branch pipes, one end of which is connected to the air supply duct, and the other end of which is an air outlet located in the room; a fresh air unit, located in the fresh air machine room or ceiling, connected to the air supply duct, and internally equipped with a fresh air valve, a pre-filter, a medium-efficiency filter, a temperature control device, a high-pressure spray humidifier, and a variable frequency air supply fan; and a control unit integrated into the building automation system. The air outlet is also equipped with an electric air volume regulating valve and an orifice plate air volume measuring device. An infrared sensor is also installed in the room. A static pressure measuring point is also installed between the variable frequency air supply fan and the end of the air supply duct. An anti-freeze switch is also installed between the medium-efficiency filter and the heating and cooling device. Differential pressure switches are connected to both sides of the pre-filter, the medium-efficiency filter, and the variable frequency air supply fan.

[0005] However, in existing technologies, fresh air control mostly relies on a single [system / mechanism]. Concentration monitoring fails to comprehensively consider the dynamic changes in multiple air quality parameters and outdoor weather conditions, leading to energy waste or a decline in indoor air quality. Furthermore, the system's supply air temperature and humidity setpoints are typically set manually by season, failing to respond to short-term, dynamic load fluctuations and limiting its full energy-saving potential.

[0006] Therefore, there is an urgent need in this field for an air handling system that can proactively predict load, adaptively adjust operating strategies, and achieve multi-objective collaborative optimization. Summary of the Invention

[0007] Therefore, it is necessary to address the shortcomings of existing technologies by providing a smart predictive adaptive variable air volume air handling system and its control method that offers faster response, higher energy efficiency, and better comfort.

[0008] An air handling system for an air conditioning unit, comprising: A physical system used to handle air; The sensing and execution layer is used to collect environmental and equipment parameters and execute control commands. An edge control layer is used to implement local closed-loop control; and The cloud platform layer is used for big data analysis, AI prediction, and global optimization. The cloud platform layer includes: The AI ​​prediction module is used to predict the building's heat load and population density in future periods. A digital twin module is used to build and run a virtual model corresponding to the physical entity system; The global optimization module is used to generate the optimal control setpoint based on the outputs of the AI ​​prediction module and the digital twin module; The system receives the optimal control setting value through the edge control layer and controls the physical entity system.

[0009] Specifically, the sensing and actuation layer includes a multi-source sensor array, which at least includes sensors for monitoring indoor air quality. Sensors, PM2.5 sensors and TVOC sensors, as well as infrared sensors or cameras for sensing people density.

[0010] Specifically, the edge control layer has a built-in lightweight AI inference engine that can run prediction models optimized by the cloud platform and execute degradation control strategies when the network is interrupted.

[0011] Furthermore, a method for using an air handling system of an air conditioning unit as described above includes the following steps: The AI ​​prediction module obtains predicted values ​​of the building's heat load and population density for future periods. The global optimization module dynamically calculates and sets the supply air temperature and humidity based on the predicted value, real-time sensor data, and the maximum supply air temperature difference. The minimum fresh air volume is dynamically adjusted based on comprehensive indoor air quality parameters, predicted personnel density, and indoor-outdoor enthalpy difference. Based on the operating status of the variable air volume terminal unit, adaptive switching is performed between constant static pressure, variable static pressure, and total air volume demand control methods to adjust the frequency of the blower.

[0012] Specifically, the step of dynamically adjusting the minimum fresh air volume adopts fuzzy logic control or reinforcement learning algorithm.

[0013] Specifically, the setting of the supply air temperature and humidity adopts a cascade control loop based on the feedforward signal and with the supply air temperature and humidity as intermediate variables.

[0014] Specifically, the AI ​​prediction model and control strategy parameters are periodically validated and self-learned online through the digital twin module. The self-learning results are used to update the inference model of the edge control layer and the optimization strategy of the cloud platform to achieve continuous system optimization.

[0015] In summary, this invention discloses an air handling system and its control method for an air conditioning unit. This system integrates physical entities, edge control, and a cloud platform to construct an intelligent agent with sensing, prediction, decision-making, and optimization capabilities. Its core lies in utilizing AI technology to predict building load and occupant changes, performing system-level simulation optimization through digital twins, dynamically setting supply air parameters and fresh air volume, and adaptively switching variable air volume control modes. This method overcomes the lag inherent in traditional feedback control, achieving a shift from passive response to active intervention, significantly improving the system's energy efficiency, comfort, and adaptability. It is suitable for modern intelligent buildings with high standards for indoor environmental quality and energy consumption. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the overall architecture of an air handling system for an air conditioning unit according to the present invention; Figure 2 This is a flowchart of a control method for an air handling system of an air conditioning unit according to the present invention; Figure 3 This is a schematic diagram of the multi-parameter fusion fresh air control logic of an air handling system for an air conditioning unit according to the present invention; Figure 4 This is a logic diagram of the adaptive switching of the hybrid variable air volume control mode of an air handling unit according to the present invention. Detailed Implementation

[0017] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Many specific details are set forth in the following description to provide a thorough understanding of the present invention. However, the present invention can be practiced in many other ways different from those described herein, and those skilled in the art can make similar modifications without departing from the spirit of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0018] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," and "circumferential" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0019] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0020] In this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components, unless otherwise explicitly limited. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0021] In this invention, unless otherwise explicitly specified and limited, "above" or "below" the second feature can mean that the first feature is in direct contact with the second feature, or that the first feature is in indirect contact with the second feature through an intermediate medium. Furthermore, "above," "over," and "on top" of the second feature can mean that the first feature is directly above or diagonally above the second feature, or simply that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature can mean that the first feature is directly below or diagonally below the second feature, or simply that the first feature is at a lower horizontal level than the second feature.

[0022] It should be noted that when an element is referred to as being "fixed to" or "set on" another element, it can be directly on the other element or there may be an intervening element. When an element is considered to be "connected to" another element, it can be directly connected to the other element or there may be an intervening element. The terms "vertical," "horizontal," "upper," "lower," "left," "right," and similar expressions used herein are for illustrative purposes only and do not represent the only possible implementation.

[0023] Please refer to the following: Figures 1 to 4 , Figure 1 A four-layer architecture for an air handling system of an air conditioning unit is demonstrated. Figure 2 For the control method flowchart; Figure 3 For fresh air control logic; Figure 4 This is the logic for switching the variable air volume control mode.

[0024] Furthermore, the present invention provides an air handling system for an air conditioning unit, comprising: a physical entity system, a sensing and execution layer, an edge control layer, and a cloud platform layer.

[0025] The physical entity system includes an air handling unit consisting of a fan, air valve, heat exchange coil, humidifier, filter, and supply / return air ducts, as well as variable air volume terminal devices connected to it; the physical entity system acquires real-time data and receives control commands through the sensing and execution layer.

[0026] The sensing and execution layer includes: Multi-source sensor array: used to collect outdoor temperature and humidity, atmospheric pressure, PM2.5; indoor / return air temperature and humidity, Concentration, TVOC concentration, presence signal; supply air temperature and humidity, air volume, static pressure; mixed air temperature and humidity; dew point temperature on the outlet side of the surface cooler; supply and return water temperature / pressure; and the actual opening degree of each electric valve.

[0027] Intelligent actuators include a fan frequency converter, an electric regulating water / steam valve, and an electric air valve. The frequency converter exchanges data with the edge control layer through a standard industrial communication protocol.

[0028] Edge control layer: Consists of field controllers deployed in the data center, which have a built-in lightweight AI inference engine, such as... etc., responsible for: It receives instructions and data from the sensing and execution layer and the cloud platform layer.

[0029] Executes high-frequency local closed-loop control logic.

[0030] Run a lightweight prediction model optimized for the cloud platform.

[0031] The cloud platform layer includes: a digital twin module: which builds a high-fidelity simulation model synchronized with the physical entity system for system state estimation, fault diagnosis, and strategy verification.

[0032] AI Prediction Module: Based on historical operational data, weather forecasts, and building schedules, it uses machine learning algorithms to predict changes in building heat load and population density over the next 2-6 hours.

[0033] Global optimization module: Based on digital twin and AI prediction results, with the goal of maximizing overall system energy efficiency and optimizing indoor environment, calculates the optimal control setpoint and sends it to the edge control layer.

[0034] Furthermore, the present invention also discloses a control method for an air handling system employing the above-described air conditioning unit. The method includes the following steps: 1. Data fusion and status awareness: The system collects multi-source sensor data in real time and performs data cleaning and status reconstruction through the digital twin module to obtain a complete view of the system's operating status.

[0035] 2. Load and Population Forecasting: The AI ​​forecasting module integrates meteorological data, historical load patterns, and building schedules to predict indoor cooling / heating loads and population density distribution within future time windows.

[0036] 3. Multi-objective dynamic optimization: Supply air parameter settings: The global optimization module uses predicted load, current outdoor meteorological parameters, and the "maximum supply air temperature difference" energy-saving principle as inputs to dynamically calculate the optimal supply air temperature and humidity setpoints for future periods, ensuring that the system operates at the minimum airflow condition while meeting the load requirements. Specifically, the energy-saving mechanism of the "maximum supply air temperature difference" principle is to maximize the difference between the supply air temperature and the indoor set temperature, i.e., the supply air temperature difference, while meeting the indoor heat load demand. This is based on the building heat and humidity load formula. Where Q is the cooling capacity, C_p is the specific heat capacity of air, ρ is the air density, G is the air volume, and ΔT is the supply air temperature difference. When the indoor load Q to be transferred is constant, the larger the supply air temperature difference ΔT, the smaller the required supply air volume G. Since the fan power consumption is approximately proportional to the cube of the air volume, i.e. Therefore, reducing the air volume G will lead to a significant reduction in fan energy consumption. This principle ensures that the system always tends to operate with a smaller air volume while meeting the load requirements, thereby directly and effectively reducing fan energy consumption and achieving energy-saving operation.

[0037] Dynamic control of fresh air volume, combined with Figure 3 Comprehensive indoor The system uses real-time concentrations of PM2.5 and TVOC, predicted population density, and the enthalpy difference between indoor and outdoor air to dynamically calculate the minimum fresh air volume required, achieving the best balance between IAQ and energy consumption.

[0038] Variable air volume hybrid control, combined with Figure 4 The edge control layer adaptively switches between constant static pressure, variable static pressure, and total air volume demand control methods based on the valve opening at each VAV terminal, the total system air volume demand, and the supply static pressure. The switching strategy is evaluated and determined by the digital twin module to ensure that the system operates at the lowest fan energy consumption under any operating condition.

[0039] 4. Cascade and Feedforward Control: The system employs a cascade control loop with supply air temperature and humidity as intermediate variables to suppress overshoot caused by large inertia. Simultaneously, load changes predicted by AI are used as feedforward signals to adjust the opening of water valves and air valves, as well as the fan frequency, in advance, achieving proactive regulation.

[0040] 5. Online Learning and Adaptation: The cloud platform layer periodically compares the digital twin prediction results with actual operating data, performs online calibration and self-learning of the AI ​​prediction model and control strategy parameters, enabling the system to continuously evolve and adapt to changes in building usage characteristics. Compared with the prior art, the advantages of the present invention are as follows: 1. Proactive control: By predicting loads through AI, the system transforms passive response into proactive intervention, significantly reducing system regulation lag and overshoot, and improving control quality and stability.

[0041] 2. Optimal global energy efficiency: Through system-level simulation optimization using digital twins, the wind and water systems are managed collaboratively, avoiding the increase in global energy consumption caused by local optimization. The overall energy efficiency is expected to be 20%-30% higher than that of traditional systems.

[0042] 3. Intelligent comfort and health: The multi-parameter integrated fresh air control strategy maximizes the use of free outdoor cooling sources or reduces the energy consumption of fresh air treatment while ensuring healthy indoor air quality.

[0043] 4. Strong adaptability: The hybrid variable air volume control mode enables the system to adapt to different pipeline characteristics and load distribution, always maintaining operation in the high-efficiency zone, overcoming the limitations of a single control method.

[0044] 5. Self-evolution capability: The system has an online learning function, which can adjust itself according to changes in building usage patterns, maintain optimal performance in the long term, and reduce the difficulty and cost of later operation and maintenance.

[0045] Furthermore, the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. Example 1

[0046] The physical entity of this system is a single-fan air handling unit, serving an open-plan office area. In the sensing and actuation layer, high-precision sensors are installed in the return air duct. A PM2.5 composite sensor is installed, and personnel counters are installed at the main entrances and exits. The edge control layer uses a high-performance PLC and communicates with the wind turbine inverter and all sensors via the Modbus TCP protocol. The cloud platform layer is deployed on a private cloud and interacts with the PLC via a 4G network.

[0047] Example 2: The operation process on a certain workday in summer is as follows: At 7:00 a.m., the AI ​​prediction module, based on the weather forecast and workday schedule, predicted that the office area would experience a peak in personnel load between 9:00 and 10:00 a.m.

[0048] Based on this, the cloud platform's global optimization module calculated that, in order to cope with the peak, the supply air temperature and humidity should be gradually reduced from 16℃ to 15℃ starting at 8:30, and the opening of the fresh air valve should be increased in advance to utilize the lower outdoor air temperature in the early morning for pre-cooling.

[0049] The edge controller executes the instruction and employs cascade control with the supply air temperature and humidity as the inner loop and the indoor temperature as the outer loop.

[0050] During this period, the system detected that the average opening of the VAV (Variable Air Volume) terminal damper was greater than 85%, so it automatically switched from "constant static pressure control" to "variable static pressure control" to reduce the fan speed and further save energy.

[0051] When indoor PM2.5 concentration temporarily increases due to external pollution, the fresh air control strategy temporarily prioritizes IAQ and appropriately reduces the fresh air volume until the filtration system reduces the pollutant concentration to a safe level.

[0052] Based on the above method, the air handling system of the air conditioning unit of the present invention achieves efficient, comfortable and intelligent operation.

[0053] In summary, this invention discloses an air handling system and its control method for an air conditioning unit. By integrating physical entities, edge control, and a cloud platform, it constructs an intelligent agent with sensing, prediction, decision-making, and optimization capabilities. Its core lies in utilizing AI technology to predict building load and occupant changes, performing system-level simulation optimization through digital twins, dynamically setting supply air parameters and fresh air volume, and adaptively switching variable air volume control modes. This method overcomes the lag inherent in traditional feedback control, achieving a shift from "passive response" to "active intervention," significantly improving the system's energy efficiency, comfort, and adaptability. It is suitable for modern intelligent buildings with high standards for indoor environmental quality and energy consumption.

[0054] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0055] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these all fall within the protection scope of the present invention. Therefore, the protection scope of this invention patent should be determined by the appended claims.

Claims

1. An air handling system for an air conditioning unit, characterized in that, It includes: A physical system used to handle air; The sensing and execution layer is used to collect environmental and equipment parameters and execute control commands. Edge control layer, used to implement local closed-loop control; And the cloud platform layer, used for big data analysis, AI prediction and global optimization; The cloud platform layer includes: The AI ​​prediction module is used to predict the building's heat load and population density in future periods. A digital twin module is used to build and run a virtual model corresponding to the physical entity system; The global optimization module is used to generate the optimal control setpoint based on the outputs of the AI ​​prediction module and the digital twin module; The system receives the optimal control setting value through the edge control layer and controls the physical entity system.

2. The air handling system of an air conditioning unit according to claim 1, characterized in that: The sensing and actuation layer includes a multi-source sensor array, which includes at least one sensor for monitoring indoor air quality. Sensors, PM2.5 sensors and TVOC sensors, as well as infrared sensors or cameras for sensing people density.

3. The air handling system of an air conditioning unit according to claim 1, characterized in that: The edge control layer has a built-in lightweight AI inference engine that can run prediction models optimized for cloud platforms and execute degradation control strategies when the network is interrupted.

4. A control method for an air handling system of an air conditioning unit as described in any one of claims 1-3, characterized in that, Includes the following steps: The AI ​​prediction module obtains predicted values ​​of the building's heat load and population density for future periods. The global optimization module dynamically calculates and sets the supply air temperature and humidity based on the predicted value, real-time sensor data, and the maximum supply air temperature difference. The minimum fresh air volume is dynamically adjusted based on comprehensive indoor air quality parameters, predicted personnel density, and indoor-outdoor enthalpy difference. Based on the operating status of the variable air volume terminal unit, adaptive switching is performed between constant static pressure, variable static pressure, and total air volume demand control methods to adjust the frequency of the blower.

5. The control method for an air handling system of an air conditioning unit according to claim 4, characterized in that: The step of dynamically adjusting the minimum fresh air volume adopts fuzzy logic control or reinforcement learning algorithm.

6. The control method for an air handling system of an air conditioning unit according to claim 4, characterized in that: The supply air temperature and humidity settings are based on a cascade control loop with the supply air temperature and humidity as intermediate variables.

7. The control method for an air handling system of an air conditioning unit according to claim 4, characterized in that, Also includes: The AI ​​prediction model and control strategy parameters are periodically validated and self-learned online through the digital twin module, and the self-learning results are fed back to the cloud platform layer and edge control layer to achieve continuous system optimization.

Images