A central air conditioning system and a control method thereof

Abstract

The application provides a central air conditioning system and a control method thereof, and relates to the technical field of air conditioners. The central air conditioning system comprises: an outdoor heat exchanger; an indoor heat exchanger; a compressor; a four-way valve; a refrigerant circulation loop for circulating refrigerant in a loop composed of the compressor, the indoor heat exchanger, an expansion valve, the four-way valve and the outdoor heat exchanger; a temperature sensor for detecting temperature data of a target area; a controller electrically connected with the temperature sensor, wherein the controller is configured to: receive a target instruction, the target instruction being used to instruct to acquire the apparent temperature of the target area; in response to the target instruction, detect the temperature data of the target area through the temperature sensor; process the temperature data of the target area by using a graph attention model to obtain the apparent temperature of the target area output by the graph attention model; and adjust the operating parameters of the central air conditioning system according to the apparent temperature of the target area.

Description

Technical Field

[0001] This application relates to the field of air conditioning technology, and in particular to a central air conditioning system and its control method. Background Technology

[0002] Currently, with the improvement of living standards, central air conditioning systems are becoming increasingly common in daily life, and their level of intelligence is also increasing. Many central air conditioning systems can adjust their control parameters based on the detected perceived temperature of the user. For example, a central air conditioning system can determine the perceived temperature of the user based on the temperature at the return air vent.

[0003] In related technologies, a temperature compensation value is typically set at the factory, and the sum of the temperature at the air outlet of the central air conditioning system and the temperature compensation value is used as the user's perceived temperature. However, since the temperature compensation value is preset at the factory, it is often impossible to accurately determine the user's actual perceived temperature for different central air conditioning installation environments, different room sizes, or different sunlight conditions. This leads to inaccurate adjustments of the central air conditioning system's control parameters, affecting the user experience.

[0004] Therefore, determining the user's perceived temperature is an urgent problem to be solved. Summary of the Invention

[0005] This application provides a central air conditioning system and its control method, which is used to establish a graph attention model based on temperature data detected by a temperature sensor, process the temperature data of the target area through the graph attention model, and thus obtain the perceived temperature of the target area predicted by the graph attention model.

[0006] To achieve the above objectives, the embodiments of this application adopt the following technical solutions:

[0007] In a first aspect, a central air conditioning system is provided, the central air conditioning system comprising:

[0008] Outdoor heat exchanger;

[0009] An indoor heat exchanger; wherein, the outdoor heat exchanger and the indoor heat exchanger, one functions as a condenser and the other as an evaporator;

[0010] A compressor for compressing refrigerant gas and discharging it to the condenser;

[0011] A four-way valve is used to control the flow direction of refrigerant in the refrigerant circulation loop;

[0012] The refrigerant circulation loop is used to circulate the refrigerant in the loop consisting of the compressor, the indoor heat exchanger, the expansion valve, the four-way valve, and the outdoor heat exchanger.

[0013] Temperature sensors are used to detect temperature data in the target area;

[0014] A controller, electrically connected to the temperature sensor, is configured to:

[0015] Receive a target instruction, the target instruction being used to instruct the acquisition of the perceived temperature of a target area;

[0016] In response to the target command, the temperature data of the target area is detected by the temperature sensor;

[0017] The temperature data of the target area is processed using a graph attention model to obtain the perceived temperature of the target area output by the graph attention model.

[0018] The operating parameters of the central air conditioning system are adjusted according to the perceived temperature of the target area.

[0019] The technical solution provided in this application provides at least the following beneficial effects: Since the user's perceived temperature accurately reflects the comfort level of the central air conditioning system, accurately obtaining the user's perceived temperature is crucial. In related technologies, a temperature compensation value is typically set at the factory, and the sum of the temperature at the air outlet of the central air conditioning system and the temperature compensation value is used as the user's perceived temperature. However, due to the different environments in which central air conditioning systems operate, a fixed temperature compensation value often fails to accurately determine the user's actual perceived temperature for different installation environments, room sizes, or sunlight conditions. In this application, upon receiving an instruction to obtain the perceived temperature of a target area, a graph attention model is used to process the temperature data of the target area detected by the temperature sensor, thereby obtaining the perceived temperature of the target area output by the graph attention model. Since the graph attention model is trained based on temperature data samples detected by the temperature sensor, the output perceived temperature of the target area can better match the perceived temperature in the actual environment of the central air conditioning system. Furthermore, adjusting the operating parameters of the central air conditioning system based on the perceived temperature of the target area can improve the comfort level of the central air conditioning system.

[0020] In some embodiments, the graph attention model described above is obtained by the controller performing the following steps: acquiring initial temperature data detected by multiple temperature sensors; preprocessing the initial temperature data detected by each temperature sensor to obtain the features of each node in the graph attention model; one temperature sensor corresponds to one node in the graph attention model; calculating the attention coefficients between the target node and each neighbor node in the graph attention model based on the features of each target node and the features of neighbor nodes; the target node is one of the nodes in the graph attention model, and the neighbor node is a node adjacent to the target node in the graph attention model, with one target node and one neighbor node corresponding to one attention coefficient in the graph attention model; normalizing the attention coefficients between the target node and its neighbor nodes in the graph attention model; and obtaining the graph attention model based on the normalized attention coefficients.

[0021] As can be seen from the above embodiments, not all initial temperature data detected by multiple temperature sensors can be used for learning the graph attention model. Therefore, the initial temperature data is preprocessed to meet the learning conditions of the graph attention model. In this embodiment, each temperature sensor is used as a node in the graph attention model. Based on the node characteristics of the target node and its neighboring nodes, the attention coefficients between the target node and each neighboring node in the graph attention model are calculated. These attention coefficients characterize the importance of the neighboring node to the target node. Then, by normalizing the attention coefficients between the target node and each neighboring node in the graph attention model, the graph attention model can be obtained.

[0022] In some embodiments, the attention coefficient is obtained using the following formula:

[0023]

[0024] In the formula, e ij Represents the attention coefficient; 'a' indicates that the graph attention model is a single-layer feedforward neural network; h i h represents the node characteristics of the target node. j is the node characteristics of neighboring nodes; W is the weight parameter.

[0025] In some embodiments, the controller is further configured to: update the weight parameters via backpropagation; and update the attention coefficients based on the updated weight parameters.

[0026] As can be seen from the above embodiments, during the sample training process of the graph attention model, there may be a significant difference between the actual perceived temperature in the sample data and the output predicted perceived temperature. This indicates that the predicted perceived temperature processed by the graph attention model has a large error. Therefore, the attention coefficients can be updated by updating the weight parameters, so that the predicted perceived temperature output by the graph attention model is closer to the actual perceived temperature.

[0027] In some embodiments, the controller performs processing of temperature data of the target area using a graph attention model to obtain the perceived temperature of the target area output by the graph attention model. Specifically, the controller is configured to: use a temperature sensor as a node to input the temperature processing data of the target area into the graph attention model; perform weighted summation of the features of each node in the target area to obtain the feature fusion result of the target area; and process the feature fusion result through an activation function to obtain the perceived temperature of the target area.

[0028] As can be seen from the above embodiments, after obtaining the graph attention model, the temperature processing data of the target area is input into the graph attention model. By weighted summation of the features of each node in the target area, the feature fusion result of the target area can be obtained. After the fusion result is processed by the activation function, the perceived temperature of the target area corresponding to the fusion result can be obtained, thereby realizing the prediction of the perceived temperature of the target area based on the graph attention model.

[0029] In some embodiments, the controller performs preprocessing on the initial temperature data detected by each temperature sensor to obtain the features of each node of the graph attention model. Specifically, this is configured to: remove outlier data from the initial temperature data detected by each temperature sensor to obtain intermediate temperature data, where outlier data includes data with a variance of a preset value; and perform z-score normalization on the intermediate temperature data to obtain the features of each node of the graph attention model.

[0030] As can be seen from the above embodiments, the initial temperature data may contain abnormal temperature data, such as temperature data with a preset variance. By removing abnormal data to obtain intermediate temperature data, and then performing z-score standardization on the intermediate temperature data, the intermediate temperature data after preset processing can be made to meet the learning conditions of the graph attention model. Z-score standardization is a data processing method that transforms data of different magnitudes into z-score values ​​of the same metric for comparison, thus standardizing the intermediate temperature data. Therefore, by performing Z-score standardization on the intermediate data, the intermediate temperature data becomes a node feature matrix that can be used by the graph attention model.

[0031] In some embodiments, the controller performs z-score normalization on the intermediate temperature data using the following formula to obtain the features of each node in the graph attention model:

[0032]

[0033] In the formula, x represents intermediate temperature data, x′ represents the characteristics of the nodes, and σ represents the standard deviation.

[0034] Secondly, embodiments of this application provide a control method for a central air conditioning system, the method comprising:

[0035] The aforementioned central air conditioning system includes:

[0036] Outdoor heat exchanger;

[0037] An indoor heat exchanger; wherein, the outdoor heat exchanger and the indoor heat exchanger, one functions as a condenser and the other as an evaporator;

[0038] A compressor for compressing refrigerant gas and discharging it to the condenser;

[0039] A four-way valve is used to control the flow direction of refrigerant in the refrigerant circulation loop;

[0040] The refrigerant circulation loop is used to circulate the refrigerant in the loop consisting of the compressor, the indoor heat exchanger, the expansion valve, the four-way valve, and the outdoor heat exchanger.

[0041] Temperature sensors are used to detect temperature data in the target area;

[0042] The above methods include:

[0043] Receive a target instruction, the target instruction being used to instruct the acquisition of the perceived temperature of a target area;

[0044] In response to the target command, the temperature data of the target area is detected by the temperature sensor;

[0045] The temperature data of the target area is processed using the trained graph attention model to obtain the perceived temperature of the target area output by the trained graph attention model.

[0046] The operating parameters of the central air conditioning system are adjusted according to the perceived temperature of the target area.

[0047] Thirdly, embodiments of this application provide a controller, including: one or more processors; one or more memories; wherein the one or more memories are used to store computer program code, the computer program code including computer instructions, and when the one or more processors execute the computer instructions, the controller executes the control method provided in the second aspect.

[0048] Fourthly, embodiments of this application provide a computer-readable storage medium including computer instructions that, when controlled on a computer, cause the computer to perform the methods provided in the second aspect and possible implementations.

[0049] Fifthly, embodiments of the present invention provide a computer program product that can be directly loaded into a memory and contains software code. After being loaded and executed by a computer, the computer program product can implement the methods provided in the second aspect and possible implementations.

[0050] It should be noted that the aforementioned computer instructions may be stored, in whole or in part, on a computer-readable storage medium. This computer-readable storage medium may be packaged together with the controller's processor, or it may be packaged separately from the controller's processor; this application does not impose any limitations on this.

[0051] The beneficial effects described in aspects two through five of this application can be referred to the analysis of the beneficial effects of aspect one, and will not be repeated here. Attached Figure Description

[0052] The accompanying drawings are provided to further understand the technical solutions of the present invention and constitute a part of the specification. They are used together with the embodiments of this application to explain the technical solutions of the present invention and do not constitute a limitation on the technical solutions of the present invention.

[0053] Figure 1 This is a schematic diagram of the structure of a graph attention model provided in an embodiment of this application;

[0054] Figure 2 This application provides a schematic diagram of the structure of a central air conditioning system according to an embodiment of the present application.

[0055] Figure 3 This is a schematic diagram of another central air conditioning system provided in an embodiment of this application;

[0056] Figure 4 A schematic diagram of the refrigeration cycle principle of a central air conditioning system provided in this application embodiment;

[0057] Figure 5 A schematic diagram of the heating cycle principle of a central air conditioning system provided in this application embodiment;

[0058] Figure 6 A schematic diagram showing the installation location of a temperature sensor according to an embodiment of this application;

[0059] Figure 7 A schematic diagram showing the installation location of another temperature sensor provided in an embodiment of this application;

[0060] Figure 8 A schematic diagram showing the installation location of another temperature sensor provided in an embodiment of this application;

[0061] Figure 9 A schematic diagram of the hardware structure of a controller provided in an embodiment of this application;

[0062] Figure 10 A flowchart illustrating another control method for a central air conditioning system provided in this application embodiment;

[0063] Figure 11 This is a schematic diagram of another graph attention model provided in an embodiment of this application;

[0064] Figure 12 This is a flowchart of a backpropagation method provided in an embodiment of this application. Detailed Implementation

[0065] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0066] In the description of this invention, it should be understood that the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are 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.

[0067] 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. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0068] In this article, the term "and / or" is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone.

[0069] In the description of the embodiments of this application, it should be noted that, unless otherwise explicitly specified and limited, the terms "connected" and "connected" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances. Furthermore, when describing pipelines, the terms "connected" and "connected" as used in this application have the meaning of establishing electrical conductivity. The specific meaning needs to be understood in conjunction with the context.

[0070] The terms “comprising” and “having”, and any variations thereof, used in the description of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the steps or units listed, but may optionally include other steps or units not listed, or may optionally include other steps or units inherent to such process, method, product, or apparatus.

[0071] Furthermore, in the embodiments of this application, the words "exemplary" or "for example" are used to indicate that they are examples, illustrations, or descriptions. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design options. Specifically, the use of the words "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0072] To facilitate understanding, a brief introduction to the relevant concepts involved in this application will be given first.

[0073] Graph attention network (GAT) is a graph neural network model based on attention mechanisms, such as... Figure 1 As shown, the target node i in the GAT graph and its neighboring nodes j form a structural relationship. Here, i, j ∈ Ni, and Ni is the set of neighboring nodes of the target node i. Through a self-attention mechanism, the target node i in the GAT graph can adaptively match the weight parameters of different neighboring nodes j based on the characteristics of those nodes, thereby improving the model's accuracy.

[0074] As described in the background section, with the increasing prevalence and intelligence of central air conditioning systems, many systems can adjust their control parameters based on the detected perceived temperature of the user. For example, a central air conditioning system can determine the perceived temperature based on the return air vent temperature. In related technologies, a temperature compensation value is typically set at the factory, and the sum of the temperature at the air outlet and the compensation value is used as the perceived temperature. However, since the temperature compensation value is preset at the factory, it often fails to accurately determine the user's actual perceived temperature for different installation environments, room sizes, or sunlight conditions. This leads to inaccurate adjustments to the control parameters and negatively impacts the user experience.

[0075] In view of this, embodiments of this application provide a control method for a central air conditioning system. Upon receiving an instruction to obtain the perceived temperature of a target area, a graph attention model is used to process the temperature data of the target area detected by a temperature sensor, thereby obtaining the perceived temperature of the target area output by the graph attention model. Since the graph attention model is trained based on the temperature data detected by the temperature sensor, the output perceived temperature of the target area can be made more consistent with the perceived temperature in the actual environment in which the central air conditioning system operates. Furthermore, adjusting the operating parameters of the central air conditioning system based on the perceived temperature of the target area can improve the comfort level of the central air conditioning system.

[0076] The central air conditioning system provided in this application embodiment can be a duct-type central air conditioning system, a water-cooled central air conditioning system, or a multi-split central air conditioning system. This application embodiment does not impose any restrictions on the type of central air conditioning system.

[0077] To further describe the technical solutions of the embodiments of this application, as follows: Figure 2 The diagram shown is a structural diagram of a central air conditioning system provided in an embodiment of this application.

[0078] Reference Figure 2 The central air conditioning system 1 includes: an indoor unit 10, an outdoor unit 20, connecting pipes 30, a temperature sensor 40, and a controller 50 (the temperature sensor 40 and the controller 50 are located in...). Figure 2 (Not shown in the image).

[0079] The indoor unit 10 is used to exchange heat with the indoor air, thereby cooling or heating the indoor air.

[0080] For example, indoor unit 10 can be a wall-mounted unit or a floor-standing unit. Taking a wall-mounted unit as an example... Figure 2For example (as shown in the diagram), indoor wall-mounted units are typically installed on indoor walls. It should be understood that this application does not impose any limitations on the form of the indoor unit 10.

[0081] In some embodiments, such as Figure 3 As shown, the indoor unit 10 includes at least an indoor heat exchanger 101, which assists the refrigerant (also known as a refrigerant, which will not be described in detail below) in exchanging heat with the indoor environment, thereby achieving cooling or heating of the indoor air.

[0082] For example, when the central air conditioning system 1 is in cooling mode, the indoor heat exchanger 101 operates as an evaporator to assist in cooling the indoor air. When the central air conditioning system 1 is in heating mode, the indoor heat exchanger 101 operates as a condenser to assist in heating the indoor air.

[0083] The outdoor unit 20 is typically installed outdoors to assist the indoor unit 10 in heat exchange within the indoor environment. Additionally, in Figure 2 Since the outdoor unit 20 is located outdoors on the opposite side of the indoor unit 10, separated by a wall, it is represented by a dashed line.

[0084] It should be noted that the central air conditioning system 1 provided in this application embodiment may include one or more indoor units 10 and one or more outdoor units 20, and this application embodiment does not impose any restrictions on this.

[0085] In some embodiments, continue as follows Figure 3 As shown, the outdoor unit 20 may include: an outdoor heat exchanger 201, a compressor 202, a four-way valve 203, a gas-liquid separator 204, and an expansion valve 205.

[0086] The indoor heat exchanger 101, outdoor heat exchanger 201, compressor 202, four-way valve 203, gas-liquid separator 204 and expansion valve 205 form a refrigerant circulation loop.

[0087] In some embodiments, the four ports of the four-way valve 203 can be connected to the exhaust port of the compressor 202, the outdoor heat exchanger 201, the gas-liquid separator 204, and the indoor heat exchanger 101, respectively. It should be understood that "connection" here does not mean that there cannot be other components between the ports of the four-way valve 203 and the components connected to those ports. For example, components such as expansion valves can also be present to achieve throttling control, and this application does not impose specific limitations in this regard.

[0088] Reference Figure 4 and Figure 5 The four-way valve 203 can switch between cooling and heating modes by changing the flow direction of the refrigerant in the system pipeline.

[0089] like Figure 4As shown, when the four-way valve 203 connects the exhaust port of the compressor 202 and the indoor heat exchanger 101, the refrigerant flows in the direction indicated by the arrow. The indoor heat exchanger 101 works as an evaporator, and the outdoor heat exchanger 201 works as a condenser to achieve cooling of the indoor air.

[0090] like Figure 5 As shown, when the four-way valve 203 connects the exhaust port of the compressor 202 and the outdoor heat exchanger 201, the refrigerant flows in the direction indicated by the arrow. The outdoor heat exchanger 201 works as an evaporator, and the indoor heat exchanger 101 works as a condenser to heat the indoor air.

[0091] In some embodiments, compressor 202 is used to power refrigerant circulation. Compressor 202 compresses the refrigerant supplied by gas-liquid separator 204 and delivers the compressed refrigerant via four-way valve 203 to indoor heat exchanger 101 (e.g., Figure 4 (as shown) or outdoor heat exchanger 201 (e.g.) Figure 5 (As shown). Optionally, compressor 202 can be a variable capacity inverter compressor 202 with inverter speed control.

[0092] In some embodiments, the outdoor heat exchanger 201 functions as a condenser or evaporator, and the refrigerant flowing in the outdoor heat exchanger 201 exchanges heat with the outdoor air, which can assist the indoor heat exchanger 101 in achieving cooling or heating. When the outdoor heat exchanger 201 operates as an evaporator, the indoor heat exchanger heats (e.g., Figure 5 (as shown in the diagram); when the outdoor heat exchanger 201 operates as a condenser, the indoor heat exchanger 101 cools (as shown in the diagram). Figure 4 (As shown).

[0093] In some embodiments, one end of the gas-liquid separator 204 is connected to the compressor 202, and the other end is connected to the outdoor heat exchanger 201 (e.g., via a four-way valve) through a four-way valve. Figure 4 (as shown) connected to or connected to indoor heat exchanger 101 (e.g.) Figure 5 (As shown), to accommodate the refrigerant returning to the liquid portion during the refrigerant circulation, preventing liquid slugging of the compressor 202.

[0094] Furthermore, the gas-liquid separator 204 can also deliver the acquired or stored refrigerant to the compressor 202 for compression.

[0095] In some embodiments, the expansion valve 205 is disposed between the indoor heat exchanger 101 and the outdoor heat exchanger 201, and has the effect of expanding the refrigerant flowing through the expansion valve 205 to achieve pressure reduction, thereby regulating the refrigerant flow rate in the refrigerant passage. Optionally, the expansion valve 205 can be an electronic expansion valve.

[0096] The connecting pipe 30 is used to connect the indoor unit 10 and the outdoor unit 20 to form a refrigerant circulation loop, thereby completing the heat exchange between the indoor unit 10 and the indoor air.

[0097] In some embodiments, the temperature sensor 40 is used to detect temperature data at the location of the temperature sensor. For example, the temperature data of the target area can be detected by a temperature sensor within the target area.

[0098] Optionally, there can be multiple temperature sensors 40, which can be installed at the air outlet of the indoor unit 10, at the wired controller, or at other locations.

[0099] For example, such as Figure 6 As shown, a temperature sensor can be installed at the air outlet of the indoor unit 10 to detect the temperature data at the air outlet of the indoor unit 10. Figure 7 As shown, the temperature sensor 40 can be installed at the wired controller to detect temperature data at the wired controller. Figure 8 As shown, the temperature sensor 40 can be placed in office areas, on tables, or on the ground.

[0100] In some embodiments, such as Figure 9 As shown, the indoor heat exchanger 101, outdoor heat exchanger 201, compressor 202, four-way valve 203, gas-liquid separator 204, expansion valve 205, and temperature sensor 40 are electrically connected to the controller 50. The controller is a device that can generate operation control signals based on instruction operation codes and timing signals to instruct the central air conditioning system 1 to execute control commands. For example, the controller can be a central processing unit (CPU), a network processor (NP), a digital signal processor (DSP), a microprocessor, a microcontroller, a programmable logic device (PLD), or any combination thereof. The controller can also be other devices with processing functions, such as circuits, devices, or software modules; this application embodiment does not impose any limitations on this.

[0101] In some embodiments, the controller can be a microcontroller unit (MCU). An MCU, also known as a single-chip microcomputer, is a chip-level computer that integrates a central processing unit (CPU) with appropriately reduced frequency and specifications, along with peripheral interfaces such as memory, timer, USB, A / D converter, UART, PLC, DMA, and even LCD driver circuitry, all onto a single chip. This allows for different combinations of control for various applications.

[0102] In addition, the controller can be used to control the operation of each component in the central air conditioning system 1 so that each component of the central air conditioning system 1 can operate to achieve each predetermined function of the central air conditioning system 1.

[0103] It is understood that the structures illustrated in the embodiments of the present invention do not constitute a specific limitation on the central air conditioning system. In other embodiments of this application, the central air conditioning system may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0104] The embodiments of this application will now be described in detail with reference to the accompanying drawings.

[0105] like Figure 10 As shown in the figure, this application provides a control method for a central air conditioning system, applied to the controller of a central air conditioning system. The method includes the following steps:

[0106] S11, Receive target instructions.

[0107] The target instruction is used to indicate the acquisition of the perceived temperature of the target area. The target area can be one of the multiple perceived temperature detection areas set in the central air conditioning system. The target area can be the area corresponding to the perceived temperature that needs to be acquired in the operation mode of the central air conditioning system, or it can be a specific area selected by the user.

[0108] For example, the target instruction can be an electrical signal.

[0109] S12. In response to the target command, the temperature data of the target area is detected by the temperature sensor.

[0110] The temperature sensor can be one or more, and can be set at different locations in the target area to detect the temperature data at each location in the target area.

[0111] S13. Use the graph attention model to process the temperature data of the target area to obtain the perceived temperature of the target area output by the graph attention model.

[0112] As one possible implementation, the graph attention model is obtained by the controller through the following steps S131-S136:

[0113] S131. Acquire initial temperature data detected by multiple temperature sensors.

[0114] Optionally, multiple temperature sensors can periodically detect temperature data in the area where each temperature sensor is located and store the detected temperature data in the memory of the central air conditioning system. The detected temperature data can be used as sample data for training the graph attention model.

[0115] S132. Preprocess the initial temperature data detected by each temperature sensor to obtain the features of each node in the graph attention model.

[0116] In this model, a temperature sensor corresponds to a node in the graph attention model.

[0117] In some embodiments, step S132 can be specifically implemented as the following steps S1321-S1322:

[0118] S1031. Remove abnormal data from the initial temperature data to obtain intermediate temperature data.

[0119] Abnormal data includes data where the variance at the initial temperature is a preset value, for example, a preset value of 0.

[0120] S1032. Perform z-score normalization on the intermediate temperature data to obtain the features of each node in the graph attention model.

[0121] Among them, z-score standardization is a data processing method that transforms data of different magnitudes into z-score values ​​of the same metric for comparison, thereby standardizing the intermediate temperature data. In this way, by performing z-score standardization on the intermediate data, the intermediate temperature data becomes a node feature matrix that can be used by the graph attention model.

[0122] For example, the z-score normalization of the intermediate temperature data is performed using the following formula to obtain the features of each node in the graph attention model:

[0123]

[0124] In the formula, x represents intermediate temperature data, x′ represents the characteristics of the nodes, and σ represents the standard deviation.

[0125] As can be seen from the above embodiments, there may be abnormal temperature data in the initial temperature data. By removing abnormal data to obtain intermediate temperature data, and then performing z-score standardization on the intermediate temperature data, the intermediate temperature data after the preset processing can meet the learning conditions of the graph attention model.

[0126] S133. Based on the characteristics of each target node and the characteristics of its neighboring nodes, calculate the attention coefficients between the target node and each neighboring node in the graph attention model.

[0127] In this model, the target node is one of the nodes in the graph attention model, and the neighbor node is the node adjacent to the target node in the graph attention model. In the graph attention model, a target node and a neighbor node correspond to an attention coefficient, which is used to characterize the importance of the neighbor node to the target node.

[0128] When node i is the target node and other nodes are neighbor nodes j, the importance of each neighbor node j to the target node i can be reflected by calculating the attention coefficients between the target node i and each neighbor node j. Here, i, j ∈ Ni, and Ni is the set of neighbor nodes j.

[0129] For example, the attention coefficient between the target node and its neighboring nodes can be obtained using the following formula:

[0130]

[0131] Among them, e ij Represents the attention coefficient; 'a' indicates that the graph attention model is a single-layer feedforward neural network; h i h represents the node characteristics of target node i. j Let W be the node characteristics of neighbor node j; W is the weight parameter.

[0132] S134. Normalize the attention coefficients of the target node and its neighboring nodes in the graph attention model.

[0133] As one possible implementation, the attention coefficients between the target node and its neighboring nodes in the graph attention model can be normalized using the following formula:

[0134]

[0135] In the formula, ∝ ij e represents the attention coefficient after normalization. ij Ni represents the attention coefficient; k represents the number of neighboring nodes; and LeakyReLU() is the activation function.

[0136] S135. Based on the normalized attention coefficients, the graph attention model is obtained.

[0137] Optional graph attention models include:

[0138]

[0139] In the formula, h i ′ represents the output feature of the target node in the graph attention model; σ represents the activation function LeakyReLU; ∝ ij h represents the attention coefficient after normalization. j is the node characteristics of neighboring nodes; W is the weight parameter.

[0140] As one possible implementation, the output features of the target node are processed by the softmax activation function to obtain the classification result of the target node. In this way, the predicted perceived temperature corresponding to the target node can be determined based on the classification result of the target node.

[0141] For example, the output features of the target node are divided into 30 categories, namely 10℃, 11℃, 12℃, ..., 40℃, by using the softmax activation function. When the output feature of the target node belongs to the category of 20℃, the predicted perceived temperature of the target node is 20℃.

[0142] As can be seen from the above embodiments, not all initial temperature data detected by multiple temperature sensors can be used for learning the graph attention model. Therefore, the initial temperature data is preprocessed to meet the learning conditions of the graph attention model. In this embodiment, each temperature sensor is used as a node in the graph attention model. Based on the node features of each target node and the node features of its neighbors, the attention coefficients of each target node in the graph attention model are calculated. Then, by normalizing the attention coefficients of each target node in the graph attention model, the graph attention model can be obtained.

[0143] In some embodiments, step S13 above may include the following steps S136-S137:

[0144] S136. Using temperature sensors as nodes, input the temperature processing data of the target area into the graph attention model.

[0145] The number of temperature sensors can be multiple. The temperature processing data of the target area includes the temperature data of the current environment detected by the temperature sensor corresponding to the target node and the temperature data of the current environment detected by the temperature sensors corresponding to adjacent nodes.

[0146] S137. Perform a weighted summation of the features of each node in the target region to obtain the feature fusion result of the target region.

[0147] The features of each node are obtained by performing z-score normalization on the temperature data of the target area.

[0148] For example, the feature fusion result h of the target region i ′ can be obtained through the following formula:

[0149]

[0150] In the formula, σ represents the activation function LeakyReLU; ∝ ij h represents the attention coefficient after normalization. j denoted as , where is the node characteristics of neighboring nodes in the target region; W is the weight parameter.

[0151] For example, such as Figure 11 As shown, node h1 is the target node, and nodes h1, h2, h3, h4, h5, and h6 are neighboring nodes. The attention coefficient α can be obtained through the node features of node h1 and h6. 11 The attention coefficient α can be obtained by analyzing the node features of node h1 and node h2. 12 The attention coefficient α can be obtained by analyzing the node features of node h1 and node h3. 13 The attention coefficient α can be obtained by using the node features of node h1 and node h4. 14 The attention coefficient α can be obtained by using the node features of node h1 and node h5. 15 The attention coefficient α can be obtained by using the node features of node h1 and node h6. 16 By weighted summing of the features of each node, the fusion result h'1 can be obtained.

[0152] S138. The feature fusion result is processed by an activation function to obtain the perceived temperature of the target region.

[0153] For example, the activation function can be the softmax activation function.

[0154] As can be seen from the above embodiments, after obtaining the graph attention model, by inputting the temperature processing data of the target area into the graph attention model, the features of each node in the target area are weighted and summed to obtain the feature fusion result of the target area. After the fusion result is processed by the activation function, the perceived temperature of the target area corresponding to the fusion result can be obtained, thereby realizing the prediction of the perceived temperature of the target area based on the graph attention model.

[0155] In some embodiments, the central air conditioning control method provided in this application further includes the following steps S139-S1310:

[0156] S139. Update the weight parameters through backpropagation.

[0157] As one possible implementation, during the training of the graph attention model, an Adam optimizer that performs backpropagation using the first-order gradient information of the negative log-likelihood loss function is used to calculate the loss value. This loss value is used to characterize the degree of difference between the actual perceived temperature in the sample dataset and the output predicted perceived temperature. When the degree of difference is large, the weight parameters are updated.

[0158] For example, such as Figure 12 As shown, node features are input into the graph attention model, the loss value is calculated based on the Adam optimizer, and the weight parameters are updated through backpropagation.

[0159] S1310. Update the attention coefficients based on the updated weight parameters.

[0160] During the training of the graph attention model, there may be a significant difference between the actual perceived temperature in the sample data and the predicted perceived temperature output, indicating a large error in the predicted perceived temperature processed by the graph attention model. Therefore, the attention coefficients can be updated by updating the weight parameters, thereby making the predicted perceived temperature output by the graph attention model closer to the actual perceived temperature.

[0161] S14. Adjust the operating parameters of the central air conditioning system according to the perceived temperature of the target area.

[0162] For example, in cooling mode, when the perceived temperature of the target area is greater than the preset temperature of the central air conditioning system, the central air conditioning system is controlled to cool.

[0163] Figure 10The illustrated embodiment offers at least the following beneficial effects: Since the user's perceived temperature accurately reflects the comfort level of the central air conditioning system, obtaining the user's perceived temperature is crucial. In related technologies, a temperature compensation value is typically set at the factory, and the sum of the temperature at the air outlet of the central air conditioning system and the temperature compensation value is used as the user's perceived temperature. However, due to varying environments where central air conditioning systems are located, a fixed temperature compensation value often fails to accurately determine the user's actual perceived temperature for different installation environments, room sizes, or sunlight conditions. In this embodiment, upon receiving an instruction to obtain the perceived temperature of a target area, a graph attention model is used to process the temperature data of the target area detected by the temperature sensor, thereby obtaining the perceived temperature of the target area output by the graph attention model. Since the graph attention model is trained based on temperature data samples detected by the temperature sensor, the output perceived temperature of the target area can better match the perceived temperature in the actual environment of the central air conditioning system. Furthermore, adjusting the operating parameters of the central air conditioning system based on the perceived temperature of the target area can improve the comfort level of the central air conditioning system.

[0164] As can be seen, the above mainly describes the solutions provided by the embodiments of this application from a methodological perspective. To achieve the above functions, the embodiments of this application provide corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should readily recognize that, in conjunction with the modules and algorithm steps of the various examples described in the embodiments disclosed herein, the embodiments of this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in a hardware or computer software-driven hardware manner depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this invention.

[0165] This application embodiment can divide the controller into functional modules according to the above method example. For example, each function can be divided into a separate functional module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. Optionally, the module division in this application embodiment is illustrative and only represents one logical functional division; other division methods may be used in actual implementation.

[0166] This application also provides a computer-readable storage medium including computer-executable instructions that, when run on a computer, cause the computer to execute any of the central air conditioning system control methods provided in the above embodiments.

[0167] This application also provides a computer program product containing computer execution instructions, which, when run on a computer, causes the computer to execute any of the central air conditioning system control methods provided in the above embodiments.

[0168] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented using software programs, implementation can be, in whole or in part, in the form of a computer program product. This computer program product includes one or more computer-executable instructions. When these computer-executable instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer-executable instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer-executable instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device containing one or more servers, data centers, etc., that can be integrated with the medium. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state disks, SSDs).

[0169] Although this application has been described herein in conjunction with various embodiments, those skilled in the art, by reviewing the accompanying drawings, disclosure, and appended claims, will understand and implement other variations of the disclosed embodiments in carrying out the claimed application. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude multiple instances. A single processor or other unit can implement several functions listed in the claims. While different dependent claims may recite certain measures, this does not mean that these measures cannot be combined to produce good results.

[0170] Although this application has been described in conjunction with specific features and embodiments, it is obvious that various modifications and combinations can be made thereto without departing from the spirit and scope of this application. Accordingly, this specification and drawings are merely illustrative descriptions of the application as defined by the appended claims, and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from the spirit and scope of this application. Thus, if such modifications and modifications of this application fall within the scope of the claims of this application and their equivalents, this application is also intended to include such modifications and modifications.

[0171] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A central air conditioning system, characterized in that, include: Outdoor heat exchanger; An indoor heat exchanger; wherein, the outdoor heat exchanger and the indoor heat exchanger, one functions as a condenser and the other as an evaporator; A compressor for compressing refrigerant gas and discharging it to the condenser; A four-way valve is used to control the flow direction of refrigerant in the refrigerant circulation loop; The refrigerant circulation loop is used to circulate the refrigerant in the loop consisting of the compressor, the indoor heat exchanger, the expansion valve, the four-way valve, and the outdoor heat exchanger. Temperature sensors are used to detect temperature data in the target area; A controller, electrically connected to the temperature sensor, is configured to: Receive a target instruction, the target instruction being used to instruct the acquisition of the perceived temperature of a target area; In response to the target command, the temperature data of the target area is detected by the temperature sensor; The temperature data of the target area is processed using a graph attention model to obtain the perceived temperature of the target area output by the graph attention model. Adjust the operating parameters of the central air conditioning system according to the perceived temperature of the target area; The graph attention model is obtained by the controller performing the following steps: Acquire initial temperature data detected by multiple temperature sensors; The initial temperature data detected by each of the temperature sensors are preprocessed to obtain the features of each node of the graph attention model; one temperature sensor corresponds to one node of the graph attention model. Based on the characteristics of each target node and the characteristics of its neighboring nodes, the attention coefficients between each target node and each neighboring node in the graph attention model are calculated. The target node is one of the nodes in the graph attention model, and the neighboring node is the node adjacent to the target node in the graph attention model. Each target node and each neighboring node in the graph attention model corresponds to one attention coefficient. The attention coefficients of the target node and its neighboring nodes in the graph attention model are normalized. The graph attention model is obtained based on the normalized attention coefficients; The attention coefficients in the graph attention model are obtained using the following formula: In the formula, The value represents the attention coefficient; 'a' indicates that the graph attention model is a single-layer feedforward neural network. The node characteristics of the target node. denoted as , where is the node characteristic of the neighboring node; W is the weight parameter.

2. The central air conditioning system according to claim 1, characterized in that, The controller is also configured to: The weight parameters are updated via backpropagation; The attention coefficients are updated based on the updated weight parameters.

3. The central air conditioning system according to any one of claims 1-2, characterized in that, The controller executes the processing of temperature data of the target area using a graph attention model to obtain the perceived temperature of the target area output by the graph attention model, specifically configured as follows: Using the temperature sensor as a node, the temperature processing data of the target area is input into the graph attention model; The features of each node in the target region are weighted and summed to obtain the feature fusion result of the target region. The feature fusion result is processed by an activation function to obtain the perceived temperature of the target region.

4. The central air conditioning system according to claim 1, characterized in that, The controller performs preprocessing on the initial temperature data detected by each of the temperature sensors to obtain the features of each node in the graph attention model, specifically configured as follows: Abnormal data is removed from the initial temperature data detected by each of the temperature sensors to obtain intermediate temperature data. The abnormal data includes data with a variance of a preset value. The intermediate temperature data is z-score normalized to obtain the features of each node in the graph attention model.

5. The central air conditioning system according to claim 4, characterized in that, The controller performs z-score normalization on the intermediate temperature data using the following formula to obtain the features of each node in the graph attention model: In the formula, x represents the intermediate temperature data. The characteristics of the node. The standard deviation is denoted as .

6. A control method for a central air conditioning system, characterized in that, The central air conditioning system includes: Outdoor heat exchanger; An indoor heat exchanger; wherein, the outdoor heat exchanger and the indoor heat exchanger, one functions as a condenser and the other as an evaporator; A compressor for compressing refrigerant gas and discharging it to the condenser; A four-way valve is used to control the flow direction of refrigerant in the refrigerant circulation loop; The refrigerant circulation loop is used to circulate the refrigerant in the loop consisting of the compressor, the indoor heat exchanger, the expansion valve, the four-way valve, and the outdoor heat exchanger. Temperature sensors are used to detect temperature data in the target area; The method includes: Receive a target instruction, the target instruction being used to instruct the acquisition of the perceived temperature of a target area; In response to the target command, the temperature data of the target area is detected by the temperature sensor; The temperature data of the target area is processed using a graph attention model to obtain the perceived temperature of the target area output by the graph attention model. Adjust the operating parameters of the central air conditioning system according to the perceived temperature of the target area; The graph attention model is obtained through the following steps: Acquire initial temperature data detected by multiple temperature sensors; The initial temperature data detected by each of the temperature sensors are preprocessed to obtain the features of each node of the graph attention model; one temperature sensor corresponds to one node of the graph attention model. Based on the characteristics of each target node and the characteristics of its neighboring nodes, the attention coefficients between each target node and each neighboring node in the graph attention model are calculated. The target node is one of the nodes in the graph attention model, and the neighboring node is the node adjacent to the target node in the graph attention model. Each target node and each neighboring node in the graph attention model corresponds to one attention coefficient. The attention coefficients of the target node and its neighboring nodes in the graph attention model are normalized. The graph attention model is obtained based on the normalized attention coefficients; The attention coefficients in the graph attention model are obtained using the following formula: In the formula, The value represents the attention coefficient; 'a' indicates that the graph attention model is a single-layer feedforward neural network. The node characteristics of the target node. denoted as , where is the node characteristic of the neighboring node; W is the weight parameter.

7. The method according to claim 6, characterized in that, The process of using a graph attention model to process the temperature data of the target region to obtain the perceived temperature of the target region output by the graph attention model is specifically configured as follows: Using the temperature sensor as a node, the temperature processing data of the target area is input into the graph attention model; The features of each node in the target region are weighted and summed to obtain the feature fusion result of the target region. The feature fusion result is processed by an activation function to obtain the perceived temperature of the target region.

Images