Air conditioner and operation control method thereof

Abstract

The invention discloses an air conditioner and an operation control method thereof, the air conditioner comprises an indoor unit, an outdoor unit and a controller, and an indoor heat exchanger and an indoor fan are arranged in the indoor unit; an outdoor heat exchanger, an outdoor fan, a compressor, a throttling assembly and a four-way valve are arranged in the outdoor unit; the controller is configured to obtain climate data of a region where a user is located and historical use data of the user and perform data preprocessing; and the preprocessed data are input into a preset air conditioner operation parameter recommendation model, the optimal air conditioner operation parameters output by the model are obtained, and the air conditioner is controlled to operate according to the optimal air conditioner operation parameters. Analysis and prediction are carried out based on a large amount of historical data, meanwhile, the model parameters are continuously optimized according to the personalized requirements of the user, it is ensured that the user can enjoy the optimal air conditioner experience in different regional environments by intelligently recommending and dynamically adjusting the optimal operation parameters of the air conditioner, manual intervention of the user is not needed, and the user experience is improved. And the comfort and satisfaction of the user are greatly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of air conditioners, and particularly to an air conditioner and its operation control method. Background Art

[0002] With the improvement of people's living standards, air conditioners have become essential electrical appliances in places such as homes and offices. However, due to factors such as regional differences and climate characteristics, there are significant differences in the usage requirements of air conditioners in different regions. Although the air conditioners on the current market have complete functions, they cannot automatically adjust the operation mode according to the user's location, resulting in a poor user experience. In the prior art, the control methods of air conditioners mainly include manual control and intelligent control. The manual control method requires the user to adjust the operation parameters of the air conditioner according to actual needs, which is cumbersome to operate and easily causes energy waste. Although the intelligent control method can automatically adjust the operation parameters of the air conditioner according to the indoor and outdoor environment, it cannot be optimized for the climate characteristics of different regions, restricting the applicability of the air conditioner in different regions. Summary of the Invention

[0003] The present invention provides an air conditioner and its operation control method, which analyzes and predicts based on a large amount of historical data, and continuously optimizes the model parameters according to the personalized needs of users. By intelligent recommendation and dynamic adjustment of the best operation parameters of the air conditioner, it ensures that users can enjoy the best air conditioning experience in different regional environments without manual intervention by the user, greatly improving the comfort and satisfaction of users.

[0004] The air conditioner provided in the first embodiment of the present invention includes:

[0005] An indoor unit, which is provided with an indoor heat exchanger and an indoor fan;

[0006] An outdoor unit, which is provided with an outdoor heat exchanger, an outdoor fan, a compressor, a throttling component and a four-way valve. The compressor, the throttling component, the four-way valve, the outdoor heat exchanger and the indoor heat exchanger are connected through pipelines to form a refrigerant circulation loop;

[0007] The controller is configured to obtain the climate data of the user's location and the user's historical usage data, and preprocess the climate data and the historical usage data; wherein, the climate data includes temperature data, humidity data, season data and regional data; input the preprocessed climate data and historical usage data into a preset air conditioner operation parameter recommendation model to obtain the best air conditioner operation parameters output by the air conditioner operation parameter recommendation model; control the operation of the air conditioner according to the best air conditioner operation parameters.

[0008] In the air conditioner provided by the second embodiment of the present invention, the preprocessing of the climate data and the historical usage data specifically includes:

[0009] Perform data cleaning on the climate data and the historical usage data;

[0010] Check the validity of the climate data and the historical usage data, verify and correct the error data, and replace the null data with the historical mean value.

[0011] In the air conditioner provided by the third embodiment of the present invention, the training process of the air conditioner operating parameter recommendation model includes:

[0012] Obtain sample data, where the sample data includes climate data, the optimal air conditioner operating parameters corresponding to the climate data, and historical usage data;

[0013] Construct a BP neural network model, input the sample data into the BP neural network model, and obtain the predicted value output by the BP neural network model;

[0014] Calculate the error between the predicted value and the true value, and perform error iterative calculation and optimize the network weights and thresholds of the error function through neural network backpropagation until the minimum value of the error function is reached, and obtain the trained air conditioner operating parameter recommendation model.

[0015] In the air conditioner provided by the fourth embodiment of the present invention, the controller is further configured to:

[0016] Compare the optimal air conditioner operating parameters output by the air conditioner operating parameter recommendation model with the air conditioner operating parameters set by the user;

[0017] If the difference between the optimal air conditioner operating parameters and the air conditioner operating parameters set by the user is less than the preset threshold, control the air conditioner to operate with the air conditioner operating parameters set by the user;

[0018] If the difference between the optimal air conditioner operating parameters and the air conditioner operating parameters set by the user is not less than the preset threshold, use the air conditioner operating parameters set by the user as new sample data to train the air conditioner operating parameter recommendation model.

[0019] In the air conditioner provided by the fifth embodiment of the present invention, the air conditioner operating parameter recommendation model includes an input layer, a hidden layer, and an output layer connected in sequence; among them, in the input layer, the hidden layer, and the output layer, each neuron in adjacent layers is fully connected, and there is no connection between neurons in each layer; the activation function of the hidden layer is the Sigmoid function, and the error function of the air conditioner operating parameter recommendation model is the mean square error.

[0020] In the sixth embodiment of the present invention, the air conditioner operation control method provided is applied to an air conditioner including an indoor heat exchanger, an indoor fan, an outdoor heat exchanger, an outdoor fan, a compressor, a throttling component, and a four-way valve. The air conditioner operation control method includes:

[0021] Obtain the climate data of the user's location and the user's historical usage data, and preprocess the climate data and the historical usage data; wherein, the climate data includes temperature data, humidity data, season data, and regional data;

[0022] Input the preprocessed climate data and historical usage data into a preset air conditioner operation parameter recommendation model to obtain the optimal air conditioner operation parameters output by the air conditioner operation parameter recommendation model;

[0023] Control the operation of the air conditioner according to the optimal air conditioner operation parameters.

[0024] In the air conditioner operation control method provided in the seventh embodiment of the present invention, the preprocessing of the climate data and the historical usage data specifically includes:

[0025] Perform data cleaning on the climate data and the historical usage data;

[0026] Check the validity of the climate data and the historical usage data, check and correct the error data, and replace the null data with the historical mean value.

[0027] In the air conditioner operation control method provided in the eighth embodiment of the present invention, the training process of the air conditioner operation parameter recommendation model includes:

[0028] Obtain sample data, wherein the sample data includes climate data, the optimal air conditioner operation parameters corresponding to the climate data, and historical usage data;

[0029] Construct a BP neural network model, input the sample data into the BP neural network model, and obtain the predicted value output by the BP neural network model;

[0030] Calculate the error between the predicted value and the true value, and perform error iterative calculation and optimize the network weights and thresholds of the error function through neural network backpropagation until the minimum value of the error function is reached, and obtain the trained air conditioner operation parameter recommendation model.

[0031] In the air conditioner operation control method provided in the ninth embodiment of the present invention, the method further includes:

[0032] Compare the optimal air conditioner operating parameters output by the air conditioner operating parameter recommendation model with the air conditioner operating parameters set by the user;

[0033] If the difference between the optimal air conditioner operating parameters and the air conditioner operating parameters set by the user is less than a preset threshold, control the air conditioner to operate with the air conditioner operating parameters set by the user;

[0034] If the difference between the optimal air conditioner operating parameters and the air conditioner operating parameters set by the user is not less than the preset threshold, use the air conditioner operating parameters set by the user as new sample data to train the air conditioner operating parameter recommendation model.

[0035] In the air conditioner operation control method provided in the tenth embodiment of the present invention, the air conditioner operation parameter recommendation model includes an input layer, a hidden layer, and an output layer connected in sequence; wherein, in the input layer, the hidden layer, and the output layer, each neuron in adjacent layers is fully connected, and there is no connection between neurons in each layer; the activation function of the hidden layer is the Sigmoid function, and the error function of the air conditioner operation parameter recommendation model is the mean square error.

[0036] Compared with the prior art, the beneficial effects of an air conditioner and its operation control method provided in the embodiments of the present invention are as follows: by obtaining the climate data of the user's location and the user's historical usage data, and preprocessing the climate data and the historical usage data; wherein, the climate data includes temperature data, humidity data, season data, and region data; input the preprocessed climate data and historical usage data into a pre-trained air conditioner operation parameter recommendation model to obtain the optimal air conditioner operation parameters output by the air conditioner operation parameter recommendation model, and control the air conditioner to operate with the optimal air conditioner operation parameters. The embodiments of the present invention perform analysis and prediction based on a large amount of historical data, and continuously optimize the model parameters according to the personalized needs of users. By intelligently recommending and dynamically adjusting the optimal operation parameters of the air conditioner, it is ensured that users can enjoy the best air conditioning experience in different geographical environments without manual intervention by users, greatly improving the comfort and satisfaction of users. Description of the Drawings

[0037] Figure 1 is a three-dimensional external view of an air conditioner provided in an embodiment of the present invention;

[0038] Figure 2 is a schematic structural diagram of an air conditioner provided in an embodiment of the present invention;

[0039] Figure 3 is a schematic diagram of a refrigerant circulation circuit of an air conditioner provided in an embodiment of the present invention;

[0040] Figure 4 It is the first working flowchart of a controller in an air conditioner provided by an embodiment of the present invention;

[0041] Figure 5 It is the second working flowchart of a controller in an air conditioner provided by an embodiment of the present invention;

[0042] Figure 6 It is a schematic diagram of the relationship between temperature data and air conditioner operation parameters in an air conditioner provided by an embodiment of the present invention;

[0043] Figure 7 It is a schematic diagram of the relationship between humidity data and air conditioner operation parameters in an air conditioner provided by an embodiment of the present invention;

[0044] Figure 8 It is the third working flowchart of a controller in an air conditioner provided by an embodiment of the present invention;

[0045] Figure 9 It is a schematic diagram of the structure of an air conditioner operation parameter recommendation model in an air conditioner provided by an embodiment of the present invention;

[0046] Figure 10 It is a schematic flowchart of an operation control method for an air conditioner provided by an embodiment of the present invention. Detailed implementation manners

[0047] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0048] In the description of the present application, it should be understood that the orientation or positional relationship indicated by the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the accompanying drawings, and is only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation to the present application.

[0049] The terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present application, unless otherwise stated, the meaning of "a plurality" is two or more.

[0050] In the description of the present application, it should be noted that unless otherwise clearly specified and defined, the terms "installed", "connected", and "coupled" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific circumstances.

[0051] Please refer to Figures 1 to 2 , Figure 1 which is a perspective view of the appearance of an air conditioner provided by an embodiment of the present invention, Figure 2 and which is a schematic structural view of an air conditioner provided by an embodiment of the present invention. The air conditioner 1 provided in the embodiment of the present invention includes:

[0052] An indoor unit 2, which is internally provided with an indoor heat exchanger 21 and an indoor fan 22;

[0053] An outdoor unit 3, which is internally provided with an outdoor heat exchanger 31, an outdoor fan 32, a compressor 33, a throttling component 34, and a four-way valve 35. The compressor 33, the throttling component 34, the four-way valve 35, the outdoor heat exchanger 31, and the indoor heat exchanger 21 are connected through pipelines to form a refrigerant circulation loop;

[0054] The indoor heat exchanger 21 is used to act as an evaporator or a condenser according to the operating state of the indoor unit, so as to perform heat exchange between the refrigerant flowing in the heat transfer tubes and the air passing through the indoor heat exchanger;

[0055] The outdoor heat exchanger 31 is used to act as a condenser or an evaporator according to the operating state of the outdoor unit, so as to perform heat exchange between the refrigerant flowing in the heat transfer tubes and the air passing through the outdoor heat exchanger;

[0056] The compressor 33 is used to compress the refrigerant into a high-temperature and high-pressure gas;

[0057] The throttling component 34 is used to turn the medium-temperature and high-pressure liquid after the outdoor heat exchanger absorbs and releases heat into a low-temperature and low-pressure liquid;

[0058] The four-way valve 35 is used to realize the conversion between refrigeration and heating by changing the flow direction of the refrigerant in the circulation loop;

[0059] The controller is configured to obtain the climate data of the user's location and the user's historical usage data, and preprocess the climate data and the historical usage data; wherein, the climate data includes temperature data, humidity data, season data, and regional data; input the preprocessed climate data and historical usage data into a preset air conditioner operation parameter recommendation model to obtain the optimal air conditioner operation parameters output by the air conditioner operation parameter recommendation model; and control the operation of the air conditioner according to the optimal air conditioner operation parameters.

[0060] Specifically, in the embodiment of the present invention, the air conditioner 1 includes an indoor unit 2. Taking an indoor hanging unit (shown in the figure) as an example, the indoor hanging unit is usually installed on an indoor wall surface or the like. Again, an indoor cabinet unit (not shown in the figure) is also a form of the indoor unit. An outdoor unit 3, which is usually arranged outdoors and is used for heat exchange of the indoor environment. In addition, Figure 1 As shown, since the outdoor unit 3 is located outdoors on the opposite side of the wall surface from the indoor unit 2, the outdoor unit 3 is represented by a dashed line. The indoor unit 2 and the outdoor unit 3 are connected by a connecting pipe 4. Among them, the indoor unit 2 is provided with an indoor heat exchanger 21 and an indoor fan 22. When the air conditioner is in the cooling mode, the indoor heat exchanger 21 operates as an evaporator. The indoor heat exchanger 21 functions as an evaporator or a radiator according to the operating state of the indoor unit, so that heat exchange occurs between the refrigerant flowing in the heat transfer pipe and the air passing through the indoor heat exchanger. The indoor fan 22 generates an air flow of the indoor air passing through the indoor heat exchanger 21 to promote the heat exchange between the refrigerant flowing in the heat transfer pipe of the indoor heat exchanger 21 and the indoor air. The outdoor unit 3 is provided with an outdoor heat exchanger 31, an outdoor fan 32, a compressor 33, a throttling component (i.e., a flow regulating valve) 34, and a four-way valve 35. When the air conditioner is in the cooling mode, the outdoor heat exchanger 31 operates as a condenser. The outdoor fan 32 generates an air flow of the outdoor air passing through the outdoor heat exchanger 31 to promote the heat exchange between the refrigerant flowing in the heat transfer pipe of the outdoor heat exchanger 31 and the outdoor air.

[0061] Please refer to Figure 3 , Figure 3It is a schematic diagram of a refrigerant circulation circuit of an air conditioner provided by an embodiment of the present invention. A compressor 33, a throttling component 34, a four-way valve 35, an outdoor heat exchanger 31, and an indoor heat exchanger 21 are connected by pipelines to form a refrigerant circulation circuit. When the air conditioner is in the cooling mode, the indoor heat exchanger 21 and the outdoor heat exchanger 31 are respectively used as an evaporator and a condenser to operate. The refrigerant is compressed by the compressor to be converted into a high-temperature and high-pressure gas, enters the outdoor heat exchanger of the outdoor unit through the four-way valve, becomes a medium-temperature and high-pressure liquid after absorbing cold and releasing heat in the outdoor heat exchanger, becomes a low-temperature and low-pressure liquid after passing through the flow regulating valve, becomes a low-temperature and low-pressure gas after the heat absorption and heat release effect of the indoor heat exchanger of the indoor unit, returns to the compressor through the four-way valve, and then continues to circulate. By circulating the refrigerant in the refrigerant circuit, a vapor compression refrigeration cycle can be executed. Among them, the flow regulating valve can change the opening degree. By reducing the opening degree, the flow path resistance of the refrigerant passing through the flow regulating valve increases; by increasing the opening degree, the flow path resistance of the refrigerant passing through the flow regulating valve decreases. Such a flow regulating valve expands and decompresses the refrigerant flowing from the indoor heat exchanger towards the outdoor heat exchanger during the cooling operation. In addition, even when the states of other devices installed in the refrigerant circuit do not change, when the opening degree of the flow regulating valve changes, the flow rate of the refrigerant flowing in the refrigerant circuit also changes.

[0062] Please refer to Figure 4 , Figure 4It is the first working flowchart of a controller in an air conditioner provided by an embodiment of the present invention. It should be noted that the optimal air conditioner operating parameters can not only improve the user's comfort, but also reduce energy consumption. Therefore, the optimal air conditioner operating parameters are affected by various factors and change dynamically with the external environment. Usually, users in different regions have different usage habits and are also affected by the climate data of the region, including information such as temperature, humidity, season, and region. Since traditional air conditioner control methods usually do not have regional adaptability and cannot automatically adjust operating parameters or operating modes according to the climate characteristics of the user's location. Therefore, the embodiment of the present invention uses a neural network algorithm to analyze a large amount of climate data and the user's historical usage data, establishes a neural network model between the climate data and the optimal air conditioner operating parameters through user behavior learning and preference analysis, and continuously optimizes the model according to the user's usage habits. The optimal air conditioner operating parameters are intelligently recommended for the user through the neural network model, realizing the regional adaptive control of the air conditioner, reducing the complexity of user operation, meeting the needs and usage experiences of different users, and improving the user's comfort. Specifically, the embodiment of the present invention obtains the climate data of the user's location and the user's historical usage data, and preprocesses the climate data and the historical usage data. Among them, the climate data includes temperature data, humidity data, season data, and regional data. Exemplarily, the embodiment of the present invention integrates a GPS module in the air conditioner, sends the longitude and latitude information of the user's location to the cloud server through the network, and the server queries the corresponding climate data according to the longitude and latitude information. The user's historical usage data includes the temperature, humidity, mode, and wind speed set by the user. Then, the preprocessed climate data and historical usage data are input into a pre-trained air conditioner operating parameter recommendation model, and the optimal air conditioner operating parameters output by the air conditioner operating parameter recommendation model are obtained. According to the optimal air conditioner operating parameters, the air conditioner is controlled to operate with the optimal air conditioner operating parameters.

[0063] As one optional embodiment, the preprocessing of the climate data and the historical usage data specifically includes:

[0064] Performing data cleaning on the climate data and the historical usage data;

[0065] Checking the validity of the climate data and the historical usage data, checking and correcting the error data, and replacing the null data with the historical mean.

[0066] Specifically, after obtaining the climate data of the user's location and the user's historical usage data, the embodiments of the present invention perform data preprocessing on these data. First, the data is cleaned. For example, possible error values or outliers are identified through statistical analysis methods, and data values can also be checked using a simple rule base (common sense rules, business-specific rules, etc.), or the constraints between different attributes and external data are used to detect and clean the data. Secondly, during the data preprocessing process, the validity of the data is checked, including error data processing and null data processing. The error data is verified and corrected, and the null data is replaced with the historical mean value to complete the correction of invalid data, thereby screening out samples that meet the model training requirements and improving the data reliability.

[0067] As one of the optional embodiments, the training process of the air conditioner operation parameter recommendation model includes:

[0068] Obtain sample data, where the sample data includes climate data, the optimal air conditioner operation parameters corresponding to the climate data, and historical usage data;

[0069] Construct a BP neural network model, input the sample data into the BP neural network model, and obtain the predicted value output by the BP neural network model;

[0070] Calculate the error between the predicted value and the true value, and perform error iterative calculation and optimize the network weights and thresholds of the error function through the backpropagation of the neural network until the minimum value of the error function is reached, and obtain the trained air conditioner operation parameter recommendation model.

[0071] Specifically, please refer to Figure 5 , Figure 5 FIG. is the second working flowchart of a controller in an air conditioner provided by an embodiment of the present invention. When training the air conditioner operation parameter recommendation model in the embodiments of the present invention, sample data is first obtained, where the sample data includes climate data, the optimal air conditioner operation parameters corresponding to the climate data, and historical usage data. It should be noted that the sample data is pre-obtained through an impact factor analysis of the climate data that affects the air conditioner operation parameters, and the obtained climate data and the optimal air conditioner operation parameters corresponding to the climate data are subjected to data preprocessing, such as data cleaning and checking the validity of the data, verifying and correcting the error data, and replacing the null data with the historical mean value. Exemplarily, the optimal air conditioner operation parameters are mainly affected by factors such as temperature, humidity, season, and geographical location.

[0072] 1. Temperature: When the external temperature is relatively high, the air conditioner needs to set a lower indoor target temperature to provide a cooling effect; when the external temperature is relatively low, the air conditioner may need to heat, so the target temperature will be set higher. The specific solutions are as follows. For example,Figure 6 As shown Figure 6 is a schematic diagram showing the relationship between temperature data and the operating parameters of an air conditioner provided in an embodiment of the present invention:

[0073] Below - 5°C: The outside temperature is very low, and the indoor needs to be kept warm. Recommended air conditioner set temperature: 25°C to 26°C.

[0074] -5°C to 0°C: The outside temperature is very low, and the indoor needs to be kept relatively warm. Recommended air conditioner set temperature: 24°C to 26°C.

[0075] 0°C to 5°C: It is still relatively cold, but slightly warmer than the previous range. Recommended air conditioner set temperature: 23°C to 25°C.

[0076] 5°C to 10°C: The outside temperature begins to approach the human comfort zone, but the indoor still needs to be kept warm. Recommended air conditioner set temperature: 22°C to 24°C.

[0077] 10°C to 15°C: Relatively mild spring or autumn weather. Recommended air conditioner set temperature: 21°C to 23°C.

[0078] 15°C to 20°C: Close to the human comfort temperature, but may still require slight heating or maintaining a stable indoor temperature. Recommended air conditioner set temperature: 20°C to 22°C.

[0079] 20°C to 25°C: Comfortable outdoor temperature, and the indoor may not require heating or only slight cooling. Recommended air conditioner set temperature: 20°C to 22°C.

[0080] 25°C to 30°C: It starts to feel hot and cooling is required. Recommended air conditioner set temperature: 22°C to 24°C.

[0081] 30°C to 35°C: Extremely hot, and strong cooling effect is required. Recommended air conditioner set temperature: 22°C to 23°C.

[0082] Above 35°C: Extreme high temperature, and maximum cooling effect is required. Recommended air conditioner set temperature: Try to keep it around 22°C, but also consider the balance between energy conservation and comfort.

[0083] 2. Humidity: In an environment with high humidity, the air conditioner needs to turn on the dehumidification function to reduce the indoor humidity and improve comfort; in an environment with low humidity, the dehumidification function may not need to be turned on to avoid excessive dryness. The specific solutions are as follows, as Figure 7 shown Figure 7 is a schematic diagram showing the relationship between humidity data and the operating parameters of an air conditioner provided in an embodiment of the present invention:

[0084] 0% to 30%: Too low humidity may cause dry skin, throat discomfort and static electricity problems. Recommended air conditioner humidity setting: Try to increase the humidity to between 30% and 40%.

[0085] 30% to 40%: Relatively dry, but still within the comfortable range. Recommended air conditioner humidity setting: Maintain the current humidity or slightly increase it to around 40%.

[0086] 40% to 50%: Ideal humidity range, which helps to maintain the comfort of the indoor environment. Recommended air conditioner humidity setting: Maintain the current humidity.

[0087] 50% to 60%: Still comfortable, but close to the upper limit. Attention needs to be paid to preventing mold growth. Recommended air conditioner humidity setting: Maintain the current humidity or slightly reduce it to around 50%.

[0088] 60% to 70%: Higher humidity may cause mold growth, odors and discomfort. Recommended air conditioner humidity setting: Reduce the humidity to between 50% and 60%.

[0089] 70% to 80%: Very humid, active dehumidification is required. Recommended air conditioner humidity setting: Quickly reduce the humidity below 60%.

[0090] 80% to 100%: Extremely humid, which may cause serious mold problems and deterioration of the indoor environment. Recommended air conditioner humidity setting: Immediately take measures to dehumidify and reduce the humidity below 60%.

[0091] 3. Season: In summer, the air conditioner mainly operates in the cooling mode, while in winter, the heating mode may be required; in spring and autumn, the outdoor temperature is relatively suitable, and the air conditioner may use the energy-saving mode more, saving energy by natural ventilation or reducing the compressor operation time. The specific solutions are as follows:

[0092] (1). Spring

[0093] Temperature: Keep between 20°C and 24°C.

[0094] Humidity: Control between 40% and 60%.

[0095] Wind speed: Select medium speed (2 - 4m / s), which can provide sufficient air flow without causing too strong a cold air feeling.

[0096] (2). Summer

[0097] Temperature: Set between 24°C and 26°C.

[0098] Humidity: Control between 50% and 60%.

[0099] Wind speed: Select medium or high speed (4 - 6 m / s). High-speed wind can reduce the indoor temperature faster, but be careful to avoid direct blowing for a long time to prevent discomfort.

[0100] (3), Autumn

[0101] Temperature: Maintain between 20°C and 24°C.

[0102] Humidity: Control between 40% and 50%.

[0103] Wind speed: Select low speed (1 - 2 m / s) or medium speed (2 - 4 m / s) to keep the indoor air circulating while avoiding a strong cold wind feeling.

[0104] (4), Winter

[0105] Temperature: Set between 18°C and 22°C.

[0106] Humidity: Control between 30% and 50%.

[0107] Wind speed: Select low speed (1 - 2 m / s), which can not only provide appropriate air flow but also avoid cold wind directly blowing on the body, causing discomfort.

[0108] 4. Geographical location: Different regions have different climate characteristics and user habits. For example, in the Yangtze River and Huaihe River regions, there will be a plum rain season, and the air conditioner needs to strengthen the dehumidification function to reduce the indoor humidity and avoid problems such as clothes not drying easily and furniture getting moldy due to high humidity. Due to its special terrain, the Sichuan Basin has a significant wet and cold climate in winter, and the air conditioner needs to provide both heating and dehumidification functions to increase the indoor temperature and reduce the humidity to create a comfortable indoor environment. The specific solutions are as follows:

[0109] (1), The middle and lower reaches of the Yangtze River and the areas south of it

[0110] ①. The Yangtze River Delta and the surrounding areas of Taihu Lake (Shanghai, southern Jiangsu, northern Zhejiang)

[0111] Summer: Temperature 24°C to 26°C, humidity controlled between 45% and 55%, medium wind speed, mode: cooling + dehumidification. Since this area has high temperature and high humidity in summer, it is necessary to strengthen the cooling and dehumidification effects while keeping the air circulating.

[0112] Winter: Temperature 18°C to 22°C, humidity controlled between 40% and 50%, low wind speed, mode: heating. It is relatively warm in winter, but the humidity is high, so it is necessary to heat appropriately and keep the indoor humidity suitable.

[0113] ②. The Pearl River Delta and the Pearl River Basin (central and southern Guangdong, Hong Kong, Macau)

[0114] Summer: Temperature ranges from 26°C to 28°C, humidity is controlled between 50% and 60%, wind speed is medium or high, and the mode is cooling + dehumidification + ventilation. This area is hot and humid in summer, so the cooling and dehumidification effects need to be enhanced, while maintaining air circulation to prevent mold growth.

[0115] Winter: Temperature ranges from 20°C to 24°C, humidity is controlled at about 50%, wind speed is low, and the mode is heating + ventilation. This area is warm and humid in winter, so appropriate heating is needed while keeping the indoor air fresh.

[0116] ③. Southeast coastal areas (coastal areas of southern Fujian and Zhejiang)

[0117] Summer: Temperature ranges from 24°C to 26°C, humidity is controlled between 45% and 55%, wind speed is medium or high, and the mode is cooling + dehumidification + ventilation. This area has many typhoons and heavy rains in summer, so the dehumidification and ventilation functions of the air conditioning system need to be enhanced to prevent indoor humidity and mold growth.

[0118] Winter: Temperature ranges from 18°C to 22°C, humidity is controlled at about 45%, wind speed is low, and the mode is heating. This area is warm and humid in winter, so appropriate heating is needed while keeping the indoor humidity appropriate.

[0119] (2) Areas along the Yellow River and northward

[0120] ①. Middle and lower reaches of the Yellow River (Henan, Shandong, etc.)

[0121] Summer: Temperature ranges from 24°C to 26°C, humidity is controlled between 40% and 50%, wind speed is medium, and the mode is cooling. This area is hot and dry in summer, so the cooling effect needs to be enhanced while keeping the indoor air humidity appropriate.

[0122] Winter: Temperature ranges from 16°C to 20°C, humidity is controlled between 35% and 45%, wind speed is low, and the mode is heating + humidification. This area is cold and dry in winter, so the heating effect needs to be enhanced while appropriately humidifying to keep the indoor humidity appropriate.

[0123] ②. North China Plain and Beijing-Tianjin-Tangshan area

[0124] Summer: Temperature ranges from 24°C to 26°C, humidity is controlled between 35% and 45%, wind speed is medium, and the mode is cooling + ventilation. This area is hot and dry in summer, so the cooling effect needs to be enhanced while keeping the indoor air circulating to prevent indoor dryness.

[0125] Winter: Temperature ranges from 18°C to 22°C (slightly higher in the north), humidity is controlled between 35% and 45%, wind speed is low, and the mode is heating + humidification. This area is cold and dry in winter, so the heating effect needs to be enhanced while appropriately humidifying to keep the indoor humidity appropriate.

[0126] ③. Northeast region (Liaoning, Jilin, Heilongjiang)

[0127] Summer: Temperature is 24°C to 26°C, humidity is controlled between 30% and 40%, wind speed is medium, and the mode is cooling (less needed). The summer in this area is short and cool, and the heating demand is not high, but cooling can be appropriately carried out to keep the indoor cool.

[0128] Winter: Temperature is 20°C to 24°C (higher in the north), humidity is controlled between 30% and 40%, wind speed is low, and the mode is heating + humidifying. Winter is cold and the air is dry. It is necessary to strengthen the heating effect and appropriately humidify at the same time to keep the indoor humidity appropriate.

[0129] (3), Areas around mountains and plateaus

[0130] ①. Qinghai-Tibet Plateau region (Tibet, Qinghai, etc.)

[0131] Summer: Temperature is 18°C to 22°C, humidity is controlled between 30% and 40%, wind speed is medium, and the mode is cooling (if needed). This area has a high altitude, thin air and is dry. Summer is relatively cool, but cooling can be appropriately carried out according to needs.

[0132] Winter: Temperature is adjusted according to altitude and specific regions (generally lower), humidity is controlled at about 30%, wind speed is low, and the mode is heating + humidifying. Winter is cold and dry. It is necessary to strengthen the heating effect and appropriately humidify at the same time to keep the indoor humidity appropriate.

[0133] ②. Areas around Yunnan-Guizhou Plateau and Sichuan Basin

[0134] Summer: Temperature is 24°C to 26°C (may be slightly higher in Sichuan Basin), humidity is controlled between 45% and 60% (may be higher in Sichuan Basin), wind speed is medium, and the mode is cooling + dehumidifying (strengthened in Sichuan Basin). This area has much rain and is humid in summer. It is necessary to strengthen the cooling and dehumidifying effects and keep the indoor air circulating at the same time.

[0135] Winter: Temperature is 16°C to 20°C, humidity is controlled between 45% and 55% (may be slightly higher in Sichuan Basin), wind speed is low, and the mode is heating. Winter is relatively warm and humid. It is necessary to appropriately heat and keep the indoor humidity appropriate at the same time.

[0136] ③. Qinling Mountains and surrounding areas

[0137] Summer: Temperature is 24°C to 26°C, humidity is controlled between 40% and 50%, wind speed is medium, and the mode is cooling. This area is hot but not humid in summer. It is necessary to strengthen the cooling effect and keep the indoor air humidity appropriate at the same time.

[0138] Winter: Temperature is 16°C to 20°C, humidity is controlled between 40% and 50%, wind speed is low, and the mode is heating. Winter is cold but not dry. It is necessary to appropriately heat and keep the indoor humidity appropriate at the same time.

[0139] (4) Influence of other regional characteristics:

[0140] ① Influence of mountains: Areas near mountains may be affected by terrain and climate, such as differences between windward and leeward slopes, valley winds, etc. The air conditioner settings need to be adjusted according to specific situations. For example, in windward slope areas, it may be rainy and humid in summer, and the dehumidification function needs to be strengthened; in leeward slope areas, it may be relatively dry, and appropriate humidification is required.

[0141] ② Influence of rivers: Areas around rivers may be affected by water vapor, with relatively high air humidity, and the dehumidification function needs to be strengthened; at the same time, rivers may also bring a certain cooling effect, and the cooling temperature can be appropriately reduced in summer.

[0142] ③ Altitude: In plateau areas, the air is thin and the oxygen content is low. The air supply mode or fresh air function needs to be turned on. At the same time, the temperature change in plateau areas is relatively large, and the air conditioner settings need to be adjusted according to altitude and seasonal changes.

[0143] ④ Vegetation coverage: Areas with dense vegetation may have relatively high air humidity, and the dehumidification function needs to be strengthened; while areas with sparse vegetation may be relatively dry, and appropriate humidification is required.

[0144] After obtaining the sample data, a BP neural network model is constructed. The sample data is input into the BP neural network model, and the predicted values output by the BP neural network model are obtained. It should be noted that here the sample data can be divided into a training set and a test set according to a preset ratio. For example, 70% of the sample data is used as the training set, and 30% is used as the test set. The BP neural network model is trained according to the climate data and the optimal air conditioner operating parameters. The S-shaped transfer function is selected to process the sample data, and the network weights and thresholds of the error function are calculated and optimized through the backpropagation of the neural network until the minimum value of the error function is reached, and the trained air conditioner operating parameter recommendation model is obtained.

[0145] As an optional embodiment, the controller is further configured to:

[0146] Compare the optimal air conditioner operating parameters output by the air conditioner operating parameter recommendation model with the air conditioner operating parameters set by the user;

[0147] If the difference between the optimal air conditioner operating parameters and the air conditioner operating parameters set by the user is less than the preset threshold, control the air conditioner to operate with the air conditioner operating parameters set by the user;

[0148] If the difference between the optimal air conditioner operating parameters and the air conditioner operating parameters set by the user is not less than the preset threshold, use the air conditioner operating parameters set by the user as new sample data to train the air conditioner operating parameter recommendation model.

[0149] Specifically, please refer toFigure 8 , Figure 8 This is the third working flowchart of the controller in an air conditioner provided by an embodiment of the present invention. In the process of model training in the embodiment of the present invention, the optimal air conditioner operating parameters output by the air conditioner operating parameter recommendation model are compared with the air conditioner operating parameters set by the user. If the difference between the optimal air conditioner operating parameters and the air conditioner operating parameters set by the user is less than the preset threshold, the air conditioner is controlled to operate with the air conditioner operating parameters set by the user. If the difference between the optimal air conditioner operating parameters and the air conditioner operating parameters set by the user is not less than the preset threshold, the air conditioner operating parameters set by the user are used as new sample data to train the air conditioner operating parameter recommendation model, and the weights and thresholds of the network model are optimized, so as to finally generate the optimal air conditioner operating parameters that meet the personalized needs of the user.

[0150] As one of the optional embodiments, the air conditioner operating parameter recommendation model includes an input layer, a hidden layer, and an output layer connected in sequence; wherein, in the input layer, the hidden layer, and the output layer, each neuron in adjacent layers is fully connected, and there is no connection between each neuron in each layer; the activation function of the hidden layer is the Sigmoid function, and the error function of the air conditioner operating parameter recommendation model is the mean square error.

[0151] Specifically, please refer to Figure 9 , Figure 9 This is the structural schematic diagram of the air conditioner operating parameter recommendation model in an air conditioner provided by an embodiment of the present invention. In the embodiment of the present invention, the air conditioner operating parameter recommendation model includes an input layer, a hidden layer, and an output layer connected in sequence. Among them, in the input layer, the hidden layer, and the output layer, each neuron in adjacent layers is fully connected, and there is no connection between each neuron in each layer. Exemplarily, h j represents the hidden unit, and y k represents the output unit. The connection weight from the input unit x i to the hidden unit h j is w ij , and the connection weight from the hidden unit h j to the output unit y k is w ik , and ω = (W, w) represents all connection weights. Select the S function, that is, the Sigmoid function, as the activation function of the hidden layer, then the hidden layer can be expressed as:

[0152]

[0153] The gradient descent method is used to update the connection weights and bias values in the network. The update formulas for the connection weight values between the output layer and the hidden layer and the bias value of the output layer neuron are:

[0154]

[0155] b (3) =b (3) +Δb (3)

[0156]

[0157] The update formula of the connection weight between the hidden layer and the input layer and the bias of each neuron in the hidden layer is:

[0158]

[0159] When the collected training data samples are input into the network model, each neuron obtains the input response of the model and generates connection weights. Set the mean square error as the error function Among them, y k is the true value, is the predicted value. Then the error is back-propagated through the gradient descent method to continuously adjust the weights and thresholds of the network model. This process is repeated until the global error of the network tends to the given minimum value, that is, the learning process is completed.

[0160] After obtaining the trained air conditioner operating parameter recommendation model, the user can automatically recommend the optimal air conditioner operating parameters according to different regions, temperatures, humidity, and seasons when using the air conditioner. At the same time, the database can be updated according to the user's personalized settings and personal preferences, and the network weights and thresholds can be continuously optimized, so that the optimal air conditioner operating parameters recommended by the model are more in line with the user's personalized needs, thereby improving the user's usage experience and comfort.

[0161] It should be noted that the S-type transfer function, i.e., the Sigmoid function, refers to a system transfer function with nonlinear response characteristics. Its response characteristics are like an S-shaped curve. As the input signal changes, the output signal will also respond according to the S-shaped curve. The S-type transfer function is insensitive to the initial state of the system, that is, no matter what state the system is in, only one input signal is needed for the system to operate smoothly. The characteristic of the S-type transfer function is that the function itself and its derivatives are continuous, so it is very convenient to process. The purpose of using the S-type function in the embodiment of the present invention is to normalize the sample data. Through normalization, the dimensional influence between the data features is eliminated, so that different indicators are comparable, and all features are ensured to be compared on the same scale, thereby improving the accuracy and efficiency of the algorithm, and being able to speed up the solution speed of gradient descent and improve the convergence speed of the model.

[0162] See also Figure 10 , Figure 10It is a schematic flowchart of an operation control method for an air conditioner provided by an embodiment of the present invention. The operation control method for the air conditioner provided in the embodiment of the present invention is applied to an air conditioner including an indoor heat exchanger, an indoor fan, an outdoor heat exchanger, an outdoor fan, a compressor, a throttling component, and a four-way valve; the compressor, the throttling component, the four-way valve, the outdoor heat exchanger, and the indoor heat exchanger are connected by pipelines to form a refrigerant circulation loop, and the operation control method of the air conditioner includes:

[0163] S1, obtain the climate data of the user's location and the user's historical usage data, and preprocess the climate data and the historical usage data; wherein, the climate data includes temperature data, humidity data, season data, and regional data;

[0164] S2, input the preprocessed climate data and historical usage data into a preset air conditioner operation parameter recommendation model to obtain the optimal air conditioner operation parameters output by the air conditioner operation parameter recommendation model;

[0165] S3, control the operation of the air conditioner according to the optimal air conditioner operation parameters.

[0166] As an optional embodiment, the preprocessing of the climate data and the historical usage data specifically includes:

[0167] Perform data cleaning on the climate data and the historical usage data;

[0168] Check the validity of the climate data and the historical usage data, check and correct the error data, and replace the empty data with the historical average value.

[0169] As an optional embodiment, the training process of the air conditioner operation parameter recommendation model includes:

[0170] Obtain sample data, wherein the sample data includes climate data, the optimal air conditioner operation parameters corresponding to the climate data, and historical usage data;

[0171] Construct a BP neural network model, input the sample data into the BP neural network model, and obtain the predicted value output by the BP neural network model;

[0172] Calculate the error between the predicted value and the true value, and perform error iterative calculation and optimize the network weights and thresholds of the error function through neural network backpropagation until the minimum value of the error function is reached, and obtain the trained air conditioner operation parameter recommendation model.

[0173] As an optional embodiment, the method further includes:

[0174] Compare the optimal air conditioner operating parameters output by the air conditioner operating parameter recommendation model with the air conditioner operating parameters set by the user;

[0175] If the difference between the optimal air conditioner operating parameters and the air conditioner operating parameters set by the user is less than a preset threshold, control the air conditioner to operate with the air conditioner operating parameters set by the user;

[0176] If the difference between the optimal air conditioner operating parameters and the air conditioner operating parameters set by the user is not less than the preset threshold, use the air conditioner operating parameters set by the user as new sample data to train the air conditioner operating parameter recommendation model.

[0177] As an optional embodiment, the air conditioner operating parameter recommendation model includes an input layer, a hidden layer, and an output layer connected in sequence; wherein, in the input layer, the hidden layer, and the output layer, each neuron in adjacent layers is fully connected, and there is no connection between neurons in each layer; the activation function of the hidden layer is the Sigmoid function, and the error function of the air conditioner operating parameter recommendation model is the mean square error.

[0178] The embodiment of the present invention provides an air conditioner and its operation control method, by obtaining the climate data of the user's location and the user's historical usage data, and preprocessing the climate data and the historical usage data; wherein, the climate data includes temperature data, humidity data, season data, and regional data; input the preprocessed climate data and historical usage data into a pre-trained air conditioner operating parameter recommendation model to obtain the optimal air conditioner operating parameters output by the air conditioner operating parameter recommendation model, and control the air conditioner to operate with the optimal air conditioner operating parameters. The embodiment of the present invention analyzes and predicts based on a large amount of historical data, and continuously optimizes the model parameters according to the personalized needs of the user. By intelligently recommending and dynamically adjusting the optimal operating parameters of the air conditioner, it ensures that users can enjoy the best air conditioning experience in different regional environments without manual intervention by the user, greatly improving the comfort and satisfaction of the user.

[0179] It should be noted that the system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in the attached drawings of the system embodiments provided by the present invention, the connection relationships between modules indicate that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0180] The above is the preferred embodiment of the present invention. It should be pointed out that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements are also regarded as the protection scope of the present invention.

Claims

1. An air conditioner, characterized in that, including: an indoor unit, which is internally provided with an indoor heat exchanger and an indoor fan; an outdoor unit, which is internally provided with an outdoor heat exchanger, an outdoor fan, a compressor, a throttling component and a four-way valve, and the compressor, the throttling component, the four-way valve, the outdoor heat exchanger and the indoor heat exchanger are connected through pipelines to form a refrigerant circulation loop; The controller is configured to obtain the climate data of the user's location and the user's historical usage data, and preprocess the climate data and the historical usage data; wherein, the climate data includes temperature data, humidity data, season data and regional data; input the preprocessed climate data and historical usage data into a preset air conditioner operation parameter recommendation model to obtain the optimal air conditioner operation parameters output by the air conditioner operation parameter recommendation model; control the operation of the air conditioner according to the optimal air conditioner operation parameters.

2. The air conditioner according to claim 1, characterized in that The preprocessing of the climate data and the historical usage data specifically includes: performing data cleaning on the climate data and the historical usage data; checking the validity of the climate data and the historical usage data, checking and correcting the error data, and replacing the null data with the historical mean value.

3. The air conditioner according to claim 2, wherein The training process of the air conditioner operation parameter recommendation model includes: obtaining sample data, wherein the sample data includes climate data, the optimal air conditioner operation parameters corresponding to the climate data, and historical usage data; constructing a BP neural network model, inputting the sample data into the BP neural network model, and obtaining the predicted value output by the BP neural network model; calculating the error between the predicted value and the true value, and performing error iterative calculation and optimizing the network weights and thresholds of the error function through the reverse propagation of the neural network until the minimum value of the error function is reached, and obtaining the trained air conditioner operation parameter recommendation model.

4. The air conditioner according to claim 3, wherein, The controller is further configured to: compare the optimal air conditioner operation parameters output by the air conditioner operation parameter recommendation model with the air conditioner operation parameters set by the user; if the difference between the optimal air conditioner operation parameters and the air conditioner operation parameters set by the user is less than a preset threshold, control the air conditioner to operate with the air conditioner operation parameters set by the user; if the difference between the optimal air conditioner operation parameters and the air conditioner operation parameters set by the user is not less than the preset threshold, use the air conditioner operation parameters set by the user as new sample data to train the air conditioner operation parameter recommendation model.

5. The air conditioner according to claim 4, wherein, The air conditioner operation parameter recommendation model includes an input layer, a hidden layer and an output layer connected in sequence; wherein, in the input layer, the hidden layer and the output layer, each neuron in adjacent layers is fully connected, and there is no connection between each neuron in each layer; the activation function of the hidden layer is the Sigmoid function, and the error function of the air conditioner operation parameter recommendation model is the mean square error.

6. An operating control method for an air conditioner, characterized in that The method is applied to an air conditioner including an indoor heat exchanger, an indoor fan, an outdoor heat exchanger, an outdoor fan, a compressor, a throttling component and a four-way valve, and the operation control method of the air conditioner includes: Obtain the climate data of the user's location and the user's historical usage data, and preprocess the climate data and the historical usage data; wherein, the climate data includes temperature data, humidity data, season data, and regional data; Input the preprocessed climate data and historical usage data into a preset air conditioner operation parameter recommendation model, and obtain the optimal air conditioner operation parameters output by the air conditioner operation parameter recommendation model; Control the operation of the air conditioner according to the optimal air conditioner operation parameters.

7. The operation control method of the air conditioner according to claim 6, characterized in that, The preprocessing of the climate data and the historical usage data specifically includes: Perform data cleaning on the climate data and the historical usage data; Check the validity of the climate data and the historical usage data, check and correct the error data, and replace the null data with the historical mean value.

8. The operation control method of the air conditioner according to claim 7, characterized in that, The training process of the air conditioner operation parameter recommendation model includes: Obtain sample data, wherein the sample data includes climate data, the optimal air conditioner operation parameters corresponding to the climate data, and historical usage data; Construct a BP neural network model, input the sample data into the BP neural network model, and obtain the predicted value output by the BP neural network model; Calculate the error between the predicted value and the true value, and perform error iterative calculation and optimize the network weights and thresholds of the error function through neural network backpropagation until the minimum value of the error function is reached, and obtain a trained air conditioner operation parameter recommendation model.

9. The operation control method of the air conditioner according to claim 8, characterized in that, The method further includes: Compare the optimal air conditioner operation parameters output by the air conditioner operation parameter recommendation model with the air conditioner operation parameters set by the user; If the difference between the optimal air conditioner operation parameters and the air conditioner operation parameters set by the user is less than a preset threshold, control the air conditioner to operate with the air conditioner operation parameters set by the user; If the difference between the optimal air conditioner operation parameters and the air conditioner operation parameters set by the user is not less than the preset threshold, use the air conditioner operation parameters set by the user as new sample data to train the air conditioner operation parameter recommendation model.

10. The operating control method of the air conditioner according to claim 9, wherein The air conditioner operation parameter recommendation model includes an input layer, a hidden layer, and an output layer connected in sequence; wherein, in the input layer, the hidden layer, and the output layer, all neurons between adjacent layers are fully connected, and there is no connection between neurons in each layer; the activation function of the hidden layer is the Sigmoid function, and the error function of the air conditioner operation parameter recommendation model is the mean square error.

Images