Model training and air conditioner control method

Abstract

The present disclosure provides a model training and air conditioner control method, relating to the technical field of air conditioners, which comprises: obtaining training data, the training data comprising layout parameters of an air conditioning device, regulation and control parameters of the air conditioning device, environmental parameters of a space where the air conditioning device is located, and thermal comfort parameters of a user in the space; using the training data to train an initial prediction model to obtain a target prediction model, thereby achieving efficient and accurate prediction of the thermal environment and thermal comfort state of an air-conditioned room. In actual application, based on the current layout and regulation and control parameters of the air conditioning device, the target prediction model trained can be used to quickly determine the real-time environmental parameters of the space and the thermal comfort state of the user, thereby effectively controlling the air conditioning device, greatly reducing research cost and time, improving research efficiency, achieving efficient and economic evaluation and accurate control of air flow organization in an air-conditioned room, and effectively ensuring indoor thermal environment quality and energy saving.

Description

Technical Field

[0001] This disclosure relates to the field of air conditioning technology, and in particular to a model training method, an air conditioning control method, a device, an electronic device, a chip, and a medium. Background Technology

[0002] In modern building environments, people's pursuit of indoor comfort and energy efficiency is constantly increasing. Research on airflow organization in air-conditioned rooms has become a key aspect of ensuring indoor thermal environment quality and energy conservation. Reasonable airflow organization can not only effectively regulate indoor temperature, humidity, and air quality, but also reduce the energy consumption of air conditioning systems. Therefore, in-depth research on this topic has significant practical implications and application value.

[0003] Currently, the assessment of airflow organization in air-conditioned rooms mainly employs two traditional methods: laboratory testing and numerical simulation. Laboratory testing involves directly measuring airflow parameters by setting up experimental environments, while numerical simulation utilizes CFD software to establish mathematical models for simulation analysis; the accuracy of both has been verified. However, laboratory testing requires significant investment of manpower and resources, has a long testing cycle, and is difficult to respond quickly to design adjustments; numerical simulation involves a complex modeling process, high computational resource requirements, and the accuracy of model parameters depends on experience-based settings, requiring repeated debugging which is time-consuming and costly, failing to meet the needs of efficient and economical research. Summary of the Invention

[0004] This disclosure provides a model training method, air conditioning control method, device, electronic equipment, chip, and medium to solve the problems of time-consuming and costly processes in related technologies. By selecting appropriate training data to train a prediction model, a target prediction model is obtained. Based on the current layout and control parameters of the air conditioning equipment, the target prediction model is used to quickly determine the real-time environmental parameters of the space and the thermal comfort status of the user, thereby effectively controlling the air conditioning equipment, significantly reducing research costs and time, improving research efficiency, and achieving efficient and economical assessment and precise control of airflow organization in air-conditioned rooms, effectively ensuring the quality of the indoor thermal environment and energy conservation.

[0005] The first aspect of this disclosure proposes a model training method, which includes: acquiring training data, including layout parameters of an air conditioning unit, control parameters of the air conditioning unit, environmental parameters of the space where the air conditioning unit is located, and thermal comfort parameters of users in the space where the air conditioning unit is located; and using the training data to train an initial prediction model to obtain a target prediction model.

[0006] In some embodiments of this disclosure, obtaining training data includes: obtaining different layout parameters and different control parameters of at least one type of air conditioning equipment under different modes; and obtaining environmental parameters and thermal comfort parameters corresponding to different locations in the space where the air conditioning equipment is located under different layout parameters and different control parameters.

[0007] In some embodiments of this disclosure, obtaining different layout parameters and different control parameters of at least one type of air conditioning equipment includes: obtaining different layout parameters and different control parameters of at least one type of air conditioning equipment in experimental and / or simulation environments, respectively; wherein, under different layout parameters and different control parameters, obtaining environmental parameters and thermal comfort parameters corresponding to different positions in the space where the air conditioning equipment is located includes: in an experimental environment, using a data acquisition device to obtain environmental parameters and thermal comfort parameters corresponding to different positions in the space where the air conditioning equipment is located under different layout parameters and different control parameters; and / or, in a simulation environment, using a simulation model to obtain environmental parameters and thermal comfort parameters corresponding to different positions in the space where the air conditioning equipment is located under different layout parameters and different control parameters.

[0008] In some embodiments of this disclosure, the air conditioning equipment includes an air duct in a simulation environment. The air duct includes at least the outer casing of the air conditioning equipment, the enveloping air guide plate of the air conditioning equipment, and the sweeping blades of the air conditioning equipment.

[0009] In some embodiments of this disclosure, the method further includes: in a simulation environment, using the statistical values ​​of training data that meet preset conditions as data in the training data, wherein the preset conditions are: the change of training data within a preset time period is less than or equal to a preset range.

[0010] In some embodiments of this disclosure, the layout parameters of the air conditioning equipment include at least one of the following: the location of the air conditioning equipment in the space; the installation location of the air conditioning equipment on the wall; the distance between the air conditioning equipment and at least one wall, and the angle between the air conditioning equipment and the wall; the control parameters of the air conditioning equipment include at least one of the following: the air volume supplied by the air conditioning equipment; the angle of the air guide plate of the air conditioning equipment; the angle of the air sweeping blades of the air conditioning equipment; the environmental parameters of the space where the air conditioning equipment is located include at least one of the following: the wind speed at different locations in the space where the air conditioning equipment is located; the temperature; the humidity; the thermal comfort parameters of the user in the space where the air conditioning equipment is located include at least one of the following: the user's thermal comfort index PMV; the user's airflow sensation index DR.

[0011] In some embodiments of this disclosure, the method further includes: performing feature transformation processing on the layout parameters and control parameters of the air conditioning equipment, wherein the amount of data after feature transformation processing is greater than the amount of data before feature transformation processing; and using the layout parameters and control parameters after feature transformation processing as training data.

[0012] A second aspect of this disclosure provides an air conditioning control method, which includes: acquiring current layout parameters and current control parameters of an air conditioning unit; determining current environmental parameters of the space where the air conditioning unit is located and current thermal comfort parameters of the user based on the current layout parameters and current control parameters using a target prediction model, wherein the target prediction model is trained based on the existing layout parameters of the air conditioning unit, the control parameters of the air conditioning unit, the environmental parameters of the space where the air conditioning unit is located, and the thermal comfort parameters of the user in the space where the air conditioning unit is located; and controlling the air conditioning unit based on the current environmental parameters of the space where the air conditioning unit is located and the current thermal comfort parameters of the user.

[0013] In some embodiments of this disclosure, the method further includes: determining usage parameters of the air conditioning device, the usage parameters including the current mode of the air conditioning device, the user's position and / or posture in the space where the air conditioning device is located; and determining a target prediction model corresponding to the usage parameters based on the usage parameters.

[0014] In some embodiments of this disclosure, the air conditioning equipment is controlled based on the current environmental parameters of the space where the air conditioning equipment is located and the current thermal comfort parameters of the user, including: adjusting the current layout parameters and / or the current control parameters according to the current environmental parameters of the space where the air conditioning equipment is located and the current thermal comfort parameters of the user.

[0015] A third aspect of this disclosure provides a model training apparatus, the apparatus comprising:

[0016] The first acquisition unit is used to acquire training data, which includes the layout parameters of the air conditioning equipment, the control parameters of the air conditioning equipment, the environmental parameters of the space where the air conditioning equipment is located, and the thermal comfort parameters of the users in the space where the air conditioning equipment is located.

[0017] The training unit is used to train the initial prediction model using training data to obtain the target prediction model.

[0018] A fourth aspect of this disclosure provides an air conditioning control device, the device comprising:

[0019] The second acquisition unit is used to acquire the current layout parameters and current control parameters of the air conditioning equipment;

[0020] The determination unit is used to determine the current environmental parameters of the space where the air conditioning equipment is located and the current thermal comfort parameters of the user based on the current layout parameters and current control parameters, using a target prediction model. The target prediction model is trained based on the existing layout parameters of the air conditioning equipment, the control parameters of the air conditioning equipment, the environmental parameters of the space where the air conditioning equipment is located, and the thermal comfort parameters of the user in the space where the air conditioning equipment is located.

[0021] The control unit is used to control the air conditioning equipment based on the current environmental parameters of the space where the air conditioning equipment is located and the user's current thermal comfort parameters.

[0022] A fifth aspect of this disclosure provides an air conditioning device, including a model training apparatus as described in a third aspect of this disclosure and / or an air conditioning control apparatus as described in a fourth aspect of this disclosure.

[0023] A sixth aspect of this disclosure provides an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the methods described in the first or second aspect of this disclosure.

[0024] A seventh aspect of this disclosure provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to perform the methods described in the first or second aspect of this disclosure.

[0025] In summary, based on the model training and air conditioning control method proposed in this disclosure, by integrating the layout and control parameters of air conditioning equipment, combined with spatial environmental parameters and user thermal comfort parameters, a refined training dataset is constructed. This dataset is then used to deeply optimize and train the initial model, achieving efficient and accurate prediction of the thermal environment and thermal comfort state of air-conditioned rooms. In practical applications, based on the current layout and control parameters of the air conditioning equipment, and with the help of a well-trained target prediction model, real-time spatial environmental parameters and user thermal comfort status can be quickly determined. This allows for effective control of the air conditioning equipment, significantly reducing research costs and time, improving research efficiency, and achieving efficient and economical assessment and precise control of airflow organization in air-conditioned rooms. This effectively ensures indoor thermal environment quality and energy conservation.

[0026] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0027] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure, and are not intended to unduly limit this disclosure.

[0028] Figure 1 This is a schematic diagram illustrating the principle of achieving thermal environment and thermal comfort in an air-conditioned room, provided by an embodiment of the present disclosure.

[0029] Figure 2 A schematic diagram illustrating the construction process of a rapid prediction model for thermal environment and thermal comfort in an air-conditioned room, provided in an embodiment of this disclosure;

[0030] Figure 3 A flowchart of a model training method provided in this embodiment of the disclosure;

[0031] Figure 4 A flowchart of another model training method provided in this disclosure embodiment;

[0032] Figure 5 A residual plot of a prediction model provided in an embodiment of this disclosure;

[0033] Figure 6 A learning curve diagram of a prediction model provided in an embodiment of this disclosure;

[0034] Figure 7 A flowchart of an air conditioning control method provided in this embodiment of the disclosure;

[0035] Figure 8 A schematic diagram illustrating the prediction effect of a prediction model based on the input air conditioner placement angle, provided in an embodiment of this disclosure;

[0036] Figure 9 A schematic diagram illustrating the prediction effect of a prediction model under an input air supply volume, provided in an embodiment of this disclosure;

[0037] Figure 10 A schematic diagram illustrating the prediction effect of a prediction model based on the input sweep blade angle, provided in an embodiment of this disclosure;

[0038] Figure 11 A schematic diagram illustrating the prediction effect of a prediction model under an input wind guide angle, provided in an embodiment of this disclosure;

[0039] Figure 12 A schematic diagram illustrating the prediction effect of a prediction model under different input parameters, provided in an embodiment of this disclosure;

[0040] Figure 13 This is a schematic diagram of the structure of a model training device provided in an embodiment of the present disclosure;

[0041] Figure 14 This is a schematic diagram of the structure of an air conditioning control device provided in an embodiment of the present disclosure;

[0042] Figure 15 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure;

[0043] Figure 16 This is a schematic diagram of the chip structure provided in an embodiment of this disclosure. Detailed Implementation

[0044] Embodiments of this disclosure are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments are described below with reference to the accompanying drawings.

[0045] In modern building environments, people's pursuit of indoor comfort and energy efficiency is constantly increasing. Research on airflow organization in air-conditioned rooms has become a key aspect of ensuring indoor thermal environment quality and energy conservation. Reasonable airflow organization can not only effectively regulate indoor temperature, humidity, and air quality, but also reduce the energy consumption of air conditioning systems. Therefore, in-depth research on this topic has significant practical implications and application value.

[0046] Currently, the assessment of airflow organization in air-conditioned rooms mainly employs two traditional methods: laboratory testing and numerical simulation. Laboratory testing involves setting up realistic or scaled-down experimental environments to directly measure airflow parameters during air conditioning system operation, thus obtaining accurate experimental data. Numerical simulation, on the other hand, utilizes computational fluid dynamics (CFD) software to establish mathematical models and simulate airflow flow, providing a visual representation of airflow organization distribution. The accuracy of both methods has been widely verified.

[0047] However, laboratory testing requires a significant investment of manpower and resources to build the experimental environment, and the testing cycle is long, making it difficult to quickly respond to adjustments in the design scheme. While numerical simulation is relatively flexible, the modeling process is complex, it has high requirements for computing resources, and the accuracy of model parameters depends on experience-based settings. Repeated debugging also consumes a lot of time and costs, making it difficult to meet the current needs for efficient and economical research.

[0048] In order to address the problems existing in related technologies, this disclosure aims to build a target prediction model to achieve rapid and accurate prediction of the thermal environment and thermal comfort of air-conditioned rooms, so as to optimize the layout and control parameters of air conditioners and improve living comfort and energy efficiency.

[0049] See Figure 1 The diagram shown illustrates the principle of achieving thermal environment and thermal comfort in an air-conditioned room. Figure 1 The upper part represents the traditional CFD model in related technologies, which involves evaluating and analyzing the airflow organization and thermal comfort of air-conditioned rooms based on CFD model calculations to clarify optimization directions. It is evident that related technologies require repetitive geometric modeling, parameter tuning, and output processes, resulting in low efficiency. To achieve evaluation of operating conditions without CFD calculations while saving computational efficiency and time costs, facilitating long-term design and maintenance, this disclosure provides... Figure 1 The second half is based on a fast prediction model for data-driven students (i.e., the target prediction model of this disclosure) and Figure 2The diagram illustrates the construction process of a rapid prediction model for the thermal environment and thermal comfort of an air-conditioned room. This disclosure accurately constructs a target prediction model by inputting new design parameters (i.e., the layout parameters of the air conditioning equipment, the control parameters of the air conditioning equipment, the environmental parameters of the space where the air conditioning equipment is located, and the thermal comfort parameters of the users in the space where the air conditioning equipment is located). This enables efficient and accurate prediction of the thermal environment and thermal comfort status of the air-conditioned room. In practical applications, based on the current layout and control parameters of the air conditioning equipment, and with the help of a well-trained target prediction model, the real-time environmental parameters of the space and the thermal comfort status of the users can be quickly determined. This allows for dynamic control of the air conditioning equipment, precise matching of different activity modes and population distribution needs, significantly improved indoor thermal comfort, and optimized air conditioning system operating efficiency.

[0050] The model training method provided in this application will be described in detail below with reference to the accompanying drawings.

[0051] Figure 3 A flowchart illustrating a model training method provided in an embodiment of this disclosure. Figure 3 As shown, the model training method includes steps 101-102.

[0052] Step 101: Obtain training data, which includes the layout parameters of the air conditioning equipment, the control parameters of the air conditioning equipment, the environmental parameters of the space where the air conditioning equipment is located, and the thermal comfort parameters of the users in the space where the air conditioning equipment is located.

[0053] In this embodiment of the disclosure, the layout parameters of the air conditioning equipment refer to information such as the specific installation location, orientation, and distribution of air vents of the air conditioner in the room. For example, which wall the indoor unit of the air conditioner is installed on, its height from the ground, and the relative position of the supply air vent and return air vent, etc. The layout parameters of the air conditioning equipment can affect the flow path and distribution of the airflow delivered by the air conditioner in the room.

[0054] The control parameters of air conditioning equipment can include user or system settings for the air conditioner's operating status. For example, the set temperature, different temperature settings will affect the air conditioner's cooling or heating power and duration; the fan speed setting, high and low fan speeds will change the airflow speed and coverage area; and the operating mode, such as cooling mode, heating mode, dehumidification mode, etc., the working principle and energy consumption of the air conditioner are different in different modes.

[0055] The environmental parameters of the space where air conditioning equipment is located include various physical characteristics and environmental conditions of the room. For example, the size of the room (length, width, and height) is important; the larger the space, the more difficult it is for the air conditioner to achieve a uniform temperature distribution. The room's insulation performance is also crucial; good insulation can reduce heat transfer and lower the energy consumption of the air conditioner. The initial temperature and humidity of the environment affect the workload and adjustment time of the air conditioner when it starts up. The presence of heat sources in the room (such as computers, lights, etc.) and the orientation and size of the windows also affect the indoor thermal environment.

[0056] Thermal comfort parameters for users in the space where air conditioning equipment is located mainly reflect the feelings and needs of people in that space regarding the thermal environment. For example, the number of people: the more people there are, the more heat and moisture they emit, which will change the indoor thermal and humidity environment; the intensity of people's activities: people who are sitting still feel the temperature differently than people who are exercising, and people who are active may need a lower temperature; and people's subjective evaluation of the thermal environment, such as whether they feel cool, comfortable, or stuffy.

[0057] In this disclosure, the space where the air conditioning equipment is located can be either a real physical environment or a virtual scene constructed by simulation software during numerical simulation. Correspondingly, the layout parameters and control parameters in the training data can be either real values ​​obtained through actual measurements or virtual data generated by simulation software. This disclosure fully covers diverse scenarios of actual and simulated values: the source of the training dataset is flexible, capable of collecting various parameters in the real environment in real time using hardware facilities such as sensors and data acquisition devices; or it can quickly generate virtual data under different operating conditions by running simulation programs through professional simulation software, ensuring the comprehensiveness and diversity of the training data, thereby effectively improving the generalization ability and adaptability of the prediction model.

[0058] Step 102: Use the training data to train the initial prediction model to obtain the target prediction model.

[0059] In embodiments of this disclosure, training data can be used to optimize and improve the initial prediction model. The initial prediction model is typically constructed based on certain mathematical principles and algorithms, and it makes a preliminary assumption and mapping about the relationship between various input parameters (i.e., various parameters in the previously acquired training data) and output results (such as changes in indoor environmental parameters, user thermal comfort, etc.).

[0060] During training, each set of data from the training dataset is sequentially input into the initial prediction model. The model calculates the corresponding output based on its algorithm and parameter settings. Then, the output calculated by the model is compared with the actual, known correct results (which are also part of the training data, such as indoor temperatures obtained through actual measurements and real user thermal comfort feedback) to calculate the error between the two.

[0061] Based on this error, optimization algorithms in machine learning (such as gradient descent) are used to adjust the parameters in the model, enabling it to output a prediction closer to the correct result when given the same or similar input data. This process is repeated, continuously inputting training data, calculating the error, and adjusting the parameters, until the error between the model's output and the correct result reaches an acceptable range, or until a pre-set number of training iterations is reached. At this point, the trained initial prediction model becomes the target prediction model, which can more accurately predict environmental changes in the space where the air conditioning equipment is located and the user's thermal comfort state based on the input air conditioning equipment layout parameters, control parameters, spatial environment parameters, and user thermal comfort parameters. This provides a reliable basis for subsequent intelligent control of the air conditioning equipment based on these prediction results.

[0062] In summary, based on the model training method proposed in this disclosure, the target prediction model is trained by using the layout of air conditioning equipment, control parameters, spatial environment, and user thermal comfort parameters as training data. This enables rapid model training and improves the accuracy and efficiency of the target prediction model in predicting the thermal environment of air-conditioned rooms and the thermal comfort state of users.

[0063] based on Figure 3 The embodiment shown, Figure 4 A flowchart of another model training method proposed in this disclosure is further shown. Figure 4 based on Figure 3 The illustrated embodiment further defines step 101. Figure 4 In the illustrated embodiment, step 101 includes steps 201 and 202. For example... Figure 4 As shown, the method includes the following steps:

[0064] Step 201: Obtain different layout parameters and different control parameters of at least one type of air conditioning equipment under different modes.

[0065] In the embodiments of this disclosure, different layout parameters and different control parameters of at least one type of air conditioning equipment are obtained in experimental and / or simulation environments.

[0066] In other words, this disclosure employs a combination of experimental measurement and numerical simulation to construct a multi-dimensional training dataset. During the experimental phase, a standardized testing environment is set up in the laboratory. By adjusting the spatial layout of the air conditioning equipment and changing control parameters such as airflow volume, air guide plate angle, and sweep blade angle, high-precision temperature sensors, anemometers, and other professional equipment are used to collect real-time wind speed and temperature data at various monitoring points in the room, obtaining thermal environment parameters under realistic conditions. In the numerical simulation phase, a refined airflow organization model of the air-conditioned room is established using CFD software. This model covers the detailed structural features of the air conditioning components. By simulating airflow movement and heat exchange processes under different operating conditions, the model accurately calculates the wind speed and temperature distribution at various locations within the space and simultaneously outputs core indicators such as the PMV thermal comfort index and DR draft feeling index. Finally, the experimental measurement data and numerical simulation results are systematically integrated to form a comprehensive dataset including air conditioning equipment layout parameters, control parameters, and corresponding thermal environment and thermal comfort parameters, providing rich and reliable data support for subsequent model training.

[0067] The types of air conditioning equipment disclosed herein may include floor-standing units, wall-mounted units, and central air conditioning systems. Different modes include cooling mode and heating mode. This disclosure allows for the separate acquisition of training data for each type of air conditioner under different modes, thereby training its corresponding target prediction model.

[0068] In a simulation environment, this disclosure can refine the air conditioning equipment, which may include the outer casing, the enveloping air guide plate, and the actual structure of the sweeping blades in the air duct. By refining the air conditioning equipment, this disclosure can accurately simulate the airflow path inside the equipment during operation, as well as the diffusion pattern after exiting the air outlet, providing a reliable basis for more realistically presenting the impact of the air conditioning equipment on the spatial airflow organization and thermal environment.

[0069] Step 202: Under different layout parameters and different control parameters, obtain the environmental parameters and thermal comfort parameters corresponding to different locations in the space where the air conditioning equipment is located.

[0070] In the embodiments of this disclosure, the present disclosure can obtain environmental and thermal comfort parameters corresponding to different locations in the space where the air conditioning equipment is located under different layouts and control parameters, providing data support for accurate prediction and optimization of the thermal environment. Specifically, under the same combination of layout and control parameters, the environmental parameters of different postures (such as standing and sitting postures) will be different, and the present disclosure will conduct model training for these different positions separately.

[0071] In the experimental environment, a data acquisition device is used to obtain environmental parameters and thermal comfort parameters corresponding to different locations in the space where the air conditioning equipment is located under different layout parameters and different control parameters; and / or, in the simulation environment, a simulation model is used to obtain environmental parameters and thermal comfort parameters corresponding to different locations in the space where the air conditioning equipment is located under different layout parameters and different control parameters.

[0072] In other words, this disclosure employs a parallel approach of experimentation and simulation for data acquisition. In the experimental environment, various data acquisition devices are used to conduct on-site measurements of environmental parameters (such as wind speed, temperature, and humidity) and user thermal comfort parameters (such as thermal comfort index PMV and wind-feeling index DR) at different locations within a space under different layouts and control parameters. In the simulation environment, simulation models are used to simulate different working conditions and acquire the corresponding parameters. To ensure the stability and reliability of the data, in the simulation environment, statistical values ​​of training data that meet preset conditions are included in the training dataset. The preset condition is that the change in training data within a preset time period is less than or equal to a preset range. That is, for data in the simulation environment, when the change in training data within a preset time period is less than or equal to a preset range, its statistical value is included in the training dataset.

[0073] The layout parameters of the air conditioning equipment include at least one of the following: the location of the air conditioning equipment in the space; the installation location of the air conditioning equipment on the wall; the distance between the air conditioning equipment and at least one wall, and the angle between the air conditioning equipment and the wall; the control parameters of the air conditioning equipment include at least one of the following: the air volume of the air conditioning equipment; the angle of the air guide plate of the air conditioning equipment; the angle of the air sweeping blades of the air conditioning equipment; the environmental parameters of the space where the air conditioning equipment is located include at least one of the following: the wind speed at different locations in the space where the air conditioning equipment is located; the temperature; the humidity; the thermal comfort parameters of the users in the space where the air conditioning equipment is located include at least one of the following: the user's thermal comfort index PMV; the user's airflow sensation index DR.

[0074] Furthermore, to enhance the predictive model's learning ability and representation accuracy of air conditioning equipment parameters, this disclosure introduces a feature transformation processing mechanism. This mechanism transforms the layout parameters and control parameters of the air conditioning equipment, resulting in a larger dataset after feature transformation compared to before. The transformed layout and control parameters are then used as training data. Specifically, for angle-type parameters (such as the angle of the air guide vane and the angle of the sweeping blades), trigonometric functions are used to convert them into sine and cosine values, preserving the periodicity of angle changes while transforming them into numerical features suitable for model processing. For continuous control parameters such as air volume, polynomial features such as square and cubic values ​​are further derived while retaining the original values ​​to explore the nonlinear relationship between the parameters and changes in the thermal environment. This transformation significantly expands the data volume and fully activates the potential correlations between parameter features, providing richer and more discriminative input features for subsequent model training. This effectively improves the model's prediction accuracy and generalization ability for complex thermal environment changes.

[0075] Step 203: Use the training data to train the initial prediction model to obtain the target prediction model.

[0076] In the embodiments of this disclosure, a training set of data is used to train the model, and through repeated iterations, the model learns the mapping relationship between the air conditioner layout and control parameters and thermal environment parameters.

[0077] This disclosure allows for the comparison of the applicability of different machine learning methods when training a prediction model. With limited initial investment, the feasibility and efficiency of different methods can be quickly verified. For example, the random forest algorithm is used to construct the prediction model. This algorithm improves the accuracy and stability of predictions by integrating multiple decision trees. Optimal hyperparameters of the random forest model, such as the number of trees and the maximum tree depth, are determined through grid search and cross-validation to obtain the best prediction results.

[0078] In the embodiments of this disclosure, the random forest algorithm is used as an example to demonstrate the model training effect for a room with a cabinet air conditioner. During the learning process, the training set and the validation set are divided according to a preset ratio (e.g., 8:2). The physical coordinate features and design parameter features in the dataset have significant dimensional differences, requiring feature transformation techniques for data preprocessing. The corresponding data preprocessing methods are shown in Table 1, aiming to make the data distribution input to the prediction model more conducive to the model's learning and generalization process, and to avoid excessive differences in feature parameter dimensionality that could significantly reduce the model's learning ability.

[0079] Table 1 shows the feature engineering and original parameter settings for different feature parameters.

[0080] Air conditioner placement angle / ° Decompose into sine and cosine values -15~+15 equidistant sampling Air volume / m3·h-1 Decompose into original value and square value 650 / 800 / 900 / 1100 / 1150 / 1250 / 1350 / 1500 Air guide plate rotation angle / ° Decompose into sine and cosine values 40.0~82.3 equidistant acquisition Rotation angle of the sweeping blades / ° Decompose into sine and cosine values -35 to +35 equidistant sampling

[0081] After training the prediction model, the prediction accuracy is evaluated using independent validation set data. Errors between predicted and true values ​​are calculated, such as Mean Square Error (MSE), Root Mean Square Error (RMSE), and Mean Absolute Error (MAE). Based on the validation results, model parameters are adjusted or data preprocessing is optimized until satisfactory prediction accuracy is achieved.

[0082] For example, the original training dataset for the prediction model contains 98 sets of simulation results. Each set contains approximately 15,000 data points in a single plane. Taking the velocity analysis under the input air conditioner rotation angle as an example, the performance of the prediction model is evaluated and analyzed through the output model residual plot and learning curve plot. See also... Figure 5 The residual plots of the prediction model are shown below, where (a) is the standing height plane under cooling conditions; (b) is the sitting height plane under cooling conditions; (c) is the standing height plane under heating conditions; and (d) is the sitting height plane under heating conditions. Figure 5 Under cooling conditions, there are certain deviations between predicted and actual measured values ​​for the velocity range of 0 to 1.5 m / s on the standing height surface and for the portions exceeding 4 m / s on the sitting height surface. Similarly, under heating conditions, the distribution pattern of this deviation is consistent with that under cooling conditions, with the measured velocity distribution on the standing height surface concentrated in the lower range, and the prediction model can match this characteristic well. See also Figure 6 The learning curves of the prediction model are shown below, where (a) is the standing height plane under cooling conditions; (b) is the sitting height plane under cooling conditions; (c) is the standing height plane under heating conditions; and (d) is the sitting height plane under heating conditions. Figure 6 The changes in out-of-bag error during hyperparameter tuning are shown. The current model can minimize out-of-bag error by automatically optimizing hyperparameters.

[0083] In summary, the model training method proposed in this disclosure integrates multi-data from real-world scenarios and virtual simulations. It utilizes actual data collected by sensors to ensure realism while leveraging simulation software to generate virtual data, expanding the coverage of operating conditions and significantly enriching the breadth and depth of the training dataset. The target prediction model trained on this basis not only effectively overcomes the shortcomings of traditional methods, such as low efficiency and high cost, but also accurately and quickly predicts the thermal environment of air-conditioned rooms and the thermal comfort status of users. It supports dynamic adjustment of air conditioning equipment based on real-time parameters, achieving intelligent adaptation to different activity modes and population distributions, and significantly improving indoor thermal comfort and the energy efficiency of the air conditioning system.

[0084] Figure 7 This is a flowchart illustrating an air conditioning control method provided in an embodiment of this disclosure. Figure 7 As shown, the air conditioning control method includes steps 301-303.

[0085] Step 301: Obtain the current layout parameters and current control parameters of the air conditioning equipment.

[0086] Step 302: Based on the current layout parameters and current control parameters, use the target prediction model to determine the current environmental parameters of the space where the air conditioning equipment is located and the current thermal comfort parameters of the user.

[0087] In this disclosure, the target prediction model is trained based on the layout parameters of existing air conditioning equipment, the control parameters of air conditioning equipment, the environmental parameters of the space where the air conditioning equipment is located, and the thermal comfort parameters of users in the space where the air conditioning equipment is located.

[0088] In embodiments of this disclosure, the disclosure further includes: determining usage parameters of the air conditioning device, the usage parameters including the current mode of the air conditioning device, the user's position and / or posture in the space where the air conditioning device is located; and determining a target prediction model corresponding to the usage parameters based on the usage parameters.

[0089] In one optional embodiment of this disclosure, taking a room with a cabinet-type air conditioner as an example, the target prediction module of this disclosure can output the current environmental parameters of the space where the air conditioning equipment is located and the user's current thermal comfort parameters, such as the room's velocity, temperature distribution, and thermal comfort parameters such as PMV index and DR index, based on the current layout parameters and current control parameters of the room. This disclosure can also provide optimization suggestions for the air conditioner layout and control parameters based on the output current environmental parameters of the space where the air conditioning equipment is located and the user's current thermal comfort parameters to improve thermal comfort and energy efficiency. Simultaneously, this disclosure can also monitor the air conditioner's operating status in real time and dynamically adjust the control parameters according to the model to achieve intelligent optimization.

[0090] In the embodiments disclosed herein, the initial prediction model includes functions such as a custom weighting function and grid search hyperparameter optimization. The computation time for a single CFD simulation is approximately 10 hours. After the dataset is built, the learning time for the fast prediction model is approximately 5 minutes. After learning is complete, the speed of inputting new variables to predict the thermal environment and thermal comfort display cloud maps is in the seconds, significantly improving computational efficiency. The prediction results can also be qualitatively analyzed based on the cloud maps, and the model error can be quantitatively analyzed; see [reference needed]. Figure 8 The diagram shows the prediction effect of the prediction model under the input air conditioner placement angle. Figure 9 The diagram shows the prediction effect of the prediction model under the input air supply volume. Figure 10 The diagram shows the prediction effect of the prediction model under the input sweep blade angle. Figure 11The diagram shows the prediction performance of the prediction model under the input wind direction angle (where standing and sitting postures represent horizontal planes at heights of 1.7m and 1.1m above the ground, respectively). In-depth analysis of the prediction model's performance reveals that the selection of output variables and their inherent numerical distribution characteristics significantly impact the model's prediction performance. Different output variables not only differ significantly in units but also have extremely wide numerical ranges. Although data preprocessing steps, such as standardization or normalization, can mitigate the effects of data inhomogeneity and scale differences to some extent, this cannot completely eliminate all the influence of these inherent characteristics, leading to different prediction accuracies when the model handles different output variables. Among the output variables, the prediction model accuracy is generally ranked as follows: temperature, DR, velocity, and PMV, as shown in Tables 2 and 3. PMV values ​​are mostly extremely small values ​​close to 0, thus their values ​​are relatively large when evaluating the average relative error. Table 4 summarizes the average absolute error between predicted and actual values ​​to provide a more comprehensive view of the prediction model's accuracy. The comparison reveals that the prediction results under different input parameters, ranked as follows: air supply volume, air guide vane angle, air sweeping blade angle, and air conditioner placement angle, demonstrate that changes in the geometric model have a greater impact on the model than changes in simulation parameters. Furthermore, the prediction results for cooling and heating conditions show no significant difference. However, for the human standing height plane, due to its proximity to the air supply vent, the prediction accuracy is generally slightly lower than that for the human sitting height plane. These are areas that need to be considered for future model improvement and optimization.

[0091] Table 2 is a summary table of prediction model error values.

[0092] Air conditioner placement angle Minimum 0.01 / Maximum 25.53 Minimum 0.37 / Maximum 5.05 Minimum 0.14 / Maximum 3.26 air volume Minimum 0.01 / Maximum 28.99 Minimum 0.10 / Maximum 5.38 Minimum 0.05 / Maximum 3.57 Sweeping blade angle Minimum 0.03 / Maximum 26.31 Minimum 0.16 / Maximum 5.13 Minimum 0.06 / Maximum 2.89 air guide plate angle Minimum 0.04 / Maximum 28.70 Minimum 0.20 / Maximum 5.45 Minimum 0.07 / Maximum 2.53

[0093] In Table 2, MSE is the mean square error, RMSE is the root mean square error, and MAE is the mean absolute error.

[0094] Table 3 is a summary table of the average relative errors between predicted and actual values.

[0095] Air conditioner placement angle 12.36 0.10 71.43 11.34 air volume 12.89 0.53 10.23 9.50 Sweeping blade angle 11.24 0.27 46.30 9.03 air guide plate angle 23.85 0.65 13.24 13.65

[0096] Since most of the PMV values ​​in Table 3 are extremely small values ​​close to 0, the values ​​are too large when assessing the relative error.

[0097] Table 4 is a summary table of the mean absolute error between predicted and actual values.

[0098] Air conditioner placement angle 0.04 0.29 0.09 2.40 air volume 0.04 0.36 0.11 2.09 Sweeping blade angle 0.09 0.53 0.22 3.73 air guide plate angle 0.04 0.61 0.12 2.16

[0099] The actual value ranges in Table 4 are as follows: speed is 0 to 5 m / s, temperature is 5 to 55℃, PMV is -3 to +3, and DR is 0 to 100%.

[0100] Step 303: Control the air conditioning equipment based on the current environmental parameters of the space where the air conditioning equipment is located and the user's current thermal comfort parameters.

[0101] In embodiments of this disclosure, the current layout parameters and / or current control parameters are adjusted based on the current environmental parameters of the space where the air conditioning equipment is located and the user's current thermal comfort parameters.

[0102] In one optional embodiment of this disclosure, taking a room with a cabinet-type air conditioner as an example, after constructing a target prediction model, this disclosure can optimize the layout and control parameters of the room air conditioner based on the model. In practical applications, the most suitable air conditioning layout and control parameters can be flexibly and efficiently selected according to specific environmental conditions, user preferences, and other personalized needs to adapt to different activity patterns and population distributions. For example, while ensuring rapid cooling / heating of the room, it can also ensure that most areas of the room maintain a relatively comfortable overall feeling; or the layout and control parameters of the air conditioner can be selected under specific usage scenarios, such as office environments where office workers need to sit for long periods of time, which focuses more on the thermal comfort needs of the human sitting height plane. As shown in Table 5, this is a set of room air conditioner layout and control parameters recommended based on the model. This set of parameters is selected based on the thermal comfort needs of the human sitting height plane when the user focuses their attention on the human sitting height plane. Under different schemes, the optimal PMV for cooling at the human sitting height plane is -0.06, and the minimum DR is 10.05%; the optimal PMV for heating is 0.03, and the minimum DR is 4.43%. As shown in Table 6, a similar method was used to analyze the suitability of air conditioner layout and control under the thermal comfort requirements of the human standing height plane. The optimal PMV for cooling mode at the human standing height plane was 0.01, and the lowest DR was 7.39%. The optimal PMV for heating mode was -0.03, and the lowest DR was 3.44%.

[0103] Table 5 shows an example of optimized air conditioner layout and control parameters that focus on the height requirements of the human sitting posture.

[0104] Air conditioner placement angle / ° -15 0 -15 0 Air volume / m3·h-1 1000 1000 1250 1500 Air guide plate position maximum maximum Minimum Minimum Sweeping blade position Highest lowest lowest lowest

[0105] Table 6 shows an example of optimized air conditioner layout and control parameters that focus on the height requirements of the human standing posture.

[0106] Air conditioner placement angle / ° -15 +15 -15 0 Air volume / m3·h-1 1250 1000 1250 1500 Air guide plate position maximum maximum maximum maximum position of the sweeping blades Highest lowest Highest Highest

[0107] This disclosure effectively prevents direct airflow onto the human body by slightly deflecting the air outlet of the air conditioner, reducing discomfort. A reasonable airflow setting should ensure sufficient cooling / heating rates without causing discomfort due to excessive wind speed. Appropriate settings for the air guide vanes and sweeping blades maximize the air diffusion range, helping to create a softer and wider airflow coverage area, reducing localized overcooling / overheating.

[0108] In one optional embodiment of this disclosure, taking a wall-mounted air conditioner as an example, according to... Figure 3 and Figure 4 The illustrated embodiment constructs a target prediction model for wall-mounted air conditioners, which will not be elaborated further here. Wall-mounted air conditioners exhibit unique characteristics in airflow organization and thermal environment prediction due to their different installation locations and usage scenarios. This disclosure can achieve accurate prediction of the thermal environment and thermal comfort of wall-mounted air conditioners by adjusting the model training dataset, including factors such as the air conditioner's installation height and wall reflection. The target prediction model for wall-mounted air conditioners is also constructed using machine learning methods to ensure prediction accuracy and efficiency; the corresponding prediction results can be found in [reference needed]. Figure 12 As shown, Figure 12 This diagram illustrates the prediction performance of the prediction model under different input parameters.

[0109] This disclosure allows for velocity field prediction under an input air supply angle. Specifically, it constructs a target prediction model based on the air supply angle, with a fixed air supply volume of 660 m³ / h and the air conditioner position unchanged. Using the velocity values ​​of 5059 data points at a room height of 1.1 m (corresponding to a seated human height) under seven different air supply angles, a total of 35413 data points are generated. The coordinates, air supply angle, and velocity values ​​are imported into the model for preprocessing and model training. A random forest algorithm is used to construct the prediction model, with a prediction time of approximately 10 seconds. Compared with CFD simulation results, the shape of the velocity contour map can be roughly predicted, but there are significant errors in accuracy and velocity extreme values, possibly due to insufficient data or limitations of the model itself.

[0110] Simultaneously, it can also predict the velocity field under the input air supply volume, that is, analyze the impact of air supply volume on the velocity field at a height of 1.1m in the room, with the air supply angle fixed at 90° and the air conditioner position unchanged. It exports the velocity values ​​of 5059 data points at the same height under seven air supply volumes and imports them into the trained target prediction model. The model prediction time is approximately 20 seconds, and the prediction results can reflect the basic shape of the velocity contour map, but the accuracy still needs improvement, especially in terms of velocity extreme values.

[0111] Furthermore, this disclosure can also analyze the influence of air supply angle and air volume on the temperature field at a height of 1.7m in the room (corresponding to the height of a standing person), and construct target prediction models accordingly. The model prediction speed is relatively fast, but the accuracy is poor in areas with small temperature changes, mainly due to insufficient data points and limitations in model accuracy.

[0112] In summary, after constructing the target prediction model, the layout and control parameters of room air conditioning equipment (cabinet-type, wall-mounted, split-type air conditioners, etc.) can be optimized based on this model. In practical applications, the most suitable air conditioning layout and control parameters can be flexibly and efficiently selected according to specific environmental conditions, user preferences, and other personalized needs to adapt to different activity patterns and population distributions. This disclosure takes the construction of a machine learning-based rapid prediction model for the thermal environment and thermal comfort of cabinet-type and wall-mounted air-conditioned rooms as an example, realizing efficient prediction of the thermal environment of air-conditioned rooms. This provides designers and users with a scientific basis for optimizing air conditioning layout and control parameters, thereby improving living comfort and energy efficiency, and promoting the development of green building and intelligent environmental control technologies.

[0113] Figure 13 This is a schematic diagram of the structure of a model training device 1300 provided in an embodiment of this disclosure. Figure 14 As shown, the model training device includes:

[0114] The first acquisition unit 1310 is used to acquire training data, which includes the layout parameters of the air conditioning equipment, the control parameters of the air conditioning equipment, the environmental parameters of the space where the air conditioning equipment is located, and the thermal comfort parameters of the users in the space where the air conditioning equipment is located.

[0115] Training unit 1320 is used to train the initial prediction model using training data to obtain the target prediction model.

[0116] In some embodiments of this disclosure, the first acquisition unit 1310 is configured to: acquire different layout parameters and different control parameters of at least one type of air conditioning equipment under different modes; and acquire environmental parameters and thermal comfort parameters corresponding to different locations in the space where the air conditioning equipment is located under different layout parameters and different control parameters.

[0117] In some embodiments of this disclosure, the first acquisition unit 1310 is configured to: acquire different layout parameters and different control parameters of at least one type of air conditioning equipment in an experimental environment and / or a simulation environment, respectively; wherein, under different layout parameters and different control parameters, acquiring environmental parameters and thermal comfort parameters corresponding to different positions in the space where the air conditioning equipment is located includes: in an experimental environment, using a data acquisition device to acquire environmental parameters and thermal comfort parameters corresponding to different positions in the space where the air conditioning equipment is located under different layout parameters and different control parameters; and / or, in a simulation environment, using a simulation model to acquire environmental parameters and thermal comfort parameters corresponding to different positions in the space where the air conditioning equipment is located under different layout parameters and different control parameters.

[0118] In some embodiments of this disclosure, the air conditioning equipment includes an air duct in a simulation environment. The air duct includes at least the outer casing of the air conditioning equipment, the enveloping air guide plate of the air conditioning equipment, and the sweeping blades of the air conditioning equipment.

[0119] In some embodiments of this disclosure, the first acquisition unit 1310 is used to: in a simulation environment, use the statistical values ​​of training data that meet preset conditions as data in the training data, wherein the preset conditions are: the change of training data within a preset time period is less than or equal to a preset range.

[0120] In some embodiments of this disclosure, the layout parameters of the air conditioning equipment include at least one of the following: the location of the air conditioning equipment in the space; the installation location of the air conditioning equipment on the wall; the distance between the air conditioning equipment and at least one wall, and the angle between the air conditioning equipment and the wall; the control parameters of the air conditioning equipment include at least one of the following: the air volume supplied by the air conditioning equipment; the angle of the air guide plate of the air conditioning equipment; the angle of the air sweeping blades of the air conditioning equipment; the environmental parameters of the space where the air conditioning equipment is located include at least one of the following: the wind speed at different locations in the space where the air conditioning equipment is located; the temperature; the humidity; the thermal comfort parameters of the user in the space where the air conditioning equipment is located include at least one of the following: the user's thermal comfort index PMV; the user's airflow sensation index DR.

[0121] In some embodiments of this disclosure, the first acquisition unit 1310 is used to: perform feature transformation processing on the layout parameters and control parameters of the air conditioning equipment, wherein the amount of data after feature transformation processing is greater than the amount of data before feature transformation processing; and use the layout parameters and control parameters after feature transformation processing as training data.

[0122] Figure 14 This is a schematic diagram of the structure of an air conditioning control device 1400 provided in an embodiment of this disclosure. Figure 14 As shown, the air conditioning control device includes:

[0123] The second acquisition unit 1410 is used to acquire the current layout parameters and current control parameters of the air conditioning equipment;

[0124] The determination unit 1420 is used to determine the current environmental parameters of the space where the air conditioning equipment is located and the current thermal comfort parameters of the user based on the current layout parameters and the current control parameters, using a target prediction model. The target prediction model is trained based on the existing layout parameters of the air conditioning equipment, the control parameters of the air conditioning equipment, the environmental parameters of the space where the air conditioning equipment is located, and the thermal comfort parameters of the user in the space where the air conditioning equipment is located.

[0125] The control unit 1430 is used to control the air conditioning equipment based on the current environmental parameters of the space where the air conditioning equipment is located and the current thermal comfort parameters of the user.

[0126] In some embodiments of this disclosure, the determining unit 1420 is configured to: determine the usage parameters of the air conditioning equipment, including the current mode of the air conditioning equipment, the user's position and / or posture in the space where the air conditioning equipment is located; and determine the target prediction model corresponding to the usage parameters based on the usage parameters.

[0127] In some embodiments of this disclosure, the control unit 1430 is configured to: adjust the current layout parameters and / or the current control parameters based on the current environmental parameters of the space where the air conditioning equipment is located and the current thermal comfort parameters of the user.

[0128] Corresponding to the methods provided in the above embodiments, this disclosure also provides a model training device and an air conditioning control device. Since the device provided in this disclosure corresponds to the methods provided in the above embodiments, the implementation of the methods is also applicable to the device provided in this embodiment, and will not be described in detail in this embodiment.

[0129] The methods and apparatus provided in the embodiments of this application have been described above. To implement the functions of the methods provided in the embodiments of this application, the electronic device may include a hardware structure and software modules, and may implement the above functions in the form of a hardware structure, software modules, or a hardware structure plus software modules. One of the above functions may be executed in the form of a hardware structure, software modules, or a hardware structure plus software modules.

[0130] Figure 15 This is a block diagram illustrating an electronic device 1500 for implementing the above-described model training and air conditioning control method, according to an exemplary embodiment. For example, the electronic device 1500 may be a mobile phone, computer, messaging device, game console, tablet device, medical device, fitness equipment, personal digital assistant, etc.

[0131] Reference Figure 15The electronic device 1500 may include one or more of the following components: a processing component 1502, a memory 1504, a power supply component 1506, a multimedia component 1508, an audio component 1510, an input / output (I / O) interface 1512, a sensor component 1514, and a communication component 1516.

[0132] Processing component 1502 typically controls the overall operation of electronic device 1500, such as operations associated with display, telephone calls, data communication, camera operation, and recording operations. Processing component 1502 may include one or more processors 1520 to execute instructions to perform all or part of the steps of the methods described above. Furthermore, processing component 1502 may include one or more modules to facilitate interaction between processing component 1502 and other components. For example, processing component 1502 may include a multimedia module to facilitate interaction between multimedia component 1508 and processing component 1502.

[0133] Memory 1504 is configured to store various types of data to support the operation of electronic device 1500. Examples of this data include instructions for any application or method operating on electronic device 1500, contact data, phonebook data, messages, pictures, videos, etc. Memory 1504 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0134] Power supply component 1506 provides power to various components of electronic device 1500. Power supply component 1506 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to electronic device 1500.

[0135] Multimedia component 1508 includes a screen that provides an output interface between electronic device 1500 and a user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touchscreen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors may sense not only the boundaries of touch or swipe actions but also the duration and pressure associated with the touch or swipe operation. In some embodiments, multimedia component 1508 includes a front-facing camera and / or a rear-facing camera. When electronic device 1500 is in an operating mode, such as a shooting mode or a video mode, the front-facing camera and / or rear-facing camera may receive external multimedia data. Each front-facing camera and rear-facing camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

[0136] Audio component 1510 is configured to output and / or input audio signals. For example, audio component 1510 includes a microphone (MIC) configured to receive external audio signals when electronic device 1500 is in an operating mode, such as call mode, recording mode, and voice recognition mode. The received audio signals may be further stored in memory 1504 or transmitted via communication component 1516. In some embodiments, audio component 1510 also includes a speaker for outputting audio signals.

[0137] I / O interface 1512 provides an interface between processing component 1502 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to, home buttons, volume buttons, power buttons, and lock buttons.

[0138] Sensor assembly 1514 includes one or more sensors for providing state assessments of various aspects of electronic device 1500. For example, sensor assembly 1514 may detect the on / off state of electronic device 1500, the relative positioning of components such as the display and keypad of electronic device 1500, changes in position of electronic device 1500 or a component of electronic device 1500, the presence or absence of user contact with electronic device 1500, the orientation or acceleration / deceleration of electronic device 1500, and temperature changes of electronic device 1500. Sensor assembly 1514 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. Sensor assembly 1514 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, sensor assembly 1514 may also include an accelerometer, a gyroscope, a magnetometer, a pressure sensor, or a temperature sensor.

[0139] Communication component 1516 is configured to facilitate wired or wireless communication between electronic device 1500 and other devices. Electronic device 1500 can access wireless networks based on communication standards, such as WiFi, 2G or 3G, 4G LTE, 5G NR (New Radio), or combinations thereof. In one exemplary embodiment, communication component 1516 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, communication component 1516 also includes a near-field communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0140] In an exemplary embodiment, the electronic device 1500 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the methods described above.

[0141] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 1504 including instructions, which can be executed by a processor 1520 of an electronic device 1500 to perform the above-described method. For example, the non-transitory computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0142] Embodiments of this disclosure also propose a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to execute the model training and air conditioning control methods described in the above embodiments of this disclosure.

[0143] Embodiments of this disclosure also provide a computer program product, including a computer program that is executed by a processor using the model training and air conditioning control methods described in the above embodiments of this disclosure.

[0144] Embodiments of this disclosure also propose a chip, such as Figure 16 As shown, the chip includes one or more interface circuits 1601 and one or more processors 1602; the interface circuits are used to receive signals and send signals to the processors, the signals including computer instructions stored in the memory, and when the processor executes the computer instructions, the chip causes the chip to execute the model training and air conditioning control method described in the above embodiments of this disclosure.

[0145] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0146] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "illustrative embodiment," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with an embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0147] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of the preferred embodiments of the invention includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of the invention pertain.

[0148] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processing module, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (control method), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic device, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0149] It should be understood that various parts of the embodiments of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0150] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0151] Furthermore, the functional units in the various embodiments of the present invention can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc.

[0152] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A model training method, characterized in that, The method includes: Acquire training data, which includes layout parameters of the air conditioning equipment, control parameters of the air conditioning equipment, environmental parameters of the space where the air conditioning equipment is located, and thermal comfort parameters of users in the space where the air conditioning equipment is located. The environmental parameters and thermal comfort parameters include parameter values ​​corresponding to multiple different positions on the human standing height plane and the human sitting height plane in the space where the air conditioning equipment is located. Using the training data, the initial prediction model is trained to obtain the target prediction model, which is used to predict the environmental parameters of the space where the air conditioning equipment is located and the thermal comfort parameters of the user.

2. The method according to claim 1, characterized in that, The acquisition of training data includes: Acquire different layout parameters and different control parameters of at least one type of air conditioning equipment under different modes; Under different layout parameters and different control parameters, environmental parameters and thermal comfort parameters corresponding to different locations in the space where the air conditioning equipment is located are obtained respectively.

3. The method according to claim 2, characterized in that, The acquisition of different layout parameters and different control parameters of at least one type of air conditioning equipment includes: Different layout parameters and different control parameters of the at least one type of air conditioning equipment were obtained in experimental and / or simulation environments, respectively. The step of acquiring environmental parameters and thermal comfort parameters corresponding to different locations in the space where the air conditioning equipment is located under different layout parameters and different control parameters includes: In an experimental environment, using a data acquisition device, environmental parameters and thermal comfort parameters corresponding to different locations in the space where the air conditioning equipment is located under different layout parameters and different control parameters are obtained; and / or, In a simulation environment, a simulation model is used to obtain environmental parameters and thermal comfort parameters corresponding to different locations in the space where the air conditioning equipment is located under different layout parameters and different control parameters.

4. The method according to claim 3, characterized in that, The air conditioning equipment in the simulation environment includes an air duct, which includes at least the outer shell of the air conditioning equipment, the enveloping air guide plate of the air conditioning equipment, and the sweeping blades of the air conditioning equipment.

5. The method according to claim 3 or 4, characterized in that, The method further includes: In the simulation environment, the statistical values ​​of the training data that meet the preset conditions are used as the data in the training data. The preset conditions are: the change of the training data within a preset time period is less than or equal to a preset range.

6. The method according to any one of claims 1 to 4, characterized in that, The layout parameters of the air conditioning equipment include at least one of the following: the position of the air conditioning equipment in the space; the installation position of the air conditioning equipment on the wall; the distance between the air conditioning equipment and at least one wall; and the angle between the air conditioning equipment and the wall. The control parameters of the air conditioning equipment include at least one of the following: the air supply volume of the air conditioning equipment; the angle of the air guide plate of the air conditioning equipment; and the angle of the air sweeping blades of the air conditioning equipment. The environmental parameters of the space where the air conditioning equipment is located include at least one of the following: wind speed at different locations in the space where the air conditioning equipment is located; temperature; humidity; The thermal comfort parameters of the user in the space where the air conditioning equipment is located include at least one of the following: the user's thermal comfort index PMV; and the user's airflow sensation index DR.

7. The method according to claim 6, characterized in that, The method further includes: The layout parameters and control parameters of the air conditioning equipment are subjected to feature transformation processing, wherein the amount of data after feature transformation processing is greater than the amount of data before feature transformation processing; The layout parameters and control parameters after the feature transformation are used as the training data.

8. An air conditioning control method, characterized in that, The method includes: Obtain the current layout parameters and current control parameters of the air conditioning equipment; Based on the current layout parameters and the current control parameters, a target prediction model is used to determine the current environmental parameters of the space where the air conditioning equipment is located and the current thermal comfort parameters of the user. The target prediction model is trained based on the existing layout parameters of the air conditioning equipment, the control parameters of the air conditioning equipment, the environmental parameters of the space where the air conditioning equipment is located, and the thermal comfort parameters of the user in the space where the air conditioning equipment is located. The environmental parameters and the thermal comfort parameters include parameter values ​​corresponding to multiple different positions on the human standing height plane and the human sitting height plane in the space where the air conditioning equipment is located. The air conditioning equipment is controlled based on the current environmental parameters of the space where the air conditioning equipment is located and the user's current thermal comfort parameters.

9. The air conditioning control method according to claim 8, characterized in that, The method further includes: Determine the usage parameters of the air conditioning equipment, including the current mode of the air conditioning equipment and the user's position and / or posture in the space where the air conditioning equipment is located; Based on the usage parameters, determine the target prediction model corresponding to the usage parameters.

10. The air conditioning control method according to claim 8 or 9, characterized in that, The control of the air conditioning equipment based on the current environmental parameters of the space where the air conditioning equipment is located and the user's current thermal comfort parameters includes: The current layout parameters and / or the current control parameters are adjusted based on the current environmental parameters of the space where the air conditioning equipment is located and the user's current thermal comfort parameters.

11. A model training device, characterized in that, include: The first acquisition unit is used to acquire training data, which includes layout parameters of the air conditioning equipment, control parameters of the air conditioning equipment, environmental parameters of the space where the air conditioning equipment is located, and thermal comfort parameters of the user in the space where the air conditioning equipment is located. The environmental parameters and the thermal comfort parameters include parameter values ​​corresponding to multiple different positions on the human standing height plane and the human sitting height plane in the space where the air conditioning equipment is located. The training unit is used to train the initial prediction model using the training data to obtain a target prediction model, which is used to predict the environmental parameters of the space where the air conditioning equipment is located and the thermal comfort parameters of the user.

12. An air conditioning control device, characterized in that, include: The second acquisition unit is used to acquire the current layout parameters and current control parameters of the air conditioning equipment; The determining unit is used to determine the current environmental parameters of the space where the air conditioning equipment is located and the current thermal comfort parameters of the user based on the current layout parameters and the current control parameters, using a target prediction model. The target prediction model is trained based on the existing layout parameters of the air conditioning equipment, the control parameters of the air conditioning equipment, the environmental parameters of the space where the air conditioning equipment is located, and the thermal comfort parameters of the user in the space where the air conditioning equipment is located. The environmental parameters and the thermal comfort parameters include parameter values ​​corresponding to multiple different positions on the human standing height plane and the human sitting height plane in the space where the air conditioning equipment is located. The control unit is used to control the air conditioning equipment based on the current environmental parameters of the space where the air conditioning equipment is located and the user's current thermal comfort parameters.

13. An air conditioning device, characterized in that, Includes the model training device as described in claim 11 and / or the air conditioning control device as described in claim 12.

14. An electronic device, characterized in that, include: A processor and a memory for storing a computer program capable of running on the processor, wherein the processor, when running the computer program, performs the method of any one of claims 1-7 or 8-10.

15. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-7 or 8-10.

Images