Indoor temperature prediction method and device, air conditioning equipment and storage medium

Abstract

The application provides an indoor temperature prediction method, an indoor temperature prediction device, an air conditioning equipment and a storage medium. The indoor temperature prediction method comprises the following steps: acquiring an indoor temperature sequence of a current period, an outdoor temperature sequence, an air conditioning equipment cold output value at a current time and a current date and time; calculating a target indoor temperature at a next time through a temperature prediction model according to the indoor temperature sequence of the current period, the outdoor temperature sequence and the air conditioning equipment cold output value at the current time, and the temperature prediction model is constructed by a heat balance equation and obtained through historical temperature data training. In this way, the temperature prediction model is constructed and trained through the heat balance equation representing heat change, and the heat balance equation is only established by the basic rules of physical heat transfer, so that the temperature prediction model does not depend on detailed understanding of the target building when modeling, thereby improving the automation degree and reusability of the indoor temperature prediction method, and improving the prediction accuracy.

Description

Technical Field

[0001] This invention relates to the field of air conditioning equipment technology, and in particular to an indoor temperature prediction method, an indoor temperature prediction device, an air conditioning device, and a computer-readable storage medium. Background Technology

[0002] Model predictive control (MMC) is a highly efficient operational control method. When applied to the terminal control of air conditioning systems, it can significantly unlock the energy-saving potential of these systems. However, the effectiveness of MMC in air conditioning system terminal control heavily depends on the accuracy of the building's indoor temperature change prediction model.

[0003] Currently, methods for predicting indoor building temperatures mainly rely on three types of models: white-box models, gray-box models, and black-box models. White-box models are based on the actual conditions of the target building, replicating its physical model in a computer to simulate indoor thermal processes and thus predict indoor temperature. Gray-box models are derived from the abstraction and simplification of actual building conditions and physical rules, with most parameters trained using system operating data. Black-box models ignore the specific heat transfer processes inside the building, directly training a purely mathematical model without physical meaning using the input and output data of the thermal system.

[0004] However, white-box and gray-box models are highly coupled with the target building, requiring separate modeling for each target building and lacking reusability, while black-box models have high requirements for the quality of training data and low extrapolation prediction accuracy. Summary of the Invention

[0005] In view of this, embodiments of the present invention provide an indoor temperature prediction method, an indoor temperature prediction device, an air conditioning unit, and a non-volatile computer-readable storage medium.

[0006] The indoor temperature prediction method according to embodiments of the present invention includes:

[0007] Obtain the indoor temperature sequence, outdoor temperature sequence, cooling output value of the air conditioning equipment at the current moment, and the current date and time;

[0008] The temperature prediction model predicts the target indoor temperature for the next moment based on the indoor temperature sequence, the outdoor temperature sequence, the cooling output value of the air conditioning equipment at the current time, and the current date and time. The temperature prediction model is constructed by the heat balance equation and trained using historical temperature data.

[0009] In some embodiments, before obtaining the indoor temperature sequence, outdoor temperature sequence, and cooling capacity output value of the air conditioning equipment at the current time, the indoor temperature prediction method further includes:

[0010] Acquire indoor heat transfer data and historical temperature data;

[0011] A heat balance equation for indoor air is constructed based on the heat transfer data.

[0012] An initial prediction model is constructed based on the historical temperature data and the heat balance equation.

[0013] The initial prediction model is trained using a machine learning algorithm to generate the temperature prediction model.

[0014] In some implementations, constructing a heat balance equation for indoor air based on the heat transfer data includes:

[0015] The first heat change equation is constructed based on the heat, heat capacity and temperature of indoor air. The total heat change includes the change in air conditioning heat, the change in building envelope heat, the change in air convection heat, the change in solar radiation heat and the change in indoor heat increase.

[0016] A second heat change equation is constructed based on the thermal resistance of the building envelope and the outdoor air temperature.

[0017] Based on the changing patterns of air convection heat, solar radiation heat, and indoor heat increase, a third heat change equation is constructed, which is the sum of the air convection heat, solar radiation heat, and indoor heat increase.

[0018] The heat balance equation is constructed based on the first heat change equation, the second heat change equation, and the third heat change equation.

[0019] In some implementations, an initial prediction model is constructed based on the historical temperature data and the heat balance equation, including:

[0020] The initial prediction model is generated by solving the heat balance equation based on the parameter estimation algorithm and the historical temperature data. The parameter estimation algorithm includes one of the least squares estimation method, maximum likelihood estimation method, and Bayesian estimation method.

[0021] In some implementations, the initial prediction model is trained using a machine learning algorithm to generate the temperature prediction model, including:

[0022] A residual model is generated by fitting the predicted and measured values ​​of the initial prediction model based on the historical temperature data using a machine learning algorithm.

[0023] The temperature prediction model is generated by combining the residual model and the initial prediction model.

[0024] In some embodiments, the indoor temperature prediction method includes:

[0025] Predict the cooling capacity of the air conditioning equipment for the next moment based on the current indoor temperature and the target indoor temperature;

[0026] The air conditioning equipment is controlled according to its cooling capacity so that the indoor temperature at the next moment reaches the target indoor temperature.

[0027] In some embodiments, controlling the air conditioning unit according to its cooling capacity to bring the indoor temperature to the target indoor temperature at the next moment includes:

[0028] The chilled water flow rate and air volume of the air conditioning equipment are adjusted according to the cooling capacity of the air conditioning equipment using a closed-loop control method so that the indoor temperature at the next moment reaches the target indoor temperature.

[0029] The indoor temperature prediction device according to the embodiments of this application includes

[0030] The acquisition module is used to acquire the indoor temperature sequence, outdoor temperature sequence, and cooling output value of the air conditioning equipment at the current time period.

[0031] The prediction module is used to calculate the target indoor temperature for the next moment based on the indoor temperature sequence, the outdoor temperature sequence and the cooling output value of the air conditioning equipment at the current moment using a temperature prediction model. The temperature prediction model is constructed by the heat balance equation and trained using historical temperature data.

[0032] The air conditioning device according to the embodiments of this application includes a processor and a memory. The memory stores a computer program, which, when executed by the processor, causes the processor to implement the indoor temperature prediction method described in any of the above claims.

[0033] The non-volatile computer-readable storage medium of the computer program of the embodiments of this application enables the processor to implement the indoor temperature prediction method described in any of the above claims when the computer program is executed by a processor.

[0034] In the indoor temperature prediction method of this application, the temperature prediction model is constructed and trained using a heat balance equation characterizing heat changes. This heat balance equation is derived solely from the basic rules of physical heat transfer, allowing the temperature prediction model to be built without relying on detailed knowledge of the target building and improving model accuracy. Based on the current indoor temperature sequence, outdoor temperature sequence, and the current cooling output of the air conditioning equipment, the temperature prediction model can accurately predict the indoor temperature at the next moment, thereby controlling the air conditioning equipment to output the corresponding cooling capacity to ensure the indoor temperature meets user needs.

[0035] Additional aspects and advantages of the embodiments of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0036] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the following description of embodiments taken in conjunction with the accompanying drawings, wherein:

[0037] Figure 1 This is a flowchart illustrating an indoor temperature prediction method according to certain embodiments of the present invention.

[0038] Figure 2 This is a schematic diagram of the indoor temperature prediction device according to certain embodiments of the present invention;

[0039] Figure 3 This is a flowchart illustrating an indoor temperature prediction method according to certain embodiments of the present invention.

[0040] Figure 4 This is a flowchart illustrating an indoor temperature prediction method according to certain embodiments of the present invention. Detailed Implementation

[0041] Embodiments of the present invention are described in detail below, examples of which are shown 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 described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0042] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," and "counterclockwise," etc., indicating orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of the stated features. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0043] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection, an electrical connection, or a connection that allows for communication; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0044] In this invention, unless otherwise explicitly specified and limited, "above" or "below" the second feature can include direct contact between the first and second features, or contact between the first and second features through another feature between them. Furthermore, "above," "over," and "on top" of the second feature includes the first feature directly above or diagonally above the second feature, or simply indicates that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature includes the first feature directly below or diagonally below the second feature, or simply indicates that the first feature is at a lower horizontal level than the second feature.

[0045] The following disclosure provides many different embodiments or examples for implementing various structures of the invention. To simplify the disclosure, specific examples of components and arrangements are described below. These are merely examples and are not intended to limit the invention. Furthermore, reference numerals and / or letters may be repeated in different examples; such repetition is for simplification and clarity and does not in itself indicate a relationship between the various embodiments and / or arrangements discussed. In addition, examples of various specific processes and materials are provided in this invention, but those skilled in the art will recognize the application of other processes and / or the use of other materials.

[0046] Current methods for predicting building indoor temperature often employ white-box models, which require individual modeling for each target building. This results in extremely low model reusability, and the modeling process necessitates determining numerous parameters, requiring significant time and manpower in practice. Gray-box models, while reducing the difficulty of parameter determination, still partially rely on the characteristic information of the target building, leading to poor reusability. Black-box models, on the other hand, do not require domain knowledge and can largely rely on computer automation, offering high efficiency and flexibility. However, they are highly dependent on the quality and richness of training data. When encountering new scenarios not covered by the training dataset, the predictive accuracy of these models is often low, and they may produce anomalous results that violate domain knowledge.

[0047] In view of this, please refer toFigure 1 This application provides an indoor temperature prediction method, which includes:

[0048] S10: Obtain the indoor temperature sequence, outdoor temperature sequence, cooling output value of the air conditioning equipment at the current time, and the current date and time;

[0049] S20: The temperature prediction model predicts the target indoor temperature for the next moment based on the current indoor temperature sequence, outdoor temperature sequence, the current cooling output value of the air conditioning equipment, and the current date and time. The temperature prediction model is constructed by the heat balance equation and trained using historical temperature data.

[0050] Please see Figure 2 This application also provides an indoor temperature prediction device 100, and the above-described indoor temperature prediction method can be applied to the indoor temperature prediction device 100.

[0051] The indoor temperature prediction device 100 includes an acquisition module 10 and a prediction module 20. S10 can be implemented by the acquisition module 10, and S20 can be implemented by the prediction module 20. That is, the acquisition module 10 is used to acquire the indoor temperature sequence, outdoor temperature sequence, cooling output value of the air conditioning equipment at the current time, and the current date and time. The prediction module 20 is used to calculate the target indoor temperature at the next moment based on the indoor temperature sequence, outdoor temperature sequence, cooling output value of the air conditioning equipment at the current time, and the current date and time through a temperature prediction model. The temperature prediction model is constructed by the heat balance equation and trained by historical temperature data.

[0052] This application also provides an air conditioning device, which includes a processor and a memory. The memory stores a computer program. When the computer program is executed by the processor, the processor is used to implement the above-mentioned indoor temperature prediction method. That is, the processor is used to obtain the indoor temperature sequence and outdoor temperature sequence of the current time period, the cooling output value of the air conditioning device at the current moment, and the current date and time. It is also used to calculate the target indoor temperature at the next moment based on the indoor temperature sequence and outdoor temperature sequence of the current time period, the cooling output value of the air conditioning device at the current moment, and the current date and time through a temperature prediction model. The temperature prediction model is constructed by the heat balance equation and trained by historical temperature data.

[0053] In the indoor temperature prediction method of this application, the temperature prediction model is constructed and trained using a heat balance equation characterizing heat changes. This heat balance equation is derived solely from the basic rules of physical heat transfer, allowing the temperature prediction model to be built without relying on detailed knowledge of the target building and improving model accuracy. Based on the current indoor temperature sequence, outdoor temperature sequence, and the current cooling output of the air conditioning equipment, the temperature prediction model can accurately predict the indoor temperature at the next moment, thereby controlling the air conditioning equipment to output the corresponding cooling capacity to ensure the indoor temperature meets user needs.

[0054] An indoor temperature sequence refers to multiple indoor temperatures measured over a period of time. For example, an indoor temperature sequence could be three indoor temperatures measured within ten minutes. An outdoor temperature sequence refers to multiple outdoor temperatures measured over a period of time.

[0055] The air conditioning equipment can be commercial or residential. For example, the air conditioning equipment can be a central air conditioning system. The air conditioning equipment includes a temperature prediction device, which can control the cooling output of the air conditioner to regulate the indoor temperature.

[0056] The temperature prediction device 100 may be a discrete component assembled in a certain way to have the aforementioned functions, or a chip having the aforementioned functions in the form of an integrated circuit, or a computer software code segment that enables the computer to have the aforementioned functions when running on a computer.

[0057] Temperature prediction models can be machine learning models. These models are constructed based on the heat balance equation and trained using historical temperature data. Specifically, historical temperature data is divided into training and testing sets. An initial prediction model is generated using machine learning on the training set data. This initial model is then applied to the testing set for prediction. The best-performing model on the testing set is selected as the final temperature prediction model. Here, a machine learning model is an algorithmic expression that can search for patterns or make predictions by analyzing massive amounts of data. Historical temperature data can include historical operational and environmental data of buildings, such as indoor and outdoor temperature data, the cooling capacity of the building's air conditioning equipment, and historical data on measurement time and date.

[0058] Specifically, the indoor temperature prediction method is used to predict the indoor temperature of a building. By installing temperature sensors inside the building, these sensors measure the indoor temperature at regular intervals and transmit the data to a temperature prediction model, allowing the model to obtain the indoor temperature sequence at any given time. Similarly, by installing temperature sensors outside the building, these sensors measure the outdoor temperature at regular intervals and transmit the data to the temperature prediction model, allowing the model to obtain the outdoor temperature sequence at any given time. Furthermore, by installing heat meters at the end of the building's air conditioning system, the cooling output of the air conditioning system can be measured, meaning the cooling output value of the air conditioning system at any given time can be obtained and transmitted to the temperature prediction model.

[0059] Furthermore, the temperature prediction model can predict the target indoor temperature at the next moment based on the current indoor temperature sequence, outdoor temperature sequence, current air conditioning equipment cooling output value, and current date and time. Then, it can calculate based on the target indoor temperature at the next moment and the current indoor temperature, so that the temperature prediction device 100 can control the air conditioning equipment to output cooling capacity, so that the indoor temperature at the next moment reaches the target indoor temperature.

[0060] It should be noted that historical temperature data can be obtained based on the current date and time. For example, historical operational and environmental data of buildings at the current date and time in previous years can be obtained.

[0061] In this way, a temperature prediction model is constructed based on the heat balance equation and trained using historical temperature data, which improves the automation and reusability of the indoor temperature prediction method. The temperature prediction device 100 calculates based on the target indoor temperature and the indoor temperature, thereby controlling the output of cooling capacity of the air conditioning equipment to make the indoor temperature reach the target indoor temperature and meet the user's demand for indoor temperature.

[0062] Please see Figure 3 In some embodiments, prior to S10, the indoor temperature prediction method further includes:

[0063] S01: Acquire heat transfer data and historical indoor temperature data;

[0064] S02: Construct the heat balance equation for indoor air based on heat transfer data;

[0065] S03: Construct an initial prediction model based on historical temperature data and heat balance equations;

[0066] S04: Train the initial prediction model using a machine learning algorithm to generate a temperature prediction model.

[0067] In some embodiments, the indoor temperature prediction device 100 further includes a first construction module 30, a second construction module 40, and a training module 50. S01 can be implemented by the acquisition module 10, S02 can be implemented by the first construction module 30, S03 can be implemented by the second construction module 40, and S04 can be implemented by the training module 50. That is, the acquisition module 10 is used to acquire heat transfer data and historical indoor temperature data, the first construction module 30 is used to construct an indoor air heat balance equation based on the heat transfer data, the second construction module 40 is used to construct an initial prediction model based on the historical temperature data and the heat balance equation, and the training module 50 is used to train the initial prediction model using a machine learning algorithm to generate a temperature prediction model.

[0068] In some implementations, the processor is used to acquire heat transfer data and historical indoor temperature data, to construct an indoor air heat balance equation based on the heat transfer data, to construct an initial prediction model based on the historical temperature data and the heat balance equation, and to train the initial prediction model using a machine learning algorithm to generate a temperature prediction model.

[0069] Specifically, heat transfer data can include data such as the cooling output of air conditioning equipment at a certain moment, heat conduction of building envelope, heat exchange between indoor and outdoor air convection, solar radiation, and changes in indoor heat caused by indoor occupancy and equipment operation. Based on the heat transfer data, an indoor air heat balance equation can be constructed.

[0070] First, the indoor temperature prediction device 100 can construct a first heat change equation based on the heat, heat capacity, and temperature of the indoor air. The total heat change includes changes in air conditioning heat, building envelope heat, air convection heat, solar radiation heat, and indoor heat increase.

[0071]

[0072] Among them, Q IA Q represents the heat of indoor air. 空调 Q is the cooling capacity output of the air conditioning equipment at that moment. 围护结构 For heat conduction of the building envelope at that moment, Q 空气对流 Q represents the indoor and outdoor air convection heat transfer at that moment. 太阳辐射 Q represents the solar radiation at that moment. 室内热增 C represents the change in indoor heat caused by indoor human activity and equipment operation at that moment. IA For the heat capacity of indoor air, T IA The temperature of the indoor air.

[0073] According to Fourier's law, there is a delay in the process of outdoor heat being conducted to the interior through the building envelope. The indoor temperature prediction device 100 constructs a second heat change equation for the building envelope heat based on the thermal resistance of the building envelope and the outdoor air temperature.

[0074]

[0075] Among them, a i The weights for heat transfer at different times are given by R, where R is the thermal resistance of the building envelope, and T is the weight of heat transfer at different times. OA This refers to the outdoor air temperature.

[0076] The indoor temperature prediction device 100 constructs a third heat change equation based on the changing patterns of air convection heat, solar radiation heat, and indoor heat increase:

[0077]

[0078] Among them, b j c j Both d and d are undetermined constants. Where J is the unit period length and J is the number of terms in the Fourier expansion.

[0079] Secondly, the indoor temperature prediction device 100 can construct a heat balance equation by combining the first heat change equation, the second heat change equation, and the third heat change equation:

[0080]

[0081] In practical applications, the indoor air heat capacity C IA Assuming the thermal resistance R of the building envelope is constant, combining the undetermined constants in each term yields:

[0082]

[0083] Among them, T IA T oA , t, Q 空调 All of these are known quantities and can be obtained from historical temperature data. N and J can be determined by parameter tuning. A i B j C j D and E are unknown constants to be identified.

[0084] Furthermore, the indoor temperature prediction device 100 can calculate the unknown constant A by solving the heat balance equation based on parameter estimation and historical temperature data. i B j C jThe initial prediction model is generated by calculating the values ​​of D and E. The specific values ​​of the unknown constants can be calculated based on the historical temperature data of the building, and are not limited here.

[0085] It should be noted that parameter estimation is a method of calculating system model parameters using the system's input and output data when the system model structure is known. Parameter estimation can be one of the following: least squares estimation, maximum likelihood estimation, and Bayesian estimation. For example, in order to select parameter estimates that make the model output as close as possible to the system output, the least squares method can use the sum of squares of the errors between the model and the system output to measure the degree of closeness. The parameter value that minimizes the sum of squares of the errors is the desired estimate.

[0086] Finally, the indoor temperature prediction device 100 uses a machine learning algorithm to fit the initial prediction model with the predicted and measured values ​​generated from historical temperature data, thus generating a residual model. This reduces the error between the predicted and measured values. The residual model can predict the prediction error at a given moment based on the cooling output of the air conditioning equipment and indoor and outdoor temperature data. By combining the residual model with the initial prediction model, a temperature prediction model can be generated.

[0087] In this way, an indoor air heat balance equation is constructed based on heat transfer data. The heat balance equation is combined with historical temperature data to construct an initial prediction model. Machine learning algorithms are used to train the initial prediction model to generate a temperature prediction model. The temperature prediction model is then used to calculate the indoor temperature at the next moment, which improves the automation and reusability of the indoor temperature prediction method and also improves the accuracy of the prediction.

[0088] Please see Figure 4 In some implementations, the indoor temperature prediction method further includes:

[0089] S30: Calculate the cooling capacity of the air conditioning equipment for the next moment based on the current indoor temperature and the target indoor temperature;

[0090] S40: Control the air conditioning equipment according to its cooling capacity so that the indoor temperature reaches the target indoor temperature in the next moment.

[0091] In some implementations, the processor is used to calculate the cooling capacity of the air conditioning unit for the next moment based on the current indoor temperature and the target indoor temperature, and to control the air conditioning unit according to the cooling capacity of the air conditioning unit so that the indoor temperature for the next moment reaches the target indoor temperature.

[0092] Specifically, the indoor temperature is obtained by an indoor temperature sensor. The current indoor temperature is output to a temperature prediction model, which can calculate the indoor temperature at the next moment. Based on the indoor temperature at the next moment and the target indoor temperature, the cooling capacity of the air conditioning equipment at the next moment can be calculated. Then, the air conditioning equipment can control the output of the corresponding cooling capacity according to the cooling capacity at the next moment, so that the indoor temperature at the next moment reaches the target indoor temperature.

[0093] It should be noted that when the air conditioning equipment obtains the cooling capacity signal for the next moment, it can adjust the chilled water flow and air volume according to the cooling capacity using a closed-loop control method, so that the indoor temperature reaches the target indoor temperature in the next moment. The closed-loop control method controls based on information about changes in system output; that is, it compares the deviation between the system behavior and the desired behavior and eliminates the deviation to obtain the expected system performance. For example, the air conditioning equipment uses an indoor temperature sensor to detect the indoor temperature in real time. When the indoor temperature approaches the target indoor temperature, the air conditioning equipment will reduce its cooling capacity output; when the indoor temperature reaches the target indoor temperature, the air conditioning equipment will stop outputting cooling capacity.

[0094] In this way, the indoor temperature prediction method calculates the cooling capacity of the air conditioning equipment based on the current indoor temperature and the target indoor temperature, and controls the output of the air conditioning equipment to ensure that the indoor temperature reaches the target indoor temperature in the next moment, thus meeting the user's demand for the target indoor temperature.

[0095] This application also provides a non-volatile computer-readable storage medium including a computer program, which, when executed by a processor, causes the processor to perform any of the above-mentioned indoor temperature prediction methods. The storage medium may be a magnetic disk, optical disk, read-only memory (ROM), etc.

[0096] 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 the embodiment or example is included in at least one embodiment or example of the 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.

[0097] The above embodiments merely illustrate several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for predicting indoor temperature, characterized in that, The indoor temperature prediction method includes: Obtain the indoor temperature sequence, outdoor temperature sequence, cooling output value of the air conditioning equipment at the current moment, and the current date and time; The temperature prediction model predicts the target indoor temperature for the next moment based on the indoor temperature sequence, the outdoor temperature sequence, the cooling output value of the air conditioning equipment at the current time, and the current date and time. The temperature prediction model is constructed by the heat balance equation and trained using historical temperature data. Before obtaining the indoor temperature sequence, outdoor temperature sequence, and air conditioning unit cooling capacity output value for the current time period, the indoor temperature prediction method further includes: Acquire indoor heat transfer data and historical temperature data; A heat balance equation for indoor air is constructed based on the heat transfer data. An initial prediction model is constructed based on the historical temperature data and the heat balance equation. The initial prediction model is trained using a machine learning algorithm to generate the temperature prediction model; Based on the heat transfer data, an indoor air heat balance equation is constructed, including: The first heat change equation is constructed based on the heat, heat capacity and temperature of indoor air. The total heat change includes the change in air conditioning heat, the change in building envelope heat, the change in air convection heat, the change in solar radiation heat and the change in indoor heat increase. A second heat change equation is constructed based on the thermal resistance of the building envelope and the outdoor air temperature. Based on the changing patterns of air convection heat, solar radiation heat, and indoor heat increase, a third heat change equation is constructed, which is the sum of the air convection heat, solar radiation heat, and indoor heat increase. The heat balance equation is constructed based on the first heat change equation, the second heat change equation, and the third heat change equation.

2. The indoor temperature prediction method according to claim 1, characterized in that, An initial prediction model is constructed based on the historical temperature data and the heat balance equation, including: The initial prediction model is generated by solving the heat balance equation based on the parameter estimation algorithm and the historical temperature data. The parameter estimation algorithm includes one of the least squares estimation method, maximum likelihood estimation method, and Bayesian estimation method.

3. The indoor temperature prediction method according to claim 1, characterized in that, The initial prediction model is trained using a machine learning algorithm to generate the temperature prediction model, including: A residual model is generated by fitting the predicted and measured values ​​of the initial prediction model based on the historical temperature data using a machine learning algorithm. The temperature prediction model is generated by combining the residual model and the initial prediction model.

4. The indoor temperature prediction method according to claim 1, characterized in that, The indoor temperature prediction method includes: Predict the cooling capacity of the air conditioning equipment for the next moment based on the current indoor temperature and the target indoor temperature; The air conditioning equipment is controlled according to its cooling capacity so that the indoor temperature at the next moment reaches the target indoor temperature.

5. The indoor temperature prediction method according to claim 4, characterized in that, The step of controlling the air conditioning equipment according to its cooling capacity to make the indoor temperature reach the target indoor temperature at the next moment includes: The chilled water flow rate and air volume of the air conditioning equipment are adjusted according to the cooling capacity of the air conditioning equipment using a closed-loop control method so that the indoor temperature at the next moment reaches the target indoor temperature.

6. An indoor temperature prediction device, characterized in that, To implement the indoor temperature prediction method according to any one of claims 1-5, the method comprises: The acquisition module is used to acquire the indoor temperature sequence, outdoor temperature sequence, and cooling output value of the air conditioning equipment at the current time period. The prediction module is used to predict the target indoor temperature at the next moment based on the indoor temperature sequence, the outdoor temperature sequence and the cooling output value of the air conditioning equipment at the current moment using a temperature prediction model. The temperature prediction model is constructed by the heat balance equation and trained using historical temperature data.

7. An air conditioning device, characterized in that, It includes a processor and a memory, the memory storing a computer program that, when executed by the processor, causes the processor to implement the indoor temperature prediction method according to any one of claims 1-5.

8. A non-volatile computer-readable storage medium containing a computer program, characterized in that, When the computer program is executed by a processor, the processor implements the indoor temperature prediction method according to any one of claims 1-5.

Images