Real-time inversion method and system for building envelope heat transfer coefficient

Abstract

The application belongs to the technical field of building energy saving, and provides a real-time inversion method and system for the heat transfer coefficient of a building envelope, comprising: obtaining surface parameters and environmental parameters of the building envelope; based on the obtained parameters and a physical neural network model, taking the minimum of a joint loss function based on a physical mechanism as the target, and inversely obtaining the optimal thermal conductivity coefficient of the building envelope; and calculating the heat transfer coefficient of the building envelope according to the obtained optimal thermal conductivity coefficient of the building envelope, thereby completing the real-time inversion of the heat transfer coefficient of the building envelope.

Description

Technical Field

[0001] This invention belongs to the field of building energy conservation technology, specifically relating to a real-time inversion method and system for the heat transfer coefficient of a building envelope. Background Technology

[0002] The statements in this section are merely background information related to the present invention and do not necessarily constitute prior art.

[0003] Building energy conservation is a key link in achieving dual carbon goals, and the heat transfer coefficient of the wall is a core indicator for evaluating the thermal performance of the building envelope.

[0004] Currently, the main methods for measuring the thermal performance of building envelopes include finite element analysis, steady-state methods, and transient methods. Steady-state methods, such as the heat box method and heat flow meter method, cannot reflect the impact of fluctuations in outdoor meteorological parameters (such as solar radiation and wind speed) on the heat transfer process. They require constant environmental conditions, have testing cycles lasting from hours to days, and cannot reflect the true performance under dynamic conditions. Furthermore, the equipment is bulky and complex to deploy on-site, failing to meet real-time monitoring needs. Transient methods, such as infrared thermography, are affected by surface emissivity in terms of accuracy, and the equipment is expensive. Traditional finite element analysis methods, such as numerical inversion, rely on pre-defined wall layer structures, resulting in high computational complexity and difficulty in real-time on-site application. When the actual wall structure is unknown, the inversion results can deviate by more than 20%. These traditional methods are particularly inconvenient when assessing the thermal performance of large-scale building envelopes, often requiring layered sensor deployment, which is complex and costly. Summary of the Invention

[0005] To address the aforementioned issues, this invention proposes a real-time inversion method and system for the heat transfer coefficient of building envelopes. By constructing a physically constrained end-to-end inversion framework and processing data that changes over time under dynamic conditions, the heat transfer coefficient of the wall can be solved in real time without pre-setting the wall's layered structure. This enables rapid and accurate evaluation of the wall's thermal insulation performance under various environmental conditions, providing data support for energy-saving renovations.

[0006] According to some embodiments, the first aspect of the present invention provides a real-time inversion method for the heat transfer coefficient of a building envelope, employing the following technical solution:

[0007] A real-time inversion method for the heat transfer coefficient of a building envelope includes:

[0008] Obtain surface and environmental parameters of the building envelope;

[0009] Based on the acquired parameters and physical neural network model, the optimal thermal conductivity of the building envelope is obtained by inversion with the goal of minimizing the joint loss function based on physical mechanism.

[0010] The heat transfer coefficient of the building envelope is calculated based on the optimal thermal conductivity obtained, and the heat transfer coefficient of the building envelope is inverted in real time.

[0011] As a further technical limitation, the joint loss function based on physical mechanisms includes the Fourier equation residual loss function, the inner wall boundary condition loss function, and the outer wall boundary condition loss function; that is, the joint loss function based on physical mechanisms. for ;in, The Fourier equation residual loss function, , T The temperature inside the building envelope. t For time, k The thermal conductivity of the building envelope. c The specific heat capacity of the building envelope. ρ The material density of the building envelope; These are the weighting coefficients of the Fourier equation residual loss function; The loss function is the boundary condition function for the outer wall surface. , h out The convective heat transfer coefficient of the building envelope exterior wall. T L Temperature of the inner wall surface of the building envelope. T out The air temperature outside the building envelope. I sun Solar radiation intensity, a Solar radiation absorption rate of building envelope materials; These are the weighting coefficients of the loss function for the outer wall boundary conditions; The loss function is the boundary condition function for the inner wall surface. , h in The convective heat transfer coefficient of the inner wall of the building envelope. T in The air temperature inside the building envelope. These are the weighting coefficients of the loss function for the inner wall boundary conditions.

[0012] As a further technical constraint, with the goal of minimizing the joint loss function based on physical mechanisms, the weighting coefficients of the Fourier equation residual loss function, the weighting coefficients of the outer wall boundary condition loss function, the weighting coefficients of the inner wall boundary condition loss function, and the thermal conductivity of the building envelope are iteratively optimized. During the optimization process, no temperature measurement data is required; self-supervised learning is performed solely based on the physical equations and boundary conditions. When the joint loss function based on physical mechanisms is less than a preset convergence threshold, the iteration stops, and the converged thermal conductivity value is obtained, which is the optimal thermal conductivity of the building envelope.

[0013] As a further technical limitation, based on the relationship between the thermal conductivity and the heat transfer coefficient of the building envelope, i.e. The heat transfer coefficient of the building envelope corresponding to the optimal thermal conductivity of the building envelope is obtained; where... U The heat transfer coefficient of the building envelope. k The thermal conductivity of the building envelope. h out The convective heat transfer coefficient of the building envelope exterior wall. h in It is the convective heat transfer coefficient of the inner wall of the building envelope.

[0014] As a further technical limitation, the physical neural network model adopts a fully connected neural network, including an input layer, an output layer, and a hidden layer.

[0015] As a further technical limitation, after obtaining the surface parameters and environmental parameters of the building envelope, the obtained parameters are preprocessed, and the preprocessing includes at least data cleaning, data filling and data alignment.

[0016] According to some embodiments, a second aspect of the present invention provides a real-time inversion system for the heat transfer coefficient of a building envelope, employing the following technical solution:

[0017] A real-time inversion system for the heat transfer coefficient of a building envelope includes:

[0018] The acquisition module is configured to acquire surface parameters and environmental parameters of the building envelope;

[0019] The inversion module is configured to obtain the optimal thermal conductivity of the building envelope based on the acquired parameters and physical neural network model, with the goal of minimizing the joint loss function based on the physical mechanism; and to calculate the heat transfer coefficient of the building envelope based on the obtained optimal thermal conductivity, thus completing the real-time inversion of the heat transfer coefficient of the building envelope.

[0020] According to some embodiments, a third aspect of the present invention provides a computer-readable storage medium, employing the following technical solution:

[0021] A computer-readable storage medium having a program stored thereon, which, when executed by a processor, implements the steps in the real-time inversion method for the heat transfer coefficient of a building envelope as described in the first aspect of the present invention.

[0022] According to some embodiments, the fourth aspect of the present invention provides an electronic device, which adopts the following technical solution:

[0023] An electronic device includes a memory, a processor, and a program stored in the memory and running on the processor, wherein the processor executes the program to implement the steps in the real-time inversion method for the heat transfer coefficient of a building envelope as described in the first aspect of the present invention.

[0024] According to some embodiments, the fifth aspect of the present invention provides a computer program product, which adopts the following technical solution:

[0025] A computer program product includes software code, wherein the program in the software code performs the steps in the real-time inversion method for the heat transfer coefficient of the building envelope as described in the first aspect of the present invention.

[0026] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0027] This invention employs non-invasive detection, offers fast single-inversion speed, requires only a wall surface sensor, and is suitable for existing building renovations; it couples dynamic boundary conditions such as solar radiation and wind speed in real time; it is applicable to any wall, reduces hardware costs, and the results are based on physical mechanism constraints, avoiding the black box defects of pure data models.

[0028] This invention embeds Fourier equations and boundary conditions into a neural network loss function to achieve integrated modeling of physical mechanisms and data-driven approaches; it achieves dynamic inversion of heat transfer coefficients under unsteady conditions by real-time correction of the convective heat transfer coefficient of the outer wall; and it adopts a lightweight edge computing architecture to deploy the model on portable devices to meet the needs of rapid on-site testing, providing an efficient solution for building energy efficiency assessment. Attached Figure Description

[0029] The accompanying drawings, which form part of this embodiment, are used to provide a further understanding of this embodiment. The illustrative embodiments and their descriptions are used to explain this embodiment and do not constitute an improper limitation of this embodiment.

[0030] Figure 1 This is a flowchart of the real-time inversion method for the heat transfer coefficient of the building envelope in Embodiment 1 of the present invention;

[0031] Figure 2 This is an architecture diagram of the real-time inversion method for the heat transfer coefficient of the building envelope in Embodiment 1 of the present invention;

[0032] Figure 3 This is a schematic diagram of the physical neural network model in Embodiment 1 of the present invention;

[0033] Figure 4 This is a schematic diagram of the real-time inversion of the heat transfer coefficient of the building envelope in Embodiment 1 of the present invention;

[0034] Figure 5 This is a schematic diagram of the real-time inversion system for the heat transfer coefficient of the building envelope in Embodiment 2 of the present invention. Detailed Implementation

[0035] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0036] It should be noted that the following detailed descriptions are exemplary and intended to provide further illustration of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0037] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0038] In this invention, terms such as "upper," "lower," "left," "right," "front," "back," "vertical," "horizontal," "side," and "bottom" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. These terms are used only to facilitate the description of the structural relationships of the various components or elements of this invention and do not specifically refer to any component or element in this invention. They should not be construed as limiting the invention.

[0039] In this invention, terms such as "fixed connection," "connected," and "linked" should be interpreted broadly, indicating a fixed connection, an integral connection, or a detachable connection; a direct connection or an indirect connection through an intermediate medium. Those skilled in the art can determine the specific meaning of these terms in this invention based on the specific circumstances, and they should not be construed as limitations on the invention.

[0040] Where there is no conflict, the embodiments and features in the embodiments of the present invention can be combined with each other.

[0041] Example 1

[0042] Embodiment 1 of this invention introduces a real-time inversion method for the heat transfer coefficient of a building envelope.

[0043] like Figure 1 The method for real-time inversion of the heat transfer coefficient of a building envelope, as shown, includes:

[0044] Obtain surface and environmental parameters of the building envelope;

[0045] Based on the acquired parameters and physical neural network model, the optimal thermal conductivity of the building envelope is obtained by inversion with the goal of minimizing the joint loss function based on physical mechanism.

[0046] The heat transfer coefficient of the building envelope is calculated based on the optimal thermal conductivity obtained, and the heat transfer coefficient of the building envelope is inverted in real time.

[0047] To achieve real-time inversion of the heat transfer coefficient of the building envelope, this embodiment uses a physical neural network to calculate the heat transfer coefficient of the building envelope. By constructing a physical constraint end-to-end inversion framework, Fourier partial differential equations and boundary conditions are embedded into the neural network loss function to form a physical-driven intelligent inversion system. Using data processing technology under dynamic time conditions, a universal architecture is designed, which does not require a pre-defined layered structure of the building envelope and is applicable to both single-story and composite building envelopes.

[0048] As one or more implementation methods, such as Figure 2 and Figure 4 As shown, this embodiment uses a non-invasive detection method to obtain surface and environmental parameters of the building envelope to avoid damage to the building envelope. Specifically, a sensor network (i.e., temperature sensors, solar radiometers, and anemometers) is deployed on the target building envelope. The following parameters are collected in real time through the deployed sensor network: the inner wall temperature of the building envelope (… T L ), the external wall surface temperature of the building envelope ( T 0) The internal air temperature of the building envelope ( T in ), building envelope external air temperature ( T out ), solar radiation intensity ( I sun ), External wind speed of building envelope ( v The collected raw data is cleaned, missing and outlier values ​​are removed, and necessary timestamp alignment and normalization are performed to prepare it for model input. Simultaneously, the thickness of the building envelope is input or measured. L ), the convective heat transfer coefficient of the inner wall ( h in), Solar radiation absorption rate of building envelope materials ( a ), based on the wall structure and the density of the building envelope material ( ρ ) and specific heat capacity ( c Typical reference values ​​for ).

[0049] It should be noted that, among them ,in, v Wind speed. Solar absorptivity is obtained through material databases or field measurements using a spectrometer; the density and specific heat capacity of building envelope materials are taken from known thermophysical properties of different materials.

[0050] As one or more implementation methods, the collected dynamic measurement data is cleaned, Lagrange interpolation is used to fill in any missing values, and timestamps are aligned to ensure that all parameters are synchronized in time, thus preparing for model input.

[0051] In this embodiment, a feature matching mechanism is introduced to determine the initial value of thermal conductivity. Specifically, based on known building envelope physical properties (including specific heat capacity, density, thermal conductivity, etc.), the heat transfer process of different types of buildings (residential buildings, public buildings, industrial buildings, agricultural buildings) under different meteorological conditions and time scales is simulated in the early stage. This forms a feature database of different building types and walls that includes solar radiation intensity, wind speed, ambient temperature, and the temperature response of the inner and outer surfaces of the walls. This database describes the typical heat transfer behavior characteristics corresponding to different environmental conditions under known physical property conditions.

[0052] In practical applications, real-time collected environmental parameters and building envelope surface temperature data are matched with the aforementioned feature database. Samples most similar in meteorological conditions and temperature response characteristics are selected to obtain the corresponding thermal conductivity as the initial preset value. Based on this, the initial thermal conductivity is introduced into the physical constraint inversion model, and the thermal conductivity is further corrected through iterative optimization to make it more consistent with the actual unsteady heat transfer process, thereby achieving high-precision dynamic inversion of thermal conductivity.

[0053] As one or more implementation methods, this embodiment obtains the optimal thermal conductivity of the building envelope by inverting based on the acquired parameters and physical neural network model, with the goal of minimizing the joint loss function based on physical mechanisms.

[0054] This embodiment is built based on a deep learning framework, such as... Figure 3The physical neural network model shown is constructed with a fully connected neural network at its core, used to approximate the temperature distribution function T(x,t) inside the wall, where x is the coordinate along the wall's thickness and t is time. The input layer receives the spatiotemporal coordinates (x,t), and the hidden layers are set to 8 layers, each containing 20 neurons, using LeakyReLU as the activation function to avoid the vanishing gradient problem. The output layer generates the thermal conductivity value and uses Softplus activation to ensure a positive value. A custom soft activation function is introduced to ensure that all physical parameters are non-negative. The thermal conductivity k of the building envelope material is treated as a trainable variable with a preset initial value. To ensure its correct physical meaning, the output of this parameter is processed using Softplus or a custom SoftAbs activation function.

[0055] In this embodiment, the joint loss function based on physical mechanisms includes the Fourier equation residual loss function, the inner wall boundary condition loss function, and the outer wall boundary condition loss function; that is, the joint loss function based on physical mechanisms. for ;in, This is the Fourier equation residual loss function, used to describe the governing equations of heat conduction within the wall. This loss function ensures that the temperature field predicted by the model satisfies the law of heat conduction. , T The temperature inside the building envelope. t For time, k The thermal conductivity of the building envelope. c The specific heat capacity of the building envelope. ρ The material density of the building envelope; These are the weighting coefficients of the Fourier equation residual loss function; This is the boundary condition loss function for the outer wall surface, used to describe the convective heat transfer and solar radiation absorption between the outer surface of the wall and the outdoor environment. , h out The convective heat transfer coefficient of the building envelope exterior wall. T L Temperature of the inner wall surface of the building envelope. T out The air temperature outside the building envelope. I sun Solar radiation intensity, a Solar radiation absorption rate of building envelope materials; These are the weighting coefficients of the loss function for the outer wall boundary conditions; This is the boundary condition loss function for the inner wall surface, used to describe the convective heat transfer between the inner surface of the wall and the indoor environment. , hin The convective heat transfer coefficient of the inner wall of the building envelope. T in The air temperature inside the building envelope. These are the weighting coefficients of the loss function for the inner wall boundary conditions.

[0056] In this embodiment, the partial derivatives of temperature with respect to time and space are efficiently calculated using the automatic differentiation function of the neural network; the weight coefficients of the Fourier equation residual loss function, the weight coefficients of the outer wall boundary condition loss function, and the weight coefficients of the inner wall boundary condition loss function can be adjusted according to the physical importance or convergence speed of each part of the loss.

[0057] As one or more implementation methods, this embodiment aims to minimize the joint loss function based on physical mechanisms. It iteratively optimizes the weight coefficients of the Fourier equation residual loss function, the weight coefficients of the outer wall boundary condition loss function, the weight coefficients of the inner wall boundary condition loss function, and the thermal conductivity of the building envelope. During the optimization process, no temperature measurement data is required; self-supervised learning is performed solely based on the physical equations and boundary conditions. When the joint loss function based on physical mechanisms is less than a preset convergence threshold, the iteration stops, and the converged thermal conductivity value is obtained, which is the optimal thermal conductivity of the building envelope.

[0058] This embodiment is based on the relationship between the thermal conductivity and the heat transfer coefficient of the building envelope, i.e. The heat transfer coefficient of the building envelope corresponding to the optimal thermal conductivity of the building envelope is obtained; where... U The heat transfer coefficient of the building envelope. k The thermal conductivity of the building envelope. h out The convective heat transfer coefficient of the building envelope exterior wall. h in It is the convective heat transfer coefficient of the inner wall of the building envelope.

[0059] Therefore, this embodiment obtains a time stamp, environmental parameters, inverted thermal conductivity k, and final heat transfer coefficient U; the entire inversion process is short and can be completed within 6 hours, realizing rapid and non-destructive testing under unsteady conditions.

[0060] This embodiment fully leverages the advantages of combining physical neural network model data-driven approach with physical mechanism integration. The design process is simple and easy to implement, and it can be effectively applied to the thermal performance evaluation of the building envelope of existing buildings, providing a scientific basis for building energy-saving renovation.

[0061] This embodiment employs non-invasive detection, offering fast single-shot inversion speed. It requires only a wall surface sensor, making it suitable for existing building renovations. It also couples dynamic boundary conditions such as solar radiation and wind speed in real time. Applicable to any wall, it reduces hardware costs, and the results are based on physical mechanism constraints, avoiding the black-box defects of pure data models.

[0062] This embodiment embeds the Fourier equation and boundary conditions into a neural network loss function to achieve integrated modeling of physical mechanisms and data-driven approaches; it achieves dynamic inversion of heat transfer coefficient under unsteady conditions by real-time correction of the convective heat transfer coefficient of the outer wall; and it adopts a lightweight edge computing architecture to deploy the model on portable devices to meet the needs of rapid on-site testing, providing an efficient solution for building energy efficiency assessment.

[0063] Example 2

[0064] Embodiment 2 of the present invention introduces a real-time inversion system for the heat transfer coefficient of a building envelope.

[0065] like Figure 5 The real-time inversion system for the heat transfer coefficient of a building envelope, as shown, includes:

[0066] The acquisition module is configured to acquire surface parameters and environmental parameters of the building envelope;

[0067] The inversion module is configured to obtain the optimal thermal conductivity of the building envelope based on the acquired parameters and physical neural network model, with the goal of minimizing the joint loss function based on the physical mechanism; and to calculate the heat transfer coefficient of the building envelope based on the obtained optimal thermal conductivity, thus completing the real-time inversion of the heat transfer coefficient of the building envelope.

[0068] The detailed steps are the same as the real-time inversion method for the heat transfer coefficient of the building envelope provided in Example 1, and will not be repeated here.

[0069] Example 3

[0070] Embodiment 3 of the present invention provides a computer-readable storage medium.

[0071] A computer-readable storage medium having a program stored thereon, which, when executed by a processor, implements the steps in the real-time inversion method for the heat transfer coefficient of a building envelope as described in Embodiment 1 of the present invention.

[0072] The detailed steps are the same as the real-time inversion method for the heat transfer coefficient of the building envelope provided in Example 1, and will not be repeated here.

[0073] Example 4

[0074] Embodiment 4 of the present invention provides an electronic device.

[0075] An electronic device includes a memory, a processor, and a program stored in the memory and running on the processor. When the processor executes the program, it implements the steps in the real-time inversion method for the heat transfer coefficient of a building envelope as described in Embodiment 1 of the present invention.

[0076] The detailed steps are the same as the real-time inversion method for the heat transfer coefficient of the building envelope provided in Example 1, and will not be repeated here.

[0077] Example 5

[0078] Embodiment 5 of the present invention provides a computer program product.

[0079] A computer program product includes software code, wherein the program in the software code performs the steps in the real-time inversion method for the heat transfer coefficient of the building envelope as described in Embodiment 1 of the present invention.

[0080] The detailed steps are the same as the real-time inversion method for the heat transfer coefficient of the building envelope provided in Example 1, and will not be repeated here.

[0081] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of the present invention can be implemented using various computer languages, such as the object-oriented programming language Java and the interpreted scripting language JavaScript.

[0082] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0083] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0084] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0085] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0086] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

[0087] The above description is merely a preferred embodiment of this practice and is not intended to limit the scope of this practice. Various modifications and variations can be made to this practice by those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of this practice should be included within the protection scope of this practice.

Claims

1. A real-time inversion method for the heat transfer coefficient of a building envelope, characterized in that, include: Obtain surface and environmental parameters of the building envelope; Based on the acquired parameters and physical neural network model, the optimal thermal conductivity of the building envelope is obtained by inversion with the goal of minimizing the joint loss function based on physical mechanism. The joint loss function based on physical mechanisms includes the Fourier equation residual loss function, the inner wall boundary condition loss function, and the outer wall boundary condition loss function; that is, the joint loss function based on physical mechanisms. for ;in, The Fourier equation residual loss function, , T The temperature inside the building envelope. t For time, k The thermal conductivity of the building envelope. c Specific heat capacity of building envelope. ρ The material density of the building envelope; These are the weighting coefficients of the Fourier equation residual loss function; The loss function is the boundary condition function for the outer wall surface. , h out The convective heat transfer coefficient of the building envelope exterior wall. T L The temperature of the building envelope wall. T out The temperature of the air outside the building envelope. I sun The intensity of solar radiation. a Solar radiation absorption rate of building envelope materials; These are the weighting coefficients of the loss function for the outer wall boundary conditions; The loss function is the boundary condition function for the inner wall surface. , h in The convective heat transfer coefficient of the inner wall of the building envelope. T in The air temperature inside the building envelope. These are the weighting coefficients of the loss function for the inner wall boundary conditions; The heat transfer coefficient of the building envelope is calculated based on the optimal thermal conductivity obtained, and the heat transfer coefficient of the building envelope is inverted in real time.

2. The real-time inversion method for the heat transfer coefficient of a building envelope as described in claim 1, characterized in that, With the goal of minimizing the joint loss function based on physical mechanisms, the weight coefficients of the Fourier equation residual loss function, the weight coefficients of the outer wall boundary condition loss function, the weight coefficients of the inner wall boundary condition loss function, and the thermal conductivity of the building envelope are iteratively optimized. During the optimization process, no temperature measurement data is required; self-supervised learning is performed solely based on the physical equations and boundary conditions. When the joint loss function based on the physical mechanism is less than the preset convergence threshold, the iteration stops and the converged thermal conductivity value is obtained, which is the optimal thermal conductivity of the building envelope.

3. The real-time inversion method for the heat transfer coefficient of a building envelope as described in claim 1, characterized in that, Based on the relationship between the thermal conductivity and the heat transfer coefficient of the building envelope, i.e. The heat transfer coefficient of the building envelope corresponding to the optimal thermal conductivity of the building envelope is obtained; where... U The heat transfer coefficient of the building envelope. k The thermal conductivity of the building envelope. h out The convective heat transfer coefficient of the building envelope exterior wall. h in It is the convective heat transfer coefficient of the inner wall of the building envelope.

4. The real-time inversion method for the heat transfer coefficient of a building envelope as described in claim 1, characterized in that, The physical neural network model adopts a fully connected neural network, including an input layer, an output layer, and a hidden layer.

5. The real-time inversion method for the heat transfer coefficient of a building envelope as described in claim 1, characterized in that, After obtaining the surface and environmental parameters of the building envelope, the obtained parameters are preprocessed, including at least data cleaning, data filling, and data alignment.

6. A real-time inversion system for the heat transfer coefficient of a building envelope, characterized in that, include: The acquisition module is configured to acquire surface parameters and environmental parameters of the building envelope; The inversion module is configured to obtain the optimal thermal conductivity of the building envelope based on the acquired parameters and physical neural network model, with the goal of minimizing the joint loss function based on the physical mechanism; and to calculate the heat transfer coefficient of the building envelope based on the obtained optimal thermal conductivity, thus completing the real-time inversion of the heat transfer coefficient of the building envelope. The joint loss function based on physical mechanisms includes the Fourier equation residual loss function, the inner wall boundary condition loss function, and the outer wall boundary condition loss function; that is, the joint loss function based on physical mechanisms. for ;in, The Fourier equation residual loss function, , T The temperature inside the building envelope. t For time, k The thermal conductivity of the building envelope. c Specific heat capacity of building envelope. ρ The material density of the building envelope; These are the weighting coefficients of the Fourier equation residual loss function; The loss function is the boundary condition function for the outer wall surface. , h out The convective heat transfer coefficient of the building envelope exterior wall. T L The temperature of the building envelope wall. T out The temperature of the air outside the building envelope. I sun The intensity of solar radiation. a Solar radiation absorption rate of building envelope materials; These are the weighting coefficients of the loss function for the outer wall boundary conditions; The loss function is the boundary condition function for the inner wall surface. , h in The convective heat transfer coefficient of the inner wall of the building envelope. T in The air temperature inside the building envelope. These are the weighting coefficients of the loss function for the inner wall boundary conditions.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps of the real-time inversion method for the heat transfer coefficient of the building envelope as described in any one of claims 1-5.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the program, it implements the steps of the real-time inversion method for the heat transfer coefficient of the building envelope as described in any one of claims 1-5.

9. A computer program product, comprising software code, characterized in that, The program in the software code executes the steps of the real-time inversion method for the heat transfer coefficient of the building envelope as described in any one of claims 1-5.

Images