A method and device for diagnosing a thermal defect on an outer surface of an outer wall of a heated building, a computer device and a readable storage medium

Abstract

The application provides a heating building outer wall outer surface thermal defect diagnosis method and device, computer equipment and a readable storage medium, and belongs to the technical field of heating building energy saving. The application solves the problems of low automation degree and low calculation efficiency of the existing building outer wall defect detection method. It comprises the following steps: step 1, constructing an outdoor temperature data set by collecting historical meteorological data of the building location; step 2, investigating the building outer wall structure; step 3, calculating the outdoor comprehensive temperature and the delay time of the wall under the periodic thermal action; step 4, determining the collection time of the outer wall outer surface infrared thermal image; step 5, performing two-stage classification and identification of the infrared image features; step 6, determining the thermal defect degree of the outer wall; and step 7, calling the model and outputting the thermal defect diagnosis result. The application is mainly used for heating building outer wall outer surface thermal defect diagnosis.

Description

Technical Field

[0001] This invention belongs to the field of energy-saving technology for heating buildings, and specifically relates to a method, device, computer equipment, and readable storage medium for diagnosing thermal defects on the outer surface of the exterior wall of a heating building. Background Technology

[0002] The exterior walls account for approximately two-thirds of the total area of ​​a building's external envelope, and thermal defects in these walls are a significant factor affecting building energy efficiency and indoor thermal comfort. Currently, many heated buildings utilize external wall insulation, placing the insulation layer outside the structural layer. This approach offers numerous advantages. However, this wall construction frequently suffers from thermal defects that impact building energy efficiency, such as missing insulation layers, cracks, hollow areas, and thermal bridging. These defects arise from aging, degradation, or damage caused by outdoor climate factors, or from poor construction quality during new construction or renovation. Furthermore, thermal defects are generally difficult to identify visually, as the insulation layer is often obscured by the finishing layer, making quick and accurate identification challenging.

[0003] To ensure building energy efficiency and indoor thermal environment quality, the "Standard for Energy Efficiency Testing of Residential Buildings" (JGJ / T132-2009) provides methods for detecting thermal defects in the building envelope and recommends using infrared thermal imagers. However, implementing the testing procedures in this standard manually has drawbacks such as long cycles, high labor and material costs, and difficulty in guaranteeing accuracy. The standard does not provide specific calculation or identification methods for defective areas and main body areas in infrared images, nor does it provide methods for identifying and segmenting non-exterior wall parts (doors, windows, etc.). Furthermore, thermal defects on the exterior surfaces of heated building walls are diverse in type and characteristics, requiring different repair or treatment measures. Methods for classifying defect types and quantifying their severity should be developed to facilitate the rapid formulation of repair or renovation plans.

[0004] The existing Chinese invention patent with publication number CN115144434A discloses "A method for detecting defects in building exterior walls using infrared thermal imaging technology". The recommended sampling test time is during the period when the outdoor air temperature rises. However, this conclusion is too general and does not take into account the specific circumstances of the tested building (such as geographical location, exterior wall orientation, and exterior wall structure). The journal article "A rapid identification method for thermal defects in building exterior walls based on infrared image features" (Building Science, 2023.06) proposes to use machine learning methods to identify thermal defects in building exterior walls, but there are still problems such as low automation and computational efficiency that need to be improved. Summary of the Invention

[0005] In view of this, the present invention aims to provide a method, device, computer equipment and readable storage medium for diagnosing thermal defects on the outer surface of the exterior wall of a heated building, so as to solve the problems of low automation and low computational efficiency of existing building exterior wall defect detection methods.

[0006] To achieve the above objectives, the present invention adopts the following technical solution:

[0007] A method for diagnosing thermal defects on the exterior surface of a heated building wall, comprising the following steps:

[0008] Step 1: Construct an outdoor temperature data set by collecting historical meteorological data of the building's location;

[0009] Step 2: Conduct a survey of the building's exterior wall structure;

[0010] Step 3: Perform outdoor comprehensive temperature calculation and the delay time of the wall under periodic thermal effects;

[0011] Step 4: Determine the acquisition time for the infrared thermal image of the outer surface of the exterior wall;

[0012] Step 5: Perform two-level classification and recognition of infrared image features;

[0013] Step 6: Determine the degree of thermal defects in the exterior wall;

[0014] Step 7: Call the model and output the thermal defect diagnosis results.

[0015] Furthermore, in step 1, time intervals of sunny or cloudy weather conditions are selected to construct a temperature data set for each hourly air temperature.

[0016] Furthermore, the combined effect of outdoor air temperature and solar radiation is expressed based on the outdoor comprehensive temperature calculated in step 3.

[0017] Furthermore, step 3 calculates the delay time of the wall under periodic thermal action based on the thermal inertia index of the exterior wall, the heat transfer coefficients of the inner and outer surfaces of the exterior wall, and the heat storage coefficients of the inner and outer surfaces of the exterior wall.

[0018] Furthermore, the selection of the acquisition time in step 4 needs to simultaneously satisfy the condition that the derivative of the sinusoidal function of the outdoor comprehensive temperature is in the interval -0. to 0.5 and the time after the heating transfer delay when the outdoor comprehensive temperature reaches its peak.

[0019] Furthermore, infrared thermal image acquisition involves capturing infrared thermal images of the inspected surfaces of the exterior walls of the building under test from various orientations, as well as infrared thermal images of the same location on the inspected surface.

[0020] Furthermore, in step 5, the two-level classification and recognition of infrared image features, through image retrieval, preprocessing and standardization, and the establishment of a machine learning diagnostic model based on a combination of mechanism analysis and data-driven approaches, completes the elimination of inherent high-temperature parts and the analysis and evaluation of thermal defects.

[0021] Furthermore, a diagnostic device for thermal defects on the exterior surface of a heated building wall, the device comprising:

[0022] The data collection module is used to construct an outdoor temperature data set by collecting historical meteorological data of the building's location;

[0023] The analysis module is used to conduct research on the structure of building exterior walls;

[0024] The calculation module is used to calculate the overall outdoor temperature and the delay time of the wall under periodic thermal effects.

[0025] The time determination module is used to determine the acquisition time of the infrared thermal image of the outer surface of the exterior wall;

[0026] The feature recognition module is used for two-level classification and recognition of infrared image features;

[0027] The defect assessment module is used to determine the degree of thermal defects in the exterior walls.

[0028] The results diagnosis module is used to call the model and output the diagnostic results of thermal defects.

[0029] Furthermore, a computer device includes a memory and a processor, wherein the memory stores a computer program, and when the processor runs the computer program stored in the memory, the processor executes the method for diagnosing thermal defects on the outer surface of the exterior wall of a heated building as described in any one of claims 1-9.

[0030] Furthermore, a computer-readable storage medium is provided for storing a computer program that executes the method for diagnosing thermal defects on the outer surface of a heated building wall as described in any one of claims 1-9.

[0031] Compared with the prior art, the beneficial effects of the present invention are:

[0032] 1. This invention combines meteorological data statistical analysis, heat transfer characteristics under harmonic effects, least squares principle, building thermal characteristics, and machine learning methods. From physical mechanisms to model construction and practical applications, it is easy to understand, convenient to implement, theoretically interpretable, and robust, and can meet the needs of thermal defect detection and analysis of building exterior walls.

[0033] 2. This invention calculates the outdoor comprehensive temperature as a periodically changing thermal effect over a period of time, and considers the delay effect of typical building exterior wall structure on harmonic thermal effects. By combining the above factors, the recommended acquisition time for infrared thermal images of exterior walls of buildings in different regions can be determined. This can effectively avoid interference from excessively small temperature differences or excessively large temperature fluctuations, and help improve the accuracy of the training process and the accuracy of thermal defect classification prediction results.

[0034] 3. This invention is characterized by its ease of use, simple operation, broad applicability, and rapid efficiency. It can accurately, efficiently, and automatically detect thermal defects on the exterior surface of building walls. This method can be used to determine thermal defects on the exterior surface of building walls, providing technical guidance for the repair and performance improvement of exterior wall insulation, and is beneficial to promoting energy conservation and emission reduction in the construction industry while improving the quality of the indoor thermal environment. Attached Figure Description

[0035] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an undue limitation of the invention. In the drawings:

[0036] Figure 1 This is a flowchart of a method for diagnosing thermal defects on the outer surface of a heated building wall, as described in this invention. Detailed Implementation

[0037] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. It should be noted that, unless otherwise specified, the embodiments and features in the embodiments of the present invention can be combined with each other, and the described embodiments are only some embodiments of the present invention, not all embodiments.

[0038] See Figure 1 This embodiment describes a method for diagnosing thermal defects on the outer surface of a heated building's exterior wall, which includes the following steps:

[0039] Step 1: Construct an outdoor temperature data set by collecting historical meteorological data of the building's location;

[0040] Select time intervals without special weather conditions (generally 3-4 days) to construct a temperature data set for each hourly air temperature.

[0041] Step 2: Conduct a survey of the building's exterior wall structure;

[0042] By conducting research on the exterior wall structure of the building's location, we can understand its typical structural layers and the important parameters of the geometric dimensions and thermophysical properties (thermal conductivity, density, specific heat capacity, etc.) of the materials in each layer.

[0043] Step 3: Perform outdoor comprehensive temperature calculation and the delay time of the wall under periodic thermal effects;

[0044] The hourly value of the comprehensive outdoor temperature is calculated based on the outdoor air temperature, the absorption coefficient of solar radiation heat on the exterior surface of a typical building, the solar radiation intensity, the heat transfer coefficient of the exterior surface, and the effective long-wave radiation temperature of the exterior wall. Using data analysis software, a sine function with a period of 24 hours is obtained by regression based on the least squares principle to express the daily fluctuation of the comprehensive outdoor temperature in different orientations.

[0045] The delay time of the wall under periodic (daily) heat action is calculated based on the thermal inertia index of the exterior wall, the heat transfer coefficients of the inner and outer surfaces of the exterior wall, and the heat storage coefficients of the inner and outer surfaces of the exterior wall.

[0046] Step 4: Determine the acquisition time for the infrared thermal image of the outer surface of the exterior wall;

[0047] Infrared thermal imaging equipment is used to collect images of building exteriors from different regions, eras, and types. The detection time needs to be calculated and determined according to the procedure, taking into account the dual effects of outdoor comprehensive temperature and the heat transfer delay characteristics of the exterior walls. The time period T corresponding to the derivative of the hourly outdoor comprehensive temperature function being located in the interval (-0.5, 0.5) is selected. Let t1 be the time when the outdoor comprehensive temperature at a certain location of the tested building reaches its peak, and t2 be the delay time of the wall under periodic thermal action. The acquisition time needs to be ensured to be included in T and later than t1+t2.

[0048] Step 5: Perform two-level classification and recognition of infrared image features;

[0049] This study investigates the infrared image features of building exterior surfaces using dynamic numerical simulation. Considering that not all areas with abnormal temperatures on the exterior surface are thermal defects, the study employs a hierarchical classification to improve identification efficiency and accuracy. The first level classifies areas into inherent high-temperature regions and those with thermal defects; the second level categorizes and diagnoses thermal defects by type.

[0050] Step 6: Determine the degree of thermal defects in the exterior wall;

[0051] The process involves image retrieval, preprocessing, standardization, and the construction of a machine learning diagnostic model for thermal defects on the exterior wall surface. Specifically, a quadtree segmentation method is used to determine the defect area ratio for areas with thermal defects.

[0052] Step 7: Call the model and output the thermal defect diagnosis results.

[0053] Furthermore, the combined effect of outdoor air temperature and solar radiation is expressed based on the outdoor comprehensive temperature calculated in step 3.

[0054] The calculation of the outdoor comprehensive temperature is used to express the combined effect of outdoor air temperature and solar radiation, and is calculated according to formula (1).

[0055] t sa =t e +ρ s I / α e -t 1r (1)

[0056] Among them, t sa The outdoor composite temperature; t e Outdoor air temperature; ρ s α is the absorption coefficient of solar radiation heat on the outer surface of the exterior wall; I is the solar radiation intensity; α e t is the heat transfer coefficient of the outer surface; 1r The effective long-wave radiation temperature of the exterior wall is used to generate the daytime outdoor comprehensive temperature curves of different orientations in sine (or cosine) form based on the least squares principle.

[0057] Furthermore, step 3 calculates the delay time of the wall under periodic thermal action based on the thermal inertia index of the exterior wall, the heat transfer coefficients of the inner and outer surfaces of the exterior wall, and the heat storage coefficients of the inner and outer surfaces of the exterior wall.

[0058] The analysis of the heat transfer delay characteristics of the exterior wall is to first calculate the heat transfer delay time of the building exterior wall under periodic thermal action based on formula (2).

[0059]

[0060] Where ξ0 is the delay time of the outdoor comprehensive temperature wave, D is the thermal inertia index of the exterior wall, which is related to the thermal resistance and heat storage coefficient of each material layer of the exterior wall; α i and α e , respectively, are the heat transfer coefficients of the inner and outer surfaces of the exterior wall; Yi and Ye are the surface heat storage coefficients of the inner and outer surfaces of the exterior wall, respectively. According to formula (2), the heat transfer delay time is estimated according to the design conditions.

[0061] Furthermore, the selection of the acquisition time in step 4 needs to simultaneously satisfy the following conditions: the derivative of the sinusoidal function of the outdoor comprehensive temperature is in the interval -0.5 to 0.5, and the time is after the heating transfer delay time when the outdoor comprehensive temperature reaches its peak.

[0062] Furthermore, infrared thermal image acquisition involves capturing infrared thermal images of the inspected surfaces of the exterior walls of the building under test from each direction. There should be no fewer than two infrared thermal images of the same location on the inspected surface. The temperature difference between two consecutive measurements at key points should not exceed 0.5°C. The infrared thermal imager used in the test should be designed to operate within a wavelength range of (8.0~14.0)μm and have no fewer than 76,800 pixels.

[0063] The main task of the aforementioned two-level classification and recognition of infrared image features is, firstly, to identify and exclude inherently high-temperature areas such as exterior windows and walls below windows; and secondly, to identify thermal defects, which include the following common types: cracking, leakage, hollowing, and thermal bridging. Specifically, based on the survey results of infrared images of exterior walls in different climate zones, at different ages, of different types (residential, public, and industrial), and with different orientations, a dynamic numerical simulation method is used to analyze and extract the infrared thermal image features of each type, and inherently high-temperature areas are excluded in advance, so as to further classify and diagnose thermal defects.

[0064] Furthermore, in step 5, the two-level classification and recognition of infrared image features, through image retrieval, preprocessing and standardization, and the establishment of a machine learning diagnostic model based on a combination of mechanism analysis and data-driven approaches, completes the elimination of inherent high-temperature parts and the analysis and evaluation of thermal defects.

[0065] Furthermore, the aforementioned external wall thermal defect judgment refers to inputting qualified infrared thermal image information of the inspected surface, calling the above-mentioned machine learning diagnostic model, excluding inherent high-temperature parts, completing the automatic identification of the main area of ​​the inspected surface and the thermal defect area, automatically classifying the thermal defect area, and automatically realizing the calculation of the relative area ratio ψ in the "Residential Building Energy Conservation Testing Standard" JGJ / T132-2009, and judging according to the indicators specified in "5.2 Qualification Indicators and Judgment Methods" of the standard. The following formula (3) is the calculation of the relative area ratio ψ.

[0066]

[0067] Where: ψ: the ratio of the area of ​​the defective region on the inspected surface to the area of ​​the main region; A 1,i Area (m²) of the main region of the i-th thermal image 2 A 2,i The area of ​​the defect region in the i-th thermal image refers to the area (m²) formed by points whose average temperature difference with the main surface area (excluding the defect region) is greater than or equal to 1℃. 2 ).

[0068] Furthermore, a diagnostic device for thermal defects on the outer surface of a heated building's exterior wall, the device comprising:

[0069] The data collection module is used to construct an outdoor temperature data set by collecting historical meteorological data of the building's location;

[0070] The analysis module is used to conduct research on the structure of building exterior walls;

[0071] The calculation module is used to calculate the overall outdoor temperature and the delay time of the wall under periodic thermal effects.

[0072] The time determination module is used to determine the acquisition time of the infrared thermal image of the outer surface of the exterior wall;

[0073] The feature recognition module is used for two-level classification and recognition of infrared image features;

[0074] The defect assessment module is used to determine the degree of thermal defects in the exterior walls.

[0075] The results diagnosis module is used to call the model and output the diagnostic results of thermal defects.

[0076] Furthermore, a computer device includes a memory and a processor, wherein the memory stores a computer program, and when the processor runs the computer program stored in the memory, the processor executes a method for diagnosing thermal defects on the outer surface of a heated building exterior wall.

[0077] Furthermore, a computer-readable storage medium is provided for storing a computer program that executes a method for diagnosing thermal defects on the outer surface of a heated building exterior wall.

[0078] Those skilled in the art will understand that the features described in the various embodiments and / or claims of this disclosure can be combined or combined in various ways, even if such combinations or combinations are not explicitly described in this disclosure. In particular, the various embodiments and features of this disclosure can be combined in various ways without departing from the spirit and teachings of this disclosure. All such combinations fall within the scope of this disclosure.

[0079] 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. Clearly, those skilled in the art can make various alterations and modifications to the invention without departing from its spirit and scope. Thus, if these modifications and modifications of the invention fall within the scope of the claims and their equivalents, the invention is also intended to include these modifications and modifications.

Claims

1. A method for diagnosing thermal defects on the outer surface of a heated building's exterior wall, characterized in that: It includes the following steps: Step 1: Construct an outdoor temperature data set by collecting historical meteorological data of the building's location; Step 2: Conduct a survey of the building's exterior wall structure; Step 3: Perform outdoor comprehensive temperature calculation and the delay time of the wall under periodic heat action. Calculate the delay time of the wall under periodic heat action based on the thermal inertia index of the exterior wall, the heat transfer coefficient of the inner and outer surfaces of the exterior wall, and the heat storage coefficient of the inner and outer surfaces of the exterior wall. Step 4: Determine the acquisition time of the infrared thermal image of the outer surface of the exterior wall. The acquisition time should be selected to simultaneously satisfy the following conditions: the derivative of the sinusoidal function of the outdoor comprehensive temperature is in the interval -0.5 to 0.5, and the time is after the heating transfer delay when the outdoor comprehensive temperature reaches its peak. Step 5: Perform two-level classification and recognition of infrared image features. The two-level classification and recognition of infrared image features involves image retrieval, preprocessing and standardization, and the establishment of a machine learning diagnostic model based on a combination of mechanism analysis and data-driven approach to complete the elimination of inherent high-temperature parts and the analysis and evaluation of thermal defects. Step 6: Determine the degree of thermal defects in the exterior wall. This involves image retrieval, preprocessing, standardization, and the construction of a machine learning diagnostic model for thermal defects on the exterior surface of the exterior wall. For areas with thermal defects, a quadtree segmentation method is used to determine the defect area ratio. Step 7: Call the model and output the thermal defect diagnosis results.

2. The method for diagnosing thermal defects on the outer surface of a heated building wall according to claim 1, characterized in that: In step 1, select time intervals for sunny or cloudy weather conditions to construct a temperature data set for each hourly air temperature.

3. The method for diagnosing thermal defects on the outer surface of a heated building wall according to claim 1, characterized in that: The combined effect of outdoor air temperature and solar radiation is expressed based on the outdoor comprehensive temperature calculated in step 3.

4. The method for diagnosing thermal defects on the outer surface of a heated building wall according to claim 1, characterized in that: Infrared thermal image acquisition involves capturing infrared thermal images of the inspected exterior walls of the building under test from various orientations, as well as infrared thermal images of the same location on the inspected surface.

5. A diagnostic device for thermal defects on the outer surface of a heated building's exterior wall, characterized in that, The device includes: The data collection module is used to construct an outdoor temperature data set by collecting historical meteorological data of the building's location; The analysis module is used to conduct research on the structure of building exterior walls; The calculation module is used to calculate the overall outdoor temperature and the delay time of the wall under periodic thermal action. It calculates the delay time of the wall under periodic thermal action based on the thermal inertia index of the exterior wall, the heat transfer coefficient of the inner and outer surfaces of the exterior wall, and the heat storage coefficient of the inner and outer surfaces of the exterior wall. The time determination module is used to determine the acquisition time of the infrared thermal image of the outer surface of the exterior wall. The selection of the acquisition time needs to simultaneously satisfy the condition that the derivative of the sinusoidal function of the outdoor comprehensive temperature is in the interval of -0. to 0.5 and the time after the heating transfer delay when the outdoor comprehensive temperature reaches its peak. The feature recognition module is used to perform two-level classification and recognition of infrared image features. The two-level classification and recognition of infrared image features completes the elimination of inherent high-temperature parts and the analysis and evaluation of thermal defects by image retrieval, preprocessing and standardization, and establishing a machine learning diagnostic model based on a combination of mechanism analysis and data-driven approach. The defect determination module is used to determine the degree of thermal defects in the exterior wall. It sequentially follows the steps of image retrieval, preprocessing, standardization, and construction of a machine learning diagnostic model for thermal defects on the exterior surface of the exterior wall. Among these steps, the quadtree segmentation method is used to determine the defect area ratio for areas with thermal defects. The results diagnosis module is used to call the model and output the diagnostic results of thermal defects.

6. A computer device, characterized in that: It includes a memory and a processor, wherein the memory stores a computer program, and when the processor runs the computer program stored in the memory, the processor executes the method for diagnosing thermal defects on the outer surface of the exterior wall of a heated building as described in any one of claims 1-4.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store a computer program that executes the method for diagnosing thermal defects on the outer surface of the exterior wall of a heated building as described in any one of claims 1-4.

Images