Data-driven building exterior wall thermal performance detection method

Abstract

The application discloses a building outer wall thermal performance detection method based on data driving, relates to the technical field of building detection, and comprises the following steps: S1, a data acquisition unit monitors infrared data and structure data of a building outer wall; S2, an edge calculation unit analyzes thermal parameters of the building wall; S3, a central processing unit performs intelligent diagnosis on a region exception of the building wall and optimizes inversion of thermal performance; and S4, a data output unit displays the exception region of the wall and obtains maintenance suggestions, and further generates an optimal construction scheme of the building outer wall in combination with optimal thermal parameters. Through multi-source data fusion and three-dimensional infrared modeling, thermal defects can be accurately positioned, the whole process is automated, manual intervention is reduced, detection efficiency and precision are improved, the whole life cycle management of the thermal performance of the building outer wall is realized through data driving and model fusion, the detection industry is transformed into intelligent and data-based, and building energy-saving reconstruction and sustainable development are realized.

Description

Technical Field

[0001] This invention relates to the field of building inspection technology, and in particular to a data-driven method for testing the thermal performance of building exterior walls. Background Technology

[0002] Globally, the thermal insulation performance of many old buildings is deteriorating, with issues such as insulation layer detachment and thermal bridging. Defective areas need to be identified through inspection to guide targeted renovations. Furthermore, construction defects such as uneven insulation material application and inadequate sealing can lead to hidden heat loss, necessitating thermal performance acceptance testing at the completion stage. These thermal defects are often accompanied by problems like hollow areas and water seepage, potentially causing structural safety hazards. Regular inspections are required for preventative maintenance to ensure building safety.

[0003] However, traditional testing methods rely on human experience, which is inefficient and prone to missing details such as thermal bridges and cracks. Existing systems generally detect through local temperature data, which is difficult to reflect the overall thermal performance of the wall, lacks three-dimensional spatial correlation, lacks intelligent diagnostic capabilities, and the large amount of data processing results in high latency, making it impossible to guide on-site maintenance in real time. This leads to unscientific construction plans, difficulty in dynamically adjusting in conjunction with real-time thermal parameters, and a tendency to over-construction or incomplete repair, resulting in high renovation costs.

[0004] To address the aforementioned technical shortcomings, a solution is proposed. Summary of the Invention

[0005] The purpose of this invention is to solve the problems of traditional detection methods, which rely on manual experience, are inefficient, and are prone to overlooking details such as thermal bridges and cracks. In addition, existing systems generally detect problems by using local temperature data, which makes it difficult to reflect the overall thermal performance of the wall, lacks three-dimensional spatial correlation, lacks intelligent diagnostic capabilities, and has high latency due to large data processing volume. This makes it impossible to guide on-site maintenance in real time, resulting in unscientific construction plans, difficulty in dynamically adjusting in conjunction with real-time thermal parameters, and easy to lead to over-construction or incomplete repair, resulting in high renovation costs.

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

[0007] A data-driven method for testing the thermal performance of building exterior walls includes the following steps:

[0008] S1, the data acquisition unit monitors the infrared and structural data of the building's exterior walls;

[0009] S2, Edge computing unit analyzes the thermal parameters of building walls: By constructing a three-dimensional infrared building model, the thermal parameters of building walls are analyzed, and the distribution of thermal performance of the building exterior walls is displayed;

[0010] S3, the central processor carries out the regional abnormal intelligent diagnosis and thermal performance optimization inversion of the building wall: through the thermal performance distribution of the building outer wall, the regional planning and comparison marking are carried out, the abnormal region of the wall is identified and output, and through the setting of m kinds of construction schemes of the building outer wall, the predicted temperature is continuously close to the measured temperature, the parameter optimization objective function of the thermal performance is built, and the optimal thermal parameter of the building outer wall region is output;

[0011] S4, the data output unit displays the abnormal region of the wall and obtains the maintenance suggestion, and generates the optimal construction scheme of the building outer wall in combination with the optimal thermal parameter.

[0012] Further, the data acquisition unit comprises an infrared thermal imager and a three-dimensional laser scanner;

[0013] The infrared data of the building outer wall is obtained through the infrared thermal imager, and the structural data is obtained through the three-dimensional laser scanner;

[0014] The three-dimensional infrared building model is constructed through the combination of the infrared data and the structural data of the building outer wall;

[0015] The infrared data comprises the inner and outer surface temperatures of the building wall, the indoor and outdoor air temperatures;

[0016] The structural data comprises the three-dimensional position, thickness and thermal conductivity coefficient of the building wall.

[0017] Further, the thermal parameters of the building wall are analyzed through the heat transfer model, and the specific process is as follows:

[0018] The building wall is planned into N regional walls through the three-dimensional infrared building model, and any regional wall is marked as P;

[0019] The regional wall P comprises n layers of wall materials, the total thickness of the wall is marked as L, any layer of the wall is marked as i, the thickness of the wall i is marked as di, and the thermal conductivity coefficient of the wall i is marked as ki;

[0020] The inner surface temperature of the regional wall P is marked as , and the outer surface temperature is marked as ;

[0021] The indoor air temperature of the regional wall P is marked as , and the outdoor air temperature is marked as ;

[0022] The indoor heat flux density and the outdoor heat flux density are obtained through the heat flow meter;

[0023] The inner surface convective heat transfer coefficient is marked as , and the outer surface convective heat transfer coefficient is marked as ;

[0024] Through the convective heat transfer coefficient of the inner surface Surface convective heat transfer coefficient By combining the thickness di of wall i and the thermal conductivity ki, the total thermal resistance R of the wall in region P is obtained, and then the heat transfer coefficient U of the wall in region P is obtained.

[0025] Thermal parameters include heat transfer coefficient and total thermal resistance.

[0026] Furthermore, the specific process of intelligent diagnosis of regional anomalies in building walls is as follows:

[0027] The thermal performance distribution of the building's exterior walls is displayed using a three-dimensional infrared building model. Then, regional planning and comparison marking are performed. The standard threshold for the total thermal resistance of the regional walls is set as Qr, and the standard threshold for the heat transfer coefficient of the regional walls is set as Qu.

[0028] When the total thermal resistance R of the wall in region P is higher than the standard threshold Qr and the heat transfer coefficient U is lower than the standard threshold Qu, the thermal performance of the wall in region P is determined to be normal; otherwise, the thermal performance of the wall in region P is determined to be abnormal, thereby identifying and outputting abnormal wall areas.

[0029] Then, it performs intelligent diagnosis on abnormal areas of the wall to determine the condition of insulation layer damage, thermal bridging, cracks and poor sealing.

[0030] Furthermore, the specific process of optimizing and inverting the thermal performance of building walls is as follows:

[0031] The steady-state and instantaneous heat transfer of the wall are analyzed using the surface heat transfer equation and the time-series heat conduction equation, respectively. The specific process is as follows:

[0032] Through heat transfer coefficient U, indoor air temperature and outdoor air temperature Combined, the heat flux density of steady-state heat transfer in wall P is analyzed. ;

[0033] heat flux density Substitute the values ​​into the surface heat transfer equation to obtain the predicted internal and external surface temperatures;

[0034] mark For the predicted inner surface temperature, The predicted outer surface temperature;

[0035] If the inner surface boundary space point q is marked as 0, then the outer surface boundary space point q is marked as L. If any time node is marked as t, then the wall surface temperature corresponding to the space point q and the time node t is marked as T(q,t).

[0036] The thermal diffusivity is obtained by the density of the wall material , the specific heat capacity c, and the thermal conductivity k ;

[0037] The time-dependent heat conduction equation is established, and the inner and outer surface boundary conditions are set.

[0038] The thermal performance optimization objective function is set by setting the thermal performance parameters, and the optimal thermal performance parameters of the building outer wall area are obtained.

[0039] Further, the specific process of setting the thermal performance parameter optimization objective function to obtain the optimal thermal performance parameters of the building outer wall area is as follows:

[0040] The thermal conductivity ki of the wall i, the inner surface convective heat transfer coefficient , the outer surface convective heat transfer coefficient , the density of the wall material , and the specific heat capacity c are integrated into the target parameter vector ;

[0041] The target parameter vector is optimized by minimizing the mean square error of the predicted temperature and the actual temperature, and the construction scheme of the building outer wall is set to m. Any construction scheme of the building outer wall is marked as j, and the thermal performance parameter optimization objective function is built.

[0042] By setting the m construction schemes of the building outer wall and calculating the minimum value of the objective function, the target parameter vector obtained is marked as the optimal thermal performance parameter, and the construction scheme obtained is marked as the optimal construction scheme of the building outer wall.

[0043] Further, the intelligent diagnosis of the abnormal area of the wall is carried out, and the specific process of determining the damage of the thermal insulation layer, the heat bridge, the crack and the sealing is as follows:

[0044] The thermal resistance change rate of the wall in the area is calculated , and the threshold is set to When the thermal resistance change rate exceeds the set threshold , it is determined that the wall has a thermal insulation layer damage;

[0045] The temperature difference between the wall P in the area and the surrounding wall is measured , and the threshold is set to When the temperature difference exceeds the set threshold , it is determined that the wall has a heat bridge;

[0046] The gray image of the wall P in the region is obtained by a three-dimensional laser scanner, and the wall gray image is denoised by Gaussian filtering, so as to compare and determine whether the wall has cracks;

[0047] By analyzing the temperature change rate of the wall and comparing it with the temperature change rate under the normal sealing state of the wall in the region, the temperature change rate difference is obtained And the threshold is set to When the temperature change rate difference Exceeds the threshold , it is determined that the wall has a sealing problem.

[0048] Further, the specific process of comparing and determining whether the wall has cracks by Gaussian filtering denoising is as follows:

[0049] The wall gray image is set as I(x, y), x is the coordinate of the horizontal direction of the image, and y is the coordinate of the vertical direction of the image;

[0050] The Gaussian filtering function is marked as G(x, y, σ), and σ is the standard deviation of the gray value of the image pixel point;

[0051] After filtering the wall gray image I(x, y) by the Gaussian filtering function G(x, y, σ), the denoising image Iqz(x, y) is obtained, and then the gradient amplitude M(x, y) and the gradient direction γ(x, y) are obtained; and then MnmS(x, y) is obtained by non-maximum suppression;

[0052] The high threshold of Mnms(x, y) is set to And the low threshold is set to Then compare the thresholds:

[0053] When Mnms(x, y) > high threshold , the pixel point is marked as a strong edge point;

[0054] When Mnms(x, y) < low threshold , the pixel point is marked as a non-edge point;

[0055] When the low threshold ≤Mnms(x, y)≤high threshold , the pixel point is marked as a crack edge, and it is determined that the wall has cracks.

[0056] Further, for each diagnostic result, a corresponding repair suggestion is preset in advance, and the abnormal area of the wall and the intelligent diagnostic result are displayed to match the corresponding repair suggestion;

[0057] The intelligent diagnostic result is verified by actually investigating the abnormal area of the wall;

[0058] When the diagnosis is verified to be correct, then the wall maintenance management is carried out according to the system output repair suggestion; otherwise, when the diagnosis is verified to be incorrect, then the professional technician is prompted to carry out the wall maintenance management according to the actual situation.

[0059] In summary, due to the adoption of the above technical solutions, the beneficial effects of the present application are:

[0060] The present application realizes the spatial mapping of temperature, thickness and material properties through multi-source data fusion and three-dimensional infrared modeling, thereby accurately positioning the thermal defects, and the whole process is automated, from data acquisition, analysis, diagnosis to optimization, reducing manual intervention, realizing the double improvement of detection efficiency and accuracy, through data driving and model fusion, overcoming the short board of traditional methods in efficiency, accuracy and real-time performance, realizing the whole life cycle management of building external wall thermal performance, promoting the intelligent and data transformation of the detection industry, realizing the building energy saving reconstruction and sustainable development.

[0061] Among them, the present application combines the infrared thermal imager and the three-dimensional laser scanner to construct a three-dimensional infrared building model, supports local high-precision re-measurement, ensures the abnormal defect detection rate of key areas, and completes the preliminary analysis of the thermal parameters of the building wall through the edge, generates a thermal performance distribution map in real time, and improves the speed of data processing and response;

[0062] The present application realizes the whole life cycle management of building external wall thermal performance, promotes the intelligent and data transformation of the detection industry, realizes the building energy saving reconstruction and sustainable development.

[0063] The present application realizes the whole life cycle management of building external wall thermal performance, promotes the intelligent and data transformation of the detection industry, realizes the building energy saving reconstruction and sustainable development. BRIEF DESCRIPTION OF DRAWINGS

[0064] Fig. 1 The flowchart shows the overall scheme of the present application;

[0065] Fig. 2 The frame diagram of the system module of the present application is shown. DETAILED DESCRIPTION

[0066] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative effort belong to the scope of the present application.

[0067] Embodiment 1

[0068] As shown in the following, the data-driven building exterior wall thermal performance detection method comprises the following steps: Figs. 1-2

[0069] S1, a data acquisition unit monitors infrared data and structural data of a building exterior wall;

[0070] The data acquisition unit comprises an infrared thermal imager and a three-dimensional laser scanner;

[0071] The infrared data of the building exterior wall is acquired by the infrared thermal imager, and the structural data is acquired by the three-dimensional laser scanner;

[0072] A three-dimensional infrared building model is constructed by combining the infrared data and the structural data of the building exterior wall;

[0073] The infrared data comprises the inner and outer surface temperatures of the building wall and the indoor and outdoor air temperatures;

[0074] The structural data comprises the three-dimensional position, thickness and thermal conductivity coefficient of the building wall;

[0075] The three-dimensional infrared building model is constructed by combining the infrared thermal imager and the three-dimensional laser scanner, supports local high-precision re-measurement, guarantees the abnormal defect detection rate of the key area, and in the present scheme, the "data-driven" is throughout the whole process of data acquisition, model construction, parameter optimization and decision generation, especially the data analysis part of the edge computing and the central processor.

[0076] S2, an edge computing unit analyzes the thermal parameters of the building wall: the thermal parameters of the building wall are analyzed by constructing the three-dimensional infrared building model, and the thermal performance distribution of the building exterior wall is displayed;

[0077] The thermal parameters of the building wall are analyzed by a heat transfer model, and the specific process is as follows:

[0078] The building wall is planned into N regional walls by the three-dimensional infrared building model, and any regional wall is marked as P;

[0079] The regional wall P is set to comprise n layers of wall materials, the total thickness of the wall is marked as L, any layer of the wall is marked as i, the thickness of the wall i is marked as di, and the thermal conductivity coefficient of the wall i is marked as ki; ​

[0080] Let the inner surface temperature of the regional wall P be marked as , and the outer surface temperature be marked as ;

[0081] Let the indoor air temperature of the regional wall P be marked as , and the outdoor air temperature be marked as ;

[0082] Obtain the indoor heat flux density , and the outdoor heat flux density ;

[0083] Mark the inner surface convective heat transfer coefficient as : ;

[0084] Mark the outer surface convective heat transfer coefficient as : ;

[0085] Obtain the total thermal resistance R of the regional wall P by combining the inner surface convective heat transfer coefficient , the outer surface convective heat transfer coefficient , the thickness di of the wall i, and the thermal conductivity ki: ;

[0086] Further obtain the heat transfer coefficient U of the regional wall P: ;

[0087] The thermal parameters include the heat transfer coefficient and the total thermal resistance;

[0088] The preliminary analysis of the thermal parameters of the building wall is completed through the edge computing port, and the thermal performance distribution map is generated in real time, which improves the speed of data processing and response.

[0089] S3, the central processor performs regional abnormal intelligent diagnosis and thermal performance optimization inversion of the building wall: through regional planning and comparative marking of the thermal performance distribution of the building outer wall, the abnormal region of the wall is identified and output, and by setting m kinds of construction schemes of the building outer wall, the predicted temperature is continuously close to the measured temperature, the parameter optimization objective function of the thermal performance is built, and the optimal thermal parameters of the building outer wall region are output.

[0090] S3-1, the specific process of the regional abnormal intelligent diagnosis of the building wall is:

[0091] Display the thermal performance distribution of the building outer wall through the three-dimensional infrared building model, then perform regional planning and comparative marking, set and mark the standard threshold of the total thermal resistance of the regional wall as Qr, and the standard threshold of the heat transfer coefficient of the regional wall as Qu;

[0092] When the total thermal resistance R of the area wall P is higher than the standard threshold Qr, and the heat transfer coefficient U is lower than the standard threshold Qu, it is determined that the thermal performance of the area wall P is normal; otherwise, it is determined that the thermal performance of the area wall P is abnormal, thereby realizing intelligent diagnosis of the area abnormality, identifying and outputting the abnormal area of the wall;

[0093] Intelligently diagnosing the abnormal area of the wall, determining the damage of the thermal insulation layer, the thermal bridge, the crack and the sealing failure;

[0094] Through the area planning and comparison marking of the building outer wall, the abnormal area of the wall is quickly located, and the damage of the thermal insulation layer, the thermal bridge and other problems are diagnosed and identified, so as to generate a customized construction scheme based on the optimal thermal performance parameters, avoid material waste, reduce the cost of energy saving and reconstruction, prolong the service life of the building, and reduce the energy loss caused by thermal defects.

[0095] S3-2, the specific process of the thermal performance optimization inversion of the building wall is:

[0096] The steady-state heat transfer and transient heat transfer of the wall are analyzed through the surface heat transfer equation and the time sequence heat conduction equation, and the specific process is as follows:

[0097] The heat transfer coefficient U, the indoor air temperature and the outdoor air temperature are combined to analyze the heat flux density of the steady-state heat transfer of the wall P:

[0098] The heat flux density is substituted into the surface heat transfer equation to obtain the predicted inner and outer surface temperatures:

[0099]

[0100] Among them, is the predicted inner surface temperature, is the predicted outer surface temperature;

[0101] The inner surface boundary space point q is marked as 0, the outer surface boundary space point q is marked as L, any time node is marked as t, and the wall surface temperature corresponding to the space point q and the time node t is marked as T(q, t);

[0102] The time sequence heat conduction equation is established:

[0103] Among them, is the thermal diffusivity, and , is the density of the wall material, c is the specific heat capacity of the wall material, and k is the thermal conductivity of the wall material;

[0104] ​​​The inner surface boundary condition is set as: ;

[0105] The outer surface boundary condition is: ;

[0106] The optimal thermal parameters of the building outer wall region are obtained by setting the thermal performance parameter optimization objective function and comparing the predicted temperature with the measured temperature.

[0107] The specific process of setting the thermal performance parameter optimization objective function and obtaining the optimal thermal parameters of the building outer wall region is as follows:

[0108] The thermal conductivity ki of the wall i, the inner surface convective heat transfer coefficient , the outer surface convective heat transfer coefficient , the density of the wall material , and the specific heat capacity c are integrated as the target parameter vector :

[0109] ;

[0110] The target parameter vector is optimized by minimizing the mean square error of the predicted temperature and the actual temperature, and the construction scheme of the building outer wall is set to m. Any construction scheme of the building outer wall is marked as j, and the thermal performance parameter optimization objective function is built:

[0111] ;

[0112] The model is fused by fusing the steady-state heat flux equation and the transient time series heat conduction equation to improve the comprehensiveness of data processing, and then the parameter optimization objective function is built to minimize the mean square error, and the optimal thermal parameters are output by inversion, which improves the inversion accuracy.

[0113] S4, the data output unit displays the abnormal region of the wall and obtains the repair suggestion, and then generates the optimal construction scheme of the building outer wall in combination with the optimal thermal parameters.

[0114] By setting m construction schemes of the building outer wall and calculating the minimum value of the objective function, the target parameter vector obtained is marked as the optimal thermal parameter, and the construction scheme obtained is marked as the optimal construction scheme of the building outer wall.

[0115] In summary, the present application realizes the spatial mapping of temperature, thickness and material properties by multi-source data fusion and three-dimensional infrared modeling, thereby accurately positioning thermal defects, and the whole process is automated, from data acquisition, analysis, diagnosis to optimization, reducing manual intervention, realizing the double improvement of detection efficiency and accuracy, overcoming the short board of traditional methods in efficiency, accuracy and real-time performance through data driving and model fusion, realizing the whole life cycle management of building external wall thermal performance, promoting the intelligent and data transformation of the detection industry, and realizing building energy saving and sustainable development.

[0116] Among them, the present application combines the infrared thermal imager and the three-dimensional laser scanner to build a three-dimensional infrared building model, supports local high-precision re-measurement, ensures the abnormal defect detection rate of key areas, and completes the preliminary analysis of the thermal parameters of the building wall through the edge port, and generates a thermal performance distribution map in real time, improving the speed of data processing and response;

[0117] The present application quickly locates the abnormal area of the wall by regional planning and contrast marking of the building external wall, and diagnoses and identifies problems such as insulation layer damage and thermal bridge, thereby generating a customized construction scheme based on the optimal thermal parameters, avoiding material waste, reducing the cost of energy saving and reconstruction, prolonging the service life of the building, and reducing the energy loss caused by thermal defects;

[0118] The present application fuses the steady-state heat flow density equation and the transient time sequence heat conduction equation to improve the comprehensiveness of data processing, and then builds a parameter optimization objective function to minimize the mean square error, thereby inverting the optimal thermal parameters and improving the inversion accuracy.

[0119] The setting of the size of the interval and the threshold value is for easy comparison, and the size of the threshold value depends on the number of sample data and the base number set by the person skilled in the art for each group of sample data; as long as it does not affect the proportional relationship of the parameters and the quantized numerical value.

[0120] The above formulas are dimensionless to calculate the numerical value, the formula is obtained by software simulation of a large amount of data to obtain the most real situation, and the preset parameters in the formula are set by the person skilled in the art according to the actual situation;

[0121] The above is only the preferred specific embodiment of the present application, but the protection scope of the present application is not limited thereto, any person skilled in the art can make equivalent replacement or change according to the technical scheme and the inventive concept of the present application within the technical range disclosed by the present application, which should be covered within the protection scope of the present application.

Claims

1. A data-driven method for testing the thermal performance of building exterior walls, characterized in that: Includes the following steps: S1, the data acquisition unit monitors the infrared and structural data of the building's exterior walls; S2, Edge computing unit analyzes the thermal parameters of building walls: By constructing a three-dimensional infrared building model, the thermal parameters of building walls are analyzed, and the distribution of thermal performance of the building exterior walls is displayed; The thermal parameters of building walls are analyzed using a heat transfer model. The specific process is as follows: The building walls are planned into N regions using a three-dimensional infrared building model, and any one region wall is marked as P. Set the area wall P to include n layers of wall material, mark the total wall thickness as L, mark any layer of wall as i, mark the thickness of wall i as di, and mark the thermal conductivity of wall i as ki; The inner surface temperature of the regional wall P is marked as... The outer surface temperature is marked as ; The indoor air temperature of the wall in area P is marked as... Outdoor air temperature is marked as ; Indoor heat flux density is obtained using a heat flow meter. Outdoor heat flux density ; The convective heat transfer coefficient of the inner surface is denoted as... The external convective heat transfer coefficient is denoted as ; Through the convective heat transfer coefficient of the inner surface Surface convective heat transfer coefficient By combining the thickness di of wall i and the thermal conductivity ki, the total thermal resistance R of the wall in region P is obtained, and then the heat transfer coefficient U of the wall in region P is obtained. Thermal parameters include heat transfer coefficient and total thermal resistance; S3, the central processing unit performs regional anomaly intelligent diagnosis and thermal performance optimization inversion of building walls: regional planning and comparison marking are performed through the thermal performance distribution of building exterior walls, anomaly areas of the walls are identified and output, and by setting the construction plan of the building exterior walls in m, the predicted temperature is made to continuously approach the measured temperature, the parameter optimization objective function of thermal performance is built, and the optimal thermal parameters of the building exterior wall area are output. The specific process of intelligent diagnosis of regional anomalies in building walls is as follows: The thermal performance distribution of the building's exterior walls is displayed using a three-dimensional infrared building model. Then, regional planning and comparison marking are performed. The standard threshold for the total thermal resistance of the regional walls is set as Qr, and the standard threshold for the heat transfer coefficient of the regional walls is set as Qu. When the total thermal resistance R of the wall in region P is higher than the standard threshold Qr and the heat transfer coefficient U is lower than the standard threshold Qu, the thermal performance of the wall in region P is determined to be normal; otherwise, the thermal performance of the wall in region P is determined to be abnormal, thereby identifying and outputting abnormal wall areas. Then, intelligent diagnosis is performed on abnormal areas of the wall to determine the condition of insulation layer damage, thermal bridging, cracks and poor sealing; The specific process of optimizing and inverting the thermal performance of building walls is as follows: The steady-state and instantaneous heat transfer of the wall are analyzed using the surface heat transfer equation and the time-series heat conduction equation, respectively. The specific process is as follows: Through heat transfer coefficient U, indoor air temperature and outdoor air temperature Combined, the heat flux density of steady-state heat transfer in wall P is analyzed. ; heat flux density Substitute the values ​​into the surface heat transfer equation to obtain the predicted internal and external surface temperatures; mark For the predicted inner surface temperature, The predicted outer surface temperature; If the inner surface boundary space point q is marked as 0, then the outer surface boundary space point q is marked as L. If any time node is marked as t, then the wall surface temperature corresponding to the space point q and the time node t is marked as T(q,t). By the density of the wall material Specific heat capacity c and thermal conductivity k are used to obtain thermal diffusivity. ; Establish the time-series heat conduction equation and set the boundary conditions for the inner and outer surfaces; Then, by setting the objective function for optimizing thermal performance parameters, thermal performance optimization inversion is performed. The predicted temperature is compared with the measured temperature to obtain the optimal thermal parameters for the building's exterior wall area. The specific process of setting the objective function for optimizing thermal performance parameters and obtaining the optimal thermal parameters for the building's exterior wall area is as follows: The thermal conductivity ki of wall i and the convective heat transfer coefficient of its inner surface are considered. Surface convective heat transfer coefficient Density of wall materials And the specific heat capacity c is integrated and labeled as the target parameter vector. ; By minimizing the mean square error between the predicted and actual temperatures, the target parameter vector is... To perform inverse optimization, there are m construction schemes for the building's exterior walls. Each construction scheme for the building's exterior walls is labeled as j. An objective function for optimizing the thermal performance parameters is then established. By setting m construction schemes for the building exterior wall and calculating the minimum value of the objective function, the resulting objective parameter vector is labeled as the optimal thermal parameters, and the resulting construction scheme is labeled as the optimal construction scheme for the building exterior wall. By minimizing the mean square error between the predicted and actual temperatures, the target parameter vector is... Inverse optimization is performed to establish the objective function for parameter optimization of thermal performance: ； S4, the data output unit displays abnormal areas of the wall and obtains maintenance suggestions, and then, combined with the optimal thermal parameters, generates the optimal construction plan for the building's exterior wall. Pre-set corresponding repair suggestions for each diagnostic result, and match the corresponding repair suggestions by displaying abnormal areas of the wall and intelligent diagnostic results; The results of the intelligent diagnosis were verified by conducting an actual inspection of the walls in the abnormal areas. If the verification diagnosis is correct, the wall maintenance management will be carried out according to the maintenance suggestions output by the system; otherwise, if the verification diagnosis is incorrect, the professional technicians will be prompted to carry out wall maintenance management according to the actual situation.

2. The data-driven method for detecting the thermal performance of building exterior walls according to claim 1, characterized in that: The data acquisition unit includes an infrared thermal imager and a 3D laser scanner; Infrared data of the building's exterior walls are acquired using an infrared thermal imager, while structural data is acquired using a 3D laser scanner. A three-dimensional infrared building model is constructed by combining infrared data of the building's exterior walls and structural data. Infrared data includes the internal and external surface temperatures of building walls and indoor and outdoor air temperatures; Structural data includes the three-dimensional location, thickness, and thermal conductivity of the building walls.

3. The data-driven method for detecting the thermal performance of building exterior walls according to claim 1, characterized in that: The specific process for intelligently diagnosing abnormal areas of the wall to determine conditions such as insulation layer damage, thermal bridging, cracks, and poor sealing is as follows: By calculating the rate of change of thermal resistance of the regional walls And set the threshold to When the rate of change of thermal resistance Exceeding the set threshold If so, it is determined that the wall insulation layer is damaged; By measuring the temperature difference between the area wall P and the surrounding walls. And set the threshold to When the temperature difference Exceeding the set threshold If so, it is determined that there is a thermal bridge in the wall; A grayscale image of the wall P in the area is obtained by a 3D laser scanner, and the grayscale image of the wall is denoised by Gaussian filtering, so as to compare and determine whether there are cracks in the wall. By analyzing the rate of temperature change in the interior wall and comparing it with the rate of temperature change in a normal area under sealed wall conditions, the difference in temperature change rate is obtained. And set the threshold to When the difference in the rate of temperature change Exceeding the threshold If so, it is determined that the wall is not properly sealed.

4. The data-driven method for detecting the thermal performance of building exterior walls according to claim 3, characterized in that: The specific process of determining the presence of cracks in a wall through Gaussian filtering and noise reduction comparison is as follows: Set the grayscale image of the wall as I(x, y), where x is the horizontal coordinate of the image and y is the vertical coordinate of the image; The Gaussian filter function is labeled as G(x, y, σ), where σ is the standard deviation of the gray values ​​of the image pixels. After filtering the grayscale image I(x,y) of the wall using the Gaussian filter function G(x,y,σ), the denoised image Iqz(x,y) is obtained, and then the gradient magnitude M(x,y) and gradient direction γ(x,y) are obtained; after non-maximum suppression, Mnms(x,y) is obtained. Set a high threshold for Mnms(x,y). and low threshold Then perform a threshold comparison: When Mnms(x,y) > high threshold If so, then mark the pixel as a strong edge point; When Mnms(x,y) < low threshold If the condition is met, then the pixel is marked as a non-edge point; When low threshold ≤Mnms(x,y)≤High threshold If the condition is met, the pixel is marked as the edge of the crack, indicating that a crack exists in the wall.

Images