A method for detecting damage to building exterior walls based on infrared thermal imaging

Abstract

This invention discloses a method for detecting damage to building exterior walls based on infrared thermal imaging, belonging to the field of building inspection technology. The proposed scheme involves: acquiring structural data, impact data, and prediction time of the current building surface; inputting the structural data into a pre-constructed degradation correlation formula to obtain the predicted heat transfer rate; inputting the impact data and prediction time into an aging impact factor coefficient formula to calculate the aging impact factor coefficient; correcting the predicted heat transfer rate using the aging impact factor coefficient to obtain the corrected predicted heat transfer rate; comparing the corrected predicted heat transfer rate with the material's standard heat transfer rate to obtain the aging coefficient; and obtaining the hazard level of the target building based on the aging coefficient and a pre-defined mapping table representing the relationship between the aging coefficient and the degree of danger. The degradation correlation formula and the aging impact factor coefficient formula clearly quantify the comprehensive impact of environmental factors on material aging, making the assessment more accurate.

Description

Technical Field

[0001] This invention relates to the field of building inspection technology, specifically to a method for detecting damage to building exterior walls based on infrared thermal imaging. Background Technology

[0002] Infrared thermal imagers are widely used in non-destructive testing of building exterior walls. Based on the laws of thermal radiation and the differential equation of heat conduction, they can measure the temperature distribution of an object's surface remotely, non-contactly, in real time, and quickly, and display the temperature differences in the form of visual images, thereby enabling intuitive and accurate detection of defects and damage to building exterior walls.

[0003] Traditional methods (such as infrared thermal imaging detection) can only obtain the current apparent damage data of a building (such as crack width and hollow area), and cannot combine environmental variables (temperature, humidity, concentration of corrosive media, etc.) with the time dimension to dynamically predict future aging trends. Although a few studies have been conducted to predict future aging trends, existing aging models usually simplify environmental variables to constant values ​​or empirical coefficients, and do not dynamically integrate real-time impact data (such as acid rain frequency and freeze-thaw cycle number), thus resulting in insufficient accuracy in aging prediction. Summary of the Invention

[0004] To address the existing problems, this invention provides a method for detecting damage to building exterior walls based on infrared thermal imaging.

[0005] To achieve the above objectives, the technical solution of the present invention is as follows:

[0006] In a first aspect, this application discloses a method for detecting damage to building exterior walls based on infrared thermal imaging, comprising the following steps:

[0007] Obtain structural data, impact data, and prediction time of the current building surface;

[0008] The structural data is input into a pre-constructed degradation correlation formula to obtain the predicted thermal conductivity.

[0009] Input the impact data and the predicted time into the aging impact factor coefficient formula to calculate the aging impact factor coefficient.

[0010] The corrected predicted thermal conductivity is obtained by adjusting the predicted thermal conductivity using the aging effect factor coefficient.

[0011] The aging coefficient is obtained by comparing the corrected predicted thermal conductivity with the standard thermal conductivity of the material.

[0012] The hazard level of the target building is obtained by referring to the aging coefficient and a pre-defined mapping table that represents the relationship between the aging coefficient and the degree of danger.

[0013] Secondly, this application introduces a building exterior wall damage detection system based on infrared thermal imaging, including the following modules:

[0014] A building exterior wall aging prediction system, characterized in that the system applies the aforementioned building exterior wall damage detection method based on infrared thermal imaging, and the system includes:

[0015] The data acquisition module is used to acquire in real time the structural data, impact data, and prediction time of the current surface of the building.

[0016] The data processing module is used to input structural data into a pre-built degradation correlation formula to obtain the predicted thermal conductivity rate; it is also used to input the influence data and the predicted time into the aging influence factor coefficient formula to calculate the aging influence factor coefficient; it is also used to correct the predicted thermal conductivity rate after applying the aging influence factor coefficient to obtain the corrected predicted thermal conductivity rate; and it is also used to compare the corrected predicted thermal conductivity rate with the material standard thermal conductivity rate to obtain the aging coefficient.

[0017] The data analysis module is used to obtain the hazard level of the target building based on the aging coefficient and a preset reference table that represents the mapping relationship between the aging coefficient and the degree of danger.

[0018] Thirdly, the present invention provides a computing device, comprising:

[0019] Memory, used to store programs;

[0020] A processor is used to execute computer-executable instructions that, when executed by the processor, implement the steps of the aforementioned method for detecting damage to building exterior walls based on infrared thermal imaging.

[0021] Fourthly, the present invention provides a computer-readable storage medium comprising: when a program is executed by a processor, implementing the aforementioned method for detecting damage to building exterior walls based on infrared thermal imaging.

[0022] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0023] 1. This application uses a degradation correlation formula to predict the thermal conductivity rate, linking structural data with the thermal conductivity rate, so that the assessment is based on physical changes rather than subjective experience alone; the aging influence factor coefficient formula clearly quantifies the comprehensive impact of environmental factors on material aging, making the assessment more accurate; the corrected predicted thermal conductivity rate is compared with the standard thermal conductivity rate of the material to obtain a quantified aging coefficient, providing an objective and measurable indicator of the degree of degradation.

[0024] 2. This application incorporates the time factor into the aging impact factor coefficient formula for calculation, which makes the assessment result not a static description of the current state, but a prediction of the degree of aging at a specific point in the future; based on the prediction result, the risk level is assessed, and potential structural safety hazards can be identified in advance, providing a valuable time window for preventive maintenance, reinforcement or evacuation decisions. Attached Figure Description

[0025] The disclosure of this invention is illustrated with reference to the accompanying drawings. It should be understood that the drawings are for illustrative purposes only and are not intended to limit the scope of protection of this invention. In the drawings, the same reference numerals are used to refer to the same parts. Wherein:

[0026] Figure 1 This is a flowchart illustrating a method for detecting damage to building exterior walls based on infrared thermal imaging, as described in this invention.

[0027] Figure 2 A flowchart for constructing the degenerate mapping formula;

[0028] Figure 3 A flowchart for constructing the formula for the aging impact factor coefficient;

[0029] Figure 4 This is a flowchart of a building exterior wall aging prediction system. Detailed Implementation

[0030] It is readily understood that, based on the technical solution of this invention, those skilled in the art can propose various interchangeable structural methods and implementations without altering the essential spirit of the invention. Therefore, the following detailed embodiments and accompanying drawings are merely illustrative examples of the technical solution of this invention and should not be considered as the entirety of the invention or as limitations or restrictions on the technical solution of this invention.

[0031] In existing technologies, infrared thermal imaging is only used when problems arise in building aging, rather than for predicting the aging of existing buildings.

[0032] To solve the above problems, such as Figure 1 As shown, this invention proposes a method for detecting damage to building exterior walls based on infrared thermal imaging, comprising the following steps:

[0033] S1. Obtain structural data, impact data, and prediction time of the current building surface;

[0034] S2. Input the structural data into the pre-built degradation correlation formula to obtain the predicted heat transfer rate; input the influence data and the predicted time into the aging influence factor coefficient formula to calculate the aging influence factor coefficient.

[0035] S3. The predicted thermal conductivity rate is corrected by applying the aging influence factor coefficient to obtain the corrected predicted thermal conductivity rate.

[0036] S4. Compare the corrected predicted thermal conductivity with the standard thermal conductivity of the material to obtain the aging coefficient;

[0037] S5. Based on the aging coefficient and a pre-defined mapping table representing the relationship between the aging coefficient and the degree of danger, the danger level of the target building is obtained.

[0038] Regarding step S1.

[0039] Obtain structural data, impact data, and prediction time of the current surface of the building.

[0040] Structural data includes temperature field distribution data on building surfaces, ambient temperature and humidity near buildings, standard thermal conductivity of building materials, spatial data on building porosity, and spatial data on salt crystallinity; influencing data includes historical average annual freeze-thaw cycles, historical average annual acid rain frequency, and historical annual extreme high temperature duration; prediction time is in years.

[0041] The methods for obtaining data are as follows:

[0042] Infrared thermal imaging is used to scan and acquire temperature field distribution data on the building surface, identifying localized low-temperature evaporation zones and high-temperature dehydration areas. Real-time temporal data of ambient temperature and humidity are acquired using temperature and humidity sensors. Ultrasonic tomography is used to quantify the pore connectivity decay curve from the material surface to a depth of 50 mm, generating spatial porosity data. Ion-sensitive electrodes are embedded at pre-defined grid points to acquire salt crystallinity data. The baseline temperature transfer rate of the building materials is obtained from an existing database of building material thermal conductivity. Historical average annual freeze-thaw cycles, acid rain frequency, and extreme high-temperature duration data for the building's location are extracted from a historical meteorological database. The required building prediction time is then obtained.

[0043] Regarding step S2.

[0044] The purpose of the degradation correlation formula is to mathematically correlate the thermal conductivity of a building with the spatial data of material porosity and the spatial data of salt crystallinity.

[0045] like Figure 2 As shown, the method for establishing the degenerate correlation formula includes the following steps:

[0046] Simultaneously collect structural data of the building surface.

[0047] (1) Data acquisition stage

[0048] Infrared thermal imaging was used to scan and acquire temperature field distribution data of the building surface, identifying localized low-temperature evaporation zones and high-temperature dehydration areas. Real-time temporal data of ambient temperature and humidity were acquired using temperature and humidity sensors. Ultrasonic tomography was used to quantify the pore connectivity decay curve from the surface to a depth of 50 mm, obtaining spatial data on material porosity. Ion-sensitive electrodes were embedded at pre-defined grid points to acquire spatial data on salt crystallinity. The baseline temperature transfer rate of the building materials was obtained using an existing database of building material thermal conductivity.

[0049] (2) Data processing stage

[0050] The acquired temperature field distribution data of the building surface, the time series data of ambient temperature and humidity, the spatial data of material porosity, and the spatial data of salt crystallinity are input into a multivariate correlation model, and a time series fluctuation coefficient of temperature and humidity is further introduced. (in Standard deviation (Assuming the mean), construct a quaternary coupled equation:

[0051]

[0052] in, These are the material property constants calibrated using the particle swarm optimization algorithm. Spatial data for material porosity. This is spatial data on salt crystallinity. For ambient temperature, This refers to ambient humidity.

[0053] (3) Data output stage

[0054] This equation is the degeneracy correlation formula.

[0055] The construction of a multivariate association model includes the following steps:

[0056] (1) Data acquisition stage

[0057] Infrared thermal imaging was used to scan and acquire temperature field distribution data of the building surface, identifying localized low-temperature evaporation zones and high-temperature dehydration areas. Real-time temporal data of ambient temperature and humidity were acquired using temperature and humidity sensors. Ultrasonic tomography was used to quantify the pore connectivity attenuation curve from the surface to a depth of 50 mm, obtaining spatial data on material porosity. Ion-sensitive electrodes were embedded at pre-defined grid points to acquire spatial data on salt crystallinity. The baseline temperature transfer rate of the building materials was obtained using an existing database of building material thermal conductivity.

[0058] (2) Data processing stage

[0059] Step 1: Data Preprocessing

[0060] Infrared temperature field distribution data and porosity spatial data are integrated using a spatial registration unit. and spatial data of salt crystallinity Aligned to the same coordinate system; spatial registration units use Kriging interpolation algorithm to integrate discrete porosity data. Salt crystallinity data Resampling was performed to obtain spatial grid data that matched the resolution of the infrared temperature field. A temporal alignment unit was used to synchronize the ambient temperature and humidity data with the temperature field acquisition timestamp.

[0061] Step 2: Constraints

[0062] Under the conditions of satisfying the dynamic response correlation engine and multi-parameter coupling mechanism, the original data is converted into model parameters to obtain a multivariate correlation model.

[0063] The establishment of a dynamic response correlation engine includes the following steps:

[0064] a. Thermal insulation performance diagnosis:

[0065] By capturing events of sudden rise / fall in ambient temperature (with a change slope > 5℃ / h), the time delay required for the surface temperature to reach 90% of its steady state was calculated to establish a negative correlation between delay time and porosity.

[0066] If the reduction in delay time exceeds a threshold (e.g., 20%), it is considered a deterioration in thermal insulation performance.

[0067] The criteria for determining deteriorated area marking are as follows:

[0068]

[0069] in: The calculated predicted value of the heat conduction rate, To measure the conduction rate, This is the threshold for judging material degradation.

[0070] b. Analysis of salt crystallization zones:

[0071] When the ambient humidity is consistently >80%, track the expansion rate of the low-temperature zone on the surface. If the rate is proportional to the increase rate of salt concentration, it is marked as a salt non-crystalline zone.

[0072] During the drying cycle (humidity <40%), the spatial offset between the peak coordinates of salt concentration and the highest point of surface temperature is detected. If the offset is >10cm, it is determined to be a salt crystallization zone.

[0073] The output function of the heat transfer anomaly early warning report is:

[0074]

[0075] In the formula: This is the critical value for safe salt crystallization. Representing coordinates Warning triggered

[0076] Multi-parameter coupling mechanisms include the following:

[0077] a. Damage conditions in the salt crystallization zone:

[0078] When the spatial overlap between regions with porosity > 25% and regions with salt concentration > 0.6% is ≥ 70%, the periodic salt crystallization damage mechanism is activated.

[0079] b. Introduce a time-dimensional variable:

[0080] Comparing the porosity monitoring data of the same location over the years, if the pore expansion rate is >2% / year for three consecutive years, the area is marked as an accelerated degradation zone.

[0081] When salt crystallization and blockage are detected in the pores, the critical salt concentration threshold for that area is automatically increased by 30%.

[0082] When local The measured value deviates from the model prediction value by more than a threshold. When this occurs, an alarm signal is triggered indicating abnormal porosity or failure of salt crystallization.

[0083] Step 3: Establish a temperature conduction rate calculation unit

[0084] The temperature field distribution data of the building surface and the time-series data of ambient temperature and humidity are used to obtain the real-time temperature transfer rate of the building materials through the heat conduction formula. The local heat conduction rate is then solved based on the temporal and spatial gradients of the temperature field data. :

[0085]

[0086] in, For temperature field, For time, This represents the space temperature gradient.

[0087] Step 4: Build the dataset

[0088] A dataset was constructed by collecting spatial data on building material temperature transfer rate, ambient temperature and humidity, material porosity, and salt crystallinity. The dataset was then constructed based on a reference table of correlation parameters between material porosity, salt crystallinity, and thermal conductivity rate.

[0089] The correlation parameter lookup table is expressed in the following matrix form:

[0090]

[0091] in, These are discrete porosity sample values. , These are discrete salt crystallinity sample values. , For the combination of ambient temperature and humidity, , This is the heat conduction rate predicted by the model.

[0092] Step 5: Dataset Processing

[0093] Outlier removal was performed on the dataset using the IQR (Interquartile Range) method. Each data point after outlier removal was then independently standardized using Z-score.

[0094] Data augmentation is achieved by adding Gaussian noise with a specified signal-to-noise ratio and expanding the dataset using linear interpolation.

[0095] The random forest algorithm is used to filter the preprocessed dataset to obtain key data and extract interference features.

[0096] We reduce mean squared error (MSE) by weighting the data and optimize the training of the dataset using a fully convolutional network (FCN).

[0097] Model stability is assessed by evaluating the error value of the key indicator (wavelength mean absolute error) through multiple rounds of cross-validation.

[0098] (3) Data output stage

[0099] Constructing a multivariate correlation model: Incorporating porosity Salt crystallinity Ambient temperature and humidity ( As input variables, output a multivariate correlation model:

[0100]

[0101] (in For model residuals, the function (obtained through training with support vector machines or neural networks)

[0102] The purpose of the aging impact factor coefficient formula is to incorporate the influence of historical environmental data on building materials. After correction by the aging impact factor coefficient, the final aging coefficient can still maintain high accuracy when predicting changes over time, reducing detection errors caused by changes in the predicted time.

[0103] like Figure 3As shown, the construction of the aging impact factor coefficient formula includes the following steps:

[0104] (1) Data acquisition stage

[0105] The impact data of the area is collected through the local historical meteorological database. The impact data includes the historical annual average number of freeze-thaw cycles, the historical annual average acid rain frequency, and the historical annual average duration of extreme high temperatures.

[0106] (2) Data processing stage

[0107] Step 1: Data Normalization

[0108] The obtained data is normalized and calibrated, and the obtained data are converted into dimensionless parameters in the 0-1 interval;

[0109] Number of freeze-thaw cycles per year Normalization transformation is performed to obtain The measured number of freeze-thaw cycles is divided by a preset climate zone baseline value. The baseline value is set according to frigid, temperate, and subtropical zones: ;

[0110] Annual acid rain frequency Convert to probability value Convert the percentage of acid rain frequency to a scale value between 0 and 1: ;

[0111] Duration of extreme high temperatures throughout the year Normalization transformation is performed to obtain The formula for converting the number of consecutive days of high temperatures into the proportion of the total number of days in the year is as follows: ;

[0112] in, The number of freeze-thaw cycles per year. The preset maximum number of freeze-thaw cycles is set as a baseline value (e.g., 50 for frigid zones, 80 for temperate zones, and 100 for subtropical zones). The annual acid rain frequency, This refers to the duration of the annual extreme high temperatures.

[0113] Step 2: Setting physical constraints:

[0114] Constraints for sign regression are set based on the material aging mechanism:

[0115] Freeze-thaw damage item power index >0 indicates the nonlinear characteristics of damage accumulation;

[0116] High temperature damage items attenuation coefficient k>0, ensuring that damage increases monotonically with exposure time;

[0117] The weighting coefficients satisfy the normalization constraint w 1+ w 2+ w 3=1 and wi ≥0.

[0118] Step 3: Symbolic Regression Execution:

[0119] The tree-structured coding formula is used, and iterative optimization is performed according to the following process:

[0120] (a) Initialization: Randomly generate a population of formulas, with the operator set {+, ×, exp, exponentiation} and the number of operands { Nn , An , Hn ,constant};

[0121] (b) Assessment: Calculating fitness ,in Mean square error, Constraint satisfaction factor (when all constraints are satisfied) =1, otherwise =0.1);

[0122] (c) Selection and genetic operations: Select high-fitness individuals through roulette wheel selection, and perform subtree crossover and node mutation;

[0123] (d) Iteration Termination: When the optimal formula... Below the threshold It may terminate when it reaches 1000 generations.

[0124] Step 4: Formula Refinement

[0125] Numerical optimization of the optimal formula for the symbolic regression output:

[0126] Fine-tuning the coefficients using gradient descent with L2 regularization { w 1, w 2, w 3, p , k};

[0127] Regularization strength λ =0.01, suppressing overfitting and ensuring the physical rationality of the coefficients.

[0128] (3) Data output stage

[0129] The formula for the aging impact factor coefficient is obtained by combining symbolic regression with physical constraints, ensuring physical rationality. The accuracy of the coefficient is improved by linear compensation and constraint optimization.

[0130] Formula for aging impact factor coefficient:

[0131]

[0132] Add the time correction parameter to the company's refined formula.

[0133] Output the formula for the final aging impact factor coefficient:

[0134]

[0135] in, This is a dimensionless parameter representing the number of freeze-thaw cycles per year. is a dimensionless parameter representing the frequency of acid rain. For the dimensionless parameter of the duration of extreme high temperature, , , Here are the weighting coefficients, and the weighting constraints are: power exponent Characterizing the nonlinear features of freeze-thaw damage, attenuation coefficient For high temperature damage rate, .

[0136] The weighting is dynamically adjusted based on the building material type; the power exponent and decay coefficient need to be realized by combining accelerated aging tests with inversion of actual engineering data.

[0137] The above details the methods and steps for constructing the aging impact factor coefficient model. Below, we will specifically illustrate an application scenario using this embodiment:

[0138] Data on concrete buildings in a temperate region in 2023:

[0139] Freeze-thaw cycles: 52 (temperate baseline 80 cycles → normalized value 0.65)

[0140] Acid rain frequency: 22% (normalized value 0.22)

[0141] High temperatures persisted for 68 days (0.186% of the total annual total).

[0142] Processing procedure: Assume the power exponent is 1.8 and the attenuation coefficient is 3.2.

[0143] Freeze-thaw damage: 0.5 × (0.65)^1.8 = 0.5 × 0.47 = 0.235

[0144] Acid rain damage: 0.3 × 0.22 = 0.066

[0145] High-temperature damage: 0.2 × (1 - e^{-3.2 × 0.186}) = 0.2 × 0.45 = 0.090

[0146] Time correction parameter: 0.5

[0147] The comprehensive aging impact factor coefficient is: (0.235 + 0.066 + 0.090) × 0.5 = 0.1955

[0148] Output result: The comprehensive aging impact factor coefficient is 0.1955.

[0149] The process of obtaining time correction parameters includes the following steps:

[0150] (1) Data acquisition stage

[0151] The data acquisition steps include: collecting daily temperature time series data for consecutive historical years in the target area through the local historical meteorological database, with a minimum time span of 15 calendar years;

[0152] The occurrence status of a single day's freeze-thaw event is determined based on a preset freeze-thaw temperature difference threshold, which is set as the daily maximum temperature ≥ 0℃ and the daily minimum temperature ≤ -3℃.

[0153] Generate an annual sequence of total freeze-thaw cycles based on the natural year, and simultaneously record the starting month and duration of each year's freeze-thaw period.

[0154] (2) Data processing stage

[0155] Data processing steps include:

[0156] Step 1: Data Reconstruction Phase

[0157] For missing years, spatial weighted interpolation of nearby weather stations was used to complete the data, and abnormal fluctuation points were eliminated based on moving median filtering.

[0158] Step 2: Feature Derivation Stage

[0159] Extract the long-term trend component, seasonal fluctuation component, and interannual variability intensity of historical sequences; construct the correlation characteristics of climate driving factors, including: the annual mean of the El Niño index and the winter integral value of the Arctic Oscillation Index;

[0160] Step 3: Model Training Phase

[0161] The reconstructed feature set is input into a bidirectional temporal encoder, and cross-year dependencies are captured through an attention mechanism; the network weights are dynamically adjusted with the annual freeze-thaw time offset as the optimization target.

[0162] (3) Data output stage

[0163] The data output steps include:

[0164] (a) Perform freeze-thaw time pattern prediction for the next 1-5 calendar years, and output the annual time adjustment coefficient as the core parameter. Its physical definition is:

[0165]

[0166] in, To predict the ordinal number of the start date of the annual freeze-thaw period (annual cumulative days). The ordinal number corresponding to the historical baseline year;

[0167] Regarding step S3.

[0168] The corrected predicted thermal conductivity rate is obtained by correcting the predicted thermal conductivity rate with the aging influence factor coefficient, as shown in the formula:

[0169]

[0170] in, To predict the heat conduction rate, This represents the coefficient of the aging impact factor.

[0171] Regarding step S4.

[0172] S4. Compare the corrected predicted thermal conductivity with the standard thermal conductivity of the material to obtain the aging coefficient;

[0173]

[0174] in, The corrected predicted heat transfer rate, This is the standard thermal conductivity rate of the material.

[0175] Regarding step S5.

[0176] A static correspondence table between the discrete intervals of aging coefficients and hazard levels was established, where the threshold boundary values ​​were determined based on the critical points of structural failure probability specified in industry standards. The table is as follows:

[0177] The continuous aging coefficient range [0,1] is discretized into preset hazard levels, including:

[0178] Level I (Safety Domain): Aging coefficient ≤ 0.3, corresponding to a state with no significant structural risk;

[0179] Level II (Warning Zone): 0.3 < aging coefficient ≤ 0.5, corresponding local components need to be monitored;

[0180] Level III (Hazardous Area): 0.5 < aging coefficient ≤ 0.7, corresponding to a decline in the overall reliability of the structure;

[0181] Level IV (High-Risk Area): Aging coefficient > 0.7, requiring immediate intervention.

[0182] Furthermore, since this application primarily addresses building aging, various factors can affect building aging, such as water seepage. Therefore, when collecting data, if it is necessary to determine whether a building is experiencing water seepage, the structural data collected in this application can be analyzed.

[0183] For example, the spatial data of building porosity and salt crystallinity collected in step 1 of this application are important because seepage areas are prone to salt precipitation and crystallization, leading to crack patterns such as straight lines and grids. When the spatial data of building porosity and salt crystallinity in a certain area are significantly different from those in other areas or differ greatly from historically collected data, there is reason to suspect that seepage exists in that area. This can be further verified by combining the temperature field distribution data of the building surface obtained by scanning with an infrared thermal imager. Therefore, if seepage exists, the temperature in the seepage area will be lower than that in the non-seepage area. If the temperature in this area is lower than other temperatures, it indicates that seepage exists in that area. If the seepage is severe, it can be observed on the exterior of the building, with discoloration, stains, water stains, wet spots, cracks, and in severe cases, even peeling, flaking, tilting, or deformation of the wall.

[0184] Based on the collected data and preset thresholds, the degree of water seepage is analyzed and categorized into three levels: severe seepage (large area) carries the risk of structural deformation; moderate seepage (large area dampness) affects building durability; and slight seepage (localized dampness) mainly leads to surface deterioration. For slight seepage, the seepage area is monitored more frequently than other areas during the aging prediction process. For severe or moderate seepage, the relevant departments are notified to carry out maintenance.

[0185] One of the main factors contributing to water seepage is the presence of hollow areas in the building. These hollow areas primarily manifest as localized surface bulges or wrinkles, often exhibiting noticeable color differences due to temperature and humidity variations, accompanied by secondary discoloration caused by water seepage. The edges of hollow areas often show a stretched state, frequently accompanied by radial or annular cracks, with crack morphologies including straight, serrated, and network patterns. Hollow areas are often accompanied by moisture, structural stress, and abnormal vibrations. Furthermore, based on the size of the hollow area, it can be classified into three levels: severe hollow areas (>0.5m). 2 There is a safety hazard due to detachment; moderate hollow areas (0.1-0.5m) 2 This affects the appearance and waterproof performance, causing slight blistering (<0.1m). 2 This has no direct impact on structural safety. Therefore, while determining whether a building is leaking, it is also possible to simultaneously determine whether the leak is caused by hollow areas, thus assisting maintenance personnel in accurately locating the damage.

[0186] Example 2

[0187] This embodiment introduces a building exterior wall damage detection system based on infrared thermal imaging, including:

[0188] The data acquisition module 100 is used to acquire in real time the structural data, impact data and prediction time of the current surface of the building;

[0189] The data processing module 200 is used to input structural data into a pre-built degradation correlation formula to obtain the predicted thermal conductivity rate; it is also used to input the influence data and the predicted time into the aging influence factor coefficient formula to calculate the aging influence factor coefficient; it is also used to correct the predicted thermal conductivity rate after applying the aging influence factor coefficient to obtain the corrected predicted thermal conductivity rate; and it is also used to compare the corrected predicted thermal conductivity rate with the material standard thermal conductivity rate to obtain the aging coefficient.

[0190] The data analysis module 300 is used to obtain the hazard level of the target building based on the aging coefficient and a preset reference table that represents the mapping relationship between the aging coefficient and the degree of danger.

[0191] Example 3

[0192] This embodiment describes a computing device, including:

[0193] Memory, used to store programs;

[0194] A processor is used to execute computer-executable instructions that, when executed by the processor, implement a method for detecting damage to building exterior walls based on infrared thermal imaging.

[0195] Example 4

[0196] This embodiment introduces a computer-readable storage medium storing a program that, when executed by a processor, implements a method for detecting damage to building exterior walls based on infrared thermal imaging.

[0197] The storage medium proposed in this embodiment belongs to the same inventive concept as the building exterior wall damage detection method based on infrared thermal imaging proposed in the above embodiments. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0198] From the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented using software and necessary general-purpose hardware, and of course, it can also be implemented using hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention essentially contributes to the prior art.

[0199] Some of these components may be embodied in the form of a software product, which may be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of the various embodiments of the present invention.

[0200] The technical scope of this invention is not limited to the content described above. Those skilled in the art can make various modifications and variations to the above embodiments without departing from the technical concept of this invention, and all such modifications and variations should fall within the protection scope of this invention.

Claims

1. A method for detecting damage to an exterior wall of a building based on infrared thermography, characterized in that, The method comprises the following steps: obtaining structure data, influence data and prediction time of the current surface of the building; inputting the structure data into a pre-constructed degradation correlation formula to obtain a predicted heat conduction rate; inputting the influence data and the prediction time into an aging influence factor coefficient formula to obtain an aging influence factor coefficient; correcting the predicted heat conduction rate by the aging influence factor coefficient to obtain a corrected predicted heat conduction rate; comparing the corrected predicted heat conduction rate with a material standard heat conduction rate to obtain an aging coefficient; obtaining the danger level of the target building according to the aging coefficient and a preset mapping relationship between the aging coefficient and the danger level; The method for establishing the degradation correlation formula comprises the following steps: obtaining structure data of the surface of the building; The obtained structure data is input into a multivariate correlation model, and a temperature and humidity time sequence fluctuation coefficient is introduced , a four-element coupling equation is constructed, and a degradation correlation formula is obtained: ； wherein, represents a predicted heat conduction rate; is a material property constant calibrated by a particle swarm optimization algorithm, is spatial data of material porosity, is spatial data of salt crystallinity, is an ambient temperature, is an ambient humidity; a temperature and humidity time series fluctuation coefficient , is a standard deviation, is a mean value, is ; The construction of the multivariate correlation model comprises the following steps: aligning the structure data to the same coordinate system through a spatial registration unit; under the condition of meeting the dynamic response correlation engine and the multi-parameter coupling mechanism, establishing a multivariate correlation model; constructing a data set according to the correlation of the material porosity-salt crystallinity-heat conduction rate; performing outlier processing, standardization processing and data enhancement processing on the data set; extracting interference features based on a random forest algorithm; optimizing and training the data set by weighting the data; inputting the optimized and trained data set into the multivariate correlation model to obtain a trained multivariate correlation model: wherein, is the model residual, the function is trained by a support vector machine or a neural network.

2. The method for detecting damage of an exterior wall of a building based on infrared thermography according to claim 1, wherein The structure data comprises temperature field distribution data of the surface of the building, time series data of environmental temperature and humidity, porosity spatial distribution data, salt crystallinity spatial data and building material benchmark temperature transfer rate; the influence data comprises historical annual average freeze-thaw cycle times, acid rain frequency and extreme high temperature duration data.

3. The method for detecting damage of an exterior wall of a building based on infrared thermography according to claim 1, wherein The construction of the aging influence factor coefficient formula comprises the following steps: obtaining influence data of the location of the building; normalizing and calibrating the obtained data to convert the obtained data into dimensionless parameters in the range of 0-1 respectively; setting constraint conditions for symbolic regression according to the material aging mechanism: Adopting tree structure encoding formula, randomly generating formula population, calculating formula fitness, selecting high fitness individual through roulette, executing sub-tree cross and node mutation, terminating when the optimal formula is lower than threshold value, adopting gradient descent method with L2 regularization to fine tune coefficient numerical optimization; lower than threshold value, adopting gradient descent method with L2 regularization to fine tune coefficient numerical optimization; obtaining the aging influence factor coefficient formula by symbolic regression combined with physical constraints, aging influence factor coefficient formula: Adding a time correction parameter to the refined formula; outputting the final aging influence factor coefficient formula: wherein, is a dimensionless parameter for the number of annual freeze-thaw cycles, is a dimensionless parameter for the acid rain frequency, is a dimensionless parameter for the duration of extreme high temperatures, , , is a weight coefficient, the weight constraint being , the power exponent characterizes the non-linear character of freeze-thaw damage, the decay coefficient is the high temperature damage rate, , is a time correction parameter, is the prediction time, in years.

4. The method for detecting damage of an exterior wall of a building based on infrared thermography according to claim 3, wherein The method for normalizing and calibrating the obtained data to convert the obtained data into dimensionless parameters in the range of 0-1 respectively is: to the number of annual freeze-thaw cycles : ; converting the annual acid rain frequency A into a scale value in the interval 0 to 1 ;​ The normalized conversion of the annual extreme high temperature duration H is obtained , and the conversion formula is ; wherein, is a predetermined region maximum freeze-thaw cycle number reference value.

5. The building outer wall damage detection method based on infrared thermal imaging according to claim 3, characterized in that, the process of obtaining the time correction parameter comprises: obtaining daily temperature time series data of the building area in consecutive historical years, determining the occurrence state of a single-day freeze-thaw event based on a preset freeze-thaw temperature difference threshold, and generating an annual freeze-thaw cycle total number sequence by aggregation according to natural years; completing the missing year data by using a spatial weighted interpolation method, and eliminating abnormal fluctuation points based on sliding median filtering; extracting long-term trend components, seasonal fluctuation components and interannual variability intensity of the historical sequence to construct climate driving factor correlation features; The reconstructed feature set is input into a bidirectional time sequence encoder, a cross-year dependency relationship is captured through an attention mechanism, and network weights are dynamically adjusted with an annual freeze time offset as an optimization target; Perform the prediction of the freeze-thaw time rule of the future natural year, and output the core parameter as the annual time adjustment coefficient , the physical definition of which is: , wherein, is the starting day sequence number (annual cumulative day) of the predicted year freeze-thaw period, is the corresponding day sequence number of the historical base year.

6. A building exterior wall damage detection system based on infrared thermography, characterized by, The system applies the building outer wall damage detection method based on infrared thermal imaging according to any one of claims 1-5, and the system comprises: A data acquisition module is configured to acquire structural data, influence data and prediction time of a current surface of a building in real time; The data processing module is configured to input the structural data into a pre-constructed degradation correlation formula to obtain a predicted heat conduction rate, input the influence data and the prediction time into an aging influence factor coefficient formula to calculate an aging influence factor coefficient, input the predicted heat conduction rate after correction by the aging influence factor coefficient to obtain a corrected predicted heat conduction rate, and compare the corrected predicted heat conduction rate with a material standard heat conduction rate to obtain an aging coefficient; The data analysis module is configured to obtain a danger level of the target building according to the aging coefficient and a reference to a preset mapping relationship between the aging coefficient and the danger level.

7. An electronic device, comprising: Comprise: A memory for storing a program; A processor for loading the program to execute the steps of the building outer wall damage detection method based on infrared thermal imaging according to any one of claims 1-5.

8. A computer-readable storage medium storing a program, characterized in that, The program is executed by the processor to implement the steps of the building outer wall damage detection method based on infrared thermal imaging according to any one of claims 1-5.

Images