A method and system for measuring water penetration of an architectural exterior wall

Abstract

The application belongs to the technical field of building engineering detection, and discloses a building outer wall water seepage measuring method and system, the method comprises the following steps: arranging a humidity sensor array on the surface and inside of the outer wall, collecting multi-point humidity original data, performing abnormal correction and noise reduction, obtaining a complete preprocessed data set, inputting the data into a diffusion modeling module, performing time series analysis and spatial distribution estimation, generating a water seepage diffusion characteristic matrix and extracting key diffusion parameters, calculating a prediction value in a penetration depth estimation model based on the parameter set, constructing a water seepage distribution curve, calling a risk judgment module, comparing the prediction result with a safety threshold, and outputting a risk level. The system comprises a data acquisition and preprocessing module, a diffusion modeling and feature extraction module, and a penetration estimation and risk evaluation module. The application can realize dynamic monitoring and graded risk evaluation of outer wall water seepage, and provide a reliable basis for building maintenance and safety management.

Description

Technical Field

[0001] This invention belongs to the field of building engineering testing technology, specifically relating to a method and system for measuring water seepage in building exterior walls. Background Technology

[0002] As a crucial protective layer against the external environment, the durability of building exterior walls directly impacts the safety and lifespan of a building. However, under long-term exposure to environmental factors such as rain, humidity, and temperature fluctuations, exterior walls are highly susceptible to water seepage. Existing methods for detecting exterior wall seepage mainly rely on manual inspections or single-point humidity sampling. These methods suffer from limitations such as limited coverage, discontinuous data, and difficulty in reflecting the dynamic process of seepage diffusion in real time. Furthermore, some methods can only provide the local location of seepage, failing to quantify the depth of penetration or generate risk classification results. This leads to delayed building maintenance strategies, increasing structural deterioration and safety hazards.

[0003] With the development of building intelligence and sensing technology, how to utilize multi-point sensor data and systematic modeling and analysis methods to achieve full-process monitoring, dynamic trend prediction, and risk level assessment based on quantitative indicators for external wall seepage has become an urgent technical problem to be solved in the field of building structural safety. Therefore, this paper proposes a method and system for measuring external wall seepage that integrates data acquisition, diffusion modeling, in-depth prediction, and risk assessment, which has significant engineering application value. Summary of the Invention

[0004] To achieve the above-mentioned objectives, the present invention provides the following technical solution: a method for measuring water seepage in the exterior walls of buildings, comprising the following steps:

[0005] Step S1: Deploy a humidity sensor array at preset monitoring points on the exterior wall surface and internal structure of the building to collect raw humidity data at different spatial locations and times in real time, and transmit the data to the central processing unit; in the central processing unit, perform anomaly detection, missing data correction and noise reduction on the raw data to obtain a complete and reliable preprocessed dataset.

[0006] Step S2: Input the preprocessed dataset into the diffusion modeling module, and use time series analysis and spatial distribution estimation methods to fit and interpolate the dynamic process of the change of humidity of the exterior wall with time and space, generate a seepage diffusion feature matrix, and extract a set of key diffusion parameters including seepage rate, seepage hysteresis time and spatial differences from it.

[0007] Step S3: Input the set of key diffusion parameters into the infiltration depth estimation model, calculate the predicted value of the infiltration depth of the external wall based on nonlinear regression, and construct the infiltration distribution curve in the monitoring area according to the prediction results to reflect the water infiltration situation at different locations and times.

[0008] Step S4: Based on the seepage distribution curve, call the dynamic risk assessment module to compare the predicted seepage depth of the exterior wall with the building safety threshold, and combine the seepage rate and spatial differences to finally output the seepage risk level index, and obtain the seepage detection and risk assessment results of the building exterior wall.

[0009] Preferably, step S1 further includes:

[0010] A distributed humidity sensor array is deployed on the surface and internal structural layer of the building's exterior wall. Raw humidity data is continuously collected at different locations and times through each monitoring point, forming a raw humidity dataset. Since sensor signal fluctuations, data loss, and outliers caused by sudden interference often occur during exterior wall monitoring, the raw humidity dataset needs to be systematically preprocessed in the central processing unit. The preprocessing process includes repairing missing data, removing outliers, and smoothing and reducing noise. Specifically, the neighborhood information of the collection points is corrected and compensated to ensure data integrity. Sudden changes are statistically analyzed to remove data points that do not conform to the overall change pattern. Repeated sampling and smoothing algorithms are used to reduce the instability caused by instantaneous interference. Finally, a preprocessed dataset that can comprehensively reflect the humidity change status of the building's exterior wall is obtained.

[0011] Preferably, step S2 further includes:

[0012] The processed humidity dataset is input into the diffusion modeling module. Time series modeling methods are used to fit the humidity trend over time. Simultaneously, spatial interpolation methods are combined to estimate humidity in areas without sensors, generating a humidity distribution map covering the entire monitoring range. During this process, the diffusion modeling module comprehensively considers spatial relationships and temporal evolution patterns, gradually forming a diffusion feature matrix that describes the external wall seepage process. This matrix not only provides the overall humidity distribution of the external wall but also extracts representative diffusion feature parameters during the seepage process. These parameters include the seepage diffusion rate, the delayed effect of humidity at different levels, and the degree of difference between different areas. The extraction of these diffusion feature parameters provides key indicators for subsequent seepage depth prediction and enhances the model's explanatory power and adaptability to complex seepage behaviors.

[0013] Preferably, step S3 further includes:

[0014] The key diffusion parameters obtained in step S2 are input into the infiltration depth estimation model. A multivariate prediction relationship is established using a nonlinear regression method to obtain the predicted value of the infiltration depth of the exterior wall. In this prediction process, the model not only considers the influence of seepage velocity and lag time on the depth, but also takes into account the degree of spatial distribution differences to ensure that the results fit the actual situation. Subsequently, based on the predicted infiltration depth data, a complete infiltration distribution curve is constructed at different monitoring points on the exterior wall. The infiltration distribution curve can intuitively reflect the infiltration expansion with time and location, showing the dynamic process of water gradually infiltrating the surface and interior of the wall. Through the infiltration distribution curve, the propagation trend of infiltration in the exterior wall can be clearly identified, providing an intuitive reference for building maintenance and repair.

[0015] Preferably, step S4 further includes:

[0016] The generated seepage distribution curve is compared with the building structure safety threshold database. The dynamic risk assessment module comprehensively analyzes the differences in seepage depth, diffusion rate and spatial distribution to generate a building exterior wall seepage risk level index. The building exterior wall seepage risk level index not only considers the comparison between seepage depth and safety limit, but also integrates the changes in diffusion rate and the stability of humidity differences between different areas, thus obtaining a comprehensive risk assessment result.

[0017] Based on the assessment results, the monitoring areas of building exterior walls can be divided into three categories: low risk, medium risk, and high risk, and corresponding detection conclusions can be output. Low-risk areas indicate that water seepage has little impact on the building structure and can continue to be monitored. Medium-risk areas suggest the need to take preventive measures, such as reinforcement and coating repair. High-risk areas require immediate intervention and maintenance to prevent water seepage from further damaging the safety of the exterior wall structure. This classification mechanism realizes a closed loop of the entire process from data modeling to risk assessment, so that the detection of exterior wall seepage is not only limited to the numerical analysis level, but can also be implemented in specific risk prevention and control and engineering decision-making.

[0018] The present invention also provides a building exterior wall seepage measurement system, comprising the following modules:

[0019] The data acquisition and preprocessing module is used to deploy humidity sensor arrays on the exterior wall surface and internal structural layer of the building to collect raw humidity data at three-dimensional coordinates and different time points, and form a complete preprocessed dataset through outlier detection, missing value correction and noise reduction.

[0020] The diffusion modeling and feature extraction module is used to perform time series analysis and spatial interpolation estimation based on the preprocessed dataset, generate a humidity distribution matrix covering the entire area, and extract the infiltration rate, lag time, and spatial variance.

[0021] The permeability estimation and risk assessment module is used to calculate the predicted permeability depth of the building exterior wall based on the permeation rate, lag time, and spatial variance, generate a permeation distribution curve, compare the prediction results with the building safety threshold database, and finally output the permeation risk level and exterior wall safety assessment conclusion.

[0022] The data acquisition and preprocessing module specifically includes the following units:

[0023] The distributed humidity sensing unit is used to deploy monitoring points on the surface and internal structural layers of the exterior wall to achieve real-time acquisition of three-dimensional spatial coordinates and humidity values ​​at different times. The distributed humidity sensing unit supports multi-point parallel sampling and can maintain high sensitivity response when the ambient humidity fluctuates rapidly, thereby ensuring that effective monitoring signals can be obtained in the early stage of water seepage. At the same time, the unit has a self-test function, which can identify and report sampling points that fail or have abnormal readings, ensuring the long-term stability of the monitoring network.

[0024] The data correction unit is used to preprocess the raw humidity data collected by the distributed humidity sensing unit, including missing value completion, outlier removal, and noise reduction. Missing value completion is achieved through a weighted estimation method based on neighborhood information, which can maintain data continuity when some sensors temporarily fail. Outlier removal uses statistical methods to identify extreme values ​​that are far from the distribution pattern, thereby avoiding their interference with the overall trend. Noise reduction is performed through multiple repeated sampling and smoothing algorithms to eliminate invalid fluctuation signals introduced by electromagnetic interference and instantaneous environmental fluctuations.

[0025] The central processing unit is used to collect and standardize the corrected humidity data, forming a complete preprocessed dataset that can be used for calculation. This unit supports batch uploading and real-time synchronization of data, ensuring that remote servers and local hosts can obtain consistent data input under different operating conditions. Through standardization processing, data from different sensor models and sampling frequencies can be integrated under a unified coordinate and time reference, providing reliable input for subsequent modeling and analysis.

[0026] The diffusion modeling and feature extraction module specifically includes the following units:

[0027] The time series modeling unit is used to fit and predict the preprocessed humidity data in the time dimension, forming a trend curve of humidity change over time. This unit can capture short-term fluctuation patterns and long-term diffusion trends, thereby revealing the evolution of seepage at different stages. Through time series modeling, the future direction of humidity change can be inferred, and possible peak seepage times can be identified, providing an early warning basis for subsequent risk assessment.

[0028] The spatial interpolation unit is used to estimate humidity values ​​in areas without sensors, thereby generating a continuous humidity distribution map covering the entire monitoring area. This unit combines the numerical differences and spatial relationships of neighboring sensor points to infer the humidity situation at unsampled points, ensuring that the entire exterior wall area is covered. The spatial interpolation results not only reflect the humidity distribution on the surface but also reveal the spatial gradient of penetration depth in the vertical direction, ensuring the three-dimensional integrity of the modeling results.

[0029] The feature parameter extraction unit is used to extract key features describing water seepage behavior from the generated humidity distribution matrix, including diffusion rate, time delay and spatial variability. Diffusion rate reflects the conduction efficiency of water seepage in the exterior wall material, time delay reflects the time difference for water seepage to reach saturation from the surface to different depths, and spatial variability is used to measure the uniformity of water seepage at different monitoring locations.

[0030] The penetration estimation and risk assessment module specifically includes the following units:

[0031] The infiltration depth prediction unit is used to calculate the predicted infiltration depth of the exterior wall at different locations and time points based on the key feature parameters output by the diffusion modeling module. Through multi-dimensional parameter fitting, this unit can still provide stable and reasonable prediction results even in the presence of environmental noise and material heterogeneity. The predicted depth values ​​are constructed as a continuous curve throughout the monitoring area, which intuitively shows the spatial distribution trend and evolution of infiltration over time.

[0032] The safety threshold comparison unit is used to compare the predicted infiltration depth with the allowable value in the building safety code. It also combines the diffusion rate and spatial difference to form a comprehensive risk index. This unit can not only determine whether the infiltration exceeds the safety standard, but also assess the local risks it may cause. Through comprehensive comparison, it can provide graded early warning for building operation and maintenance personnel.

[0033] The risk output unit is used to classify the external wall monitoring area into low-risk, medium-risk, and high-risk levels based on comprehensive risk indicators, and generate corresponding risk assessment results. Low-risk areas indicate slight signs of water seepage and no significant threat to the structure in the short term. Medium-risk areas indicate potential water seepage risks in local areas, requiring key inspections. High-risk areas mean that the water seepage trend is significant, which has a substantial impact on the building's durability and safety, requiring repair and reinforcement measures. The risk output unit also supports the generation of intuitive graphical and text reports, so that decision-makers can quickly grasp the overall situation and formulate corresponding disposal measures.

[0034] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0035] This invention enables comprehensive monitoring of water seepage in building exterior walls through dynamic acquisition and preprocessing of multi-source humidity data. It effectively avoids the problems of limited monitoring range and delayed results of traditional detection methods, and improves the accuracy and real-time performance of the detection results.

[0036] This invention establishes an external wall seepage diffusion model and predicts depth, enabling quantitative analysis of the seepage process and outputting the seepage depth and diffusion range. This provides a clear technical basis for external wall repair and reinforcement, significantly improving the scientific nature and accuracy of seepage detection.

[0037] Based on a seepage risk level determination mechanism, this invention converts the test results into low-risk, medium-risk, and high-risk levels, providing building managers with intuitive decision-making references, promoting the rational allocation of maintenance resources, and further enhancing the intelligence and efficiency of building exterior wall waterproofing management. Attached Figure Description

[0038] Figure 1 A flowchart illustrating the method steps provided in this application;

[0039] Figure 2 A schematic diagram of the system modules provided in this application. Detailed Implementation

[0040] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0041] refer to Figure 1 This invention provides a method for measuring water seepage in the exterior walls of buildings, comprising the following steps:

[0042] Step 1: Deploy a humidity sensor array at pre-set monitoring points on the exterior and interior surfaces of the building, and collect real-time data on the spatial coordinates of the exterior walls. With different time points Raw humidity data The raw data is then transmitted to the central processing unit, where outlier detection, data loss correction, and noise reduction are performed to generate a cleaned preprocessed dataset. ;

[0043] In step one, distributed capacitive humidity sensors are deployed at measurement points on the exterior wall surface and internal structural layers to collect the three-dimensional coordinates of the exterior wall. and different time points The humidity data below constitutes the raw humidity dataset. The original humidity dataset During the data acquisition process, missing values, outliers, and noise signals exist. Therefore, data preprocessing is required in the central processing unit. The preprocessing includes:

[0044] Missing values ​​are corrected using a neighborhood weighting method, employing the following interpolation formula:

[0045] ;

[0046] in, This is the corrected humidity value. These are the weighting coefficients calculated based on Euclidean distance. The humidity value is the value of a nearby point;

[0047] Instantaneous noise is reduced by repeated sampling and mean smoothing.

[0048] Outliers were removed using box plot statistical methods.

[0049] Finally, a complete and accurate preprocessed dataset is obtained. .

[0050] Step 2: Process the preprocessed dataset The input diffusion modeling module uses time series analysis and spatial distribution estimation methods to fit and interpolate the dynamic process of external wall humidity changes over time and space, obtaining the seepage diffusion characteristic matrix. And extract a set of key diffusion parameter variables, including seepage rate, hysteresis time and spatial variance. ;

[0051] In step two, the preprocessed dataset obtained in the previous step is... Input the diffusion modeling module and use the autoregressive moving average model to fit the humidity change trend to obtain the predicted curve of humidity change over time;

[0052] Simultaneously, spatial interpolation methods are used to estimate humidity values ​​at monitoring points without sensor deployment, forming a humidity distribution covering the entire monitoring area and generating a seepage diffusion characteristic matrix. The spatial interpolation formula is as follows:

[0053] ;

[0054] in, To estimate humidity values, The weighting coefficients are calculated from the covariance function and satisfy the following conditions: , The corrected humidity value obtained in step S1;

[0055] Finally, the seepage diffusion characteristic matrix was obtained. :

[0056] ;

[0057] in, This is the seepage diffusion characteristic matrix. , The coordinates of the seepage location are: For depth, The time point of water seepage. To preprocess the dataset, , Let be the weighting coefficient, satisfying ;

[0058] Based on the seepage diffusion feature matrix Extract the set of key diffusion parameter variables in the process of water seepage and diffusion in external walls. ,in, For the seepage rate, by comparison The difference at consecutive time points is obtained. As the lag time, through analysis At different depths The time difference in reaching the peak humidity level is obtained. For spatial variance, through Different at the same point in time The degree of difference in humidity distribution was obtained.

[0059] Step 3: Set up the key diffusion parameter variables Input the penetration depth estimation model, and obtain the predicted value of the external wall penetration depth through nonlinear regression calculation. Based on this predicted value, a seepage distribution curve was constructed in the external wall monitoring area. This is to reflect the water infiltration at different locations at different times;

[0060] In step three, the set of key diffusion parameter variables is... Input the penetration depth estimation model, which is a multivariate prediction model based on nonlinear regression, to calculate the predicted value of the penetration depth of the external wall. The specific formula is as follows:

[0061] ;

[0062] in, , , The fitting parameters are derived from training samples of historical building seepage experiments;

[0063] Based on the predicted infiltration depth of the external wall, continuous depth values ​​were calculated at different monitoring points, and a seepage distribution curve was generated through curve fitting. This is to reflect the overall trend of water seepage spreading within the exterior wall area.

[0064] Step 4: Based on the aforementioned seepage distribution curve The dynamic risk assessment module is invoked to determine the predicted depth of external wall penetration. The water seepage risk level index is output by comparing it with the building structure safety threshold and combining the seepage rate and spatial variance. The final water seepage detection and risk assessment results for the building's exterior walls were obtained.

[0065] In step four, the seepage distribution curve is... The data was compared with a building safety threshold database and combined with predicted external wall penetration depth values. seepage rate and spatial variance A dynamic risk assessment algorithm is used to generate a seepage risk level index. The dynamic risk assessment algorithm adopts a weighted threshold function model, and the calculation formula is as follows:

[0066] ;

[0067] in, The maximum permissible penetration depth threshold is derived from building safety codes. The critical seepage rate threshold is derived from experimental standard results. The spatial reference variance is derived from historical monitoring data. , , Let be the weight coefficient, and satisfy... ;

[0068] Ultimately, the seepage risk level index ,when At that time, the exterior wall area was classified as low-risk. At that time, the exterior wall area was classified as medium risk. At that time, the exterior wall area was classified as high-risk, and the final water seepage detection and risk assessment results were output.

[0069] refer to Figure 2 This invention provides a building exterior wall seepage measurement system, comprising the following modules:

[0070] 6. A building exterior wall seepage measurement system, characterized in that it comprises the following modules:

[0071] The data acquisition and preprocessing module is used to deploy humidity sensor arrays on the exterior wall surface and internal structural layer of the building to collect raw humidity data at three-dimensional coordinates and different time points, and form a complete preprocessed dataset through outlier detection, missing value correction and noise reduction.

[0072] In the data acquisition and preprocessing module, high-precision data acquisition and transmission are achieved through distributed humidity sensing units pre-deployed on the building's exterior wall surface and internal structural layers. These sensing units are distributed in a grid pattern at key locations on the exterior wall, including areas prone to water seepage, window frames, expansion joints, and insulation layer interfaces. Sensors are also embedded within the wall at different depths to simultaneously acquire humidity changes at different times in a three-dimensional coordinate system. Since humidity values ​​may fluctuate drastically due to environmental factors such as rainfall, temperature, and wind direction, the sensors need to possess high sensitivity and rapid response characteristics to ensure early detection of water seepage signals. Furthermore, the sensor units are equipped with self-checking and fault-tolerant functions, automatically identifying abnormal sensor states during acquisition, such as sampling values ​​exceeding reasonable physical ranges or prolonged periods of no response, thus preventing erroneous data from interfering with overall trend analysis.

[0073] During data transmission and aggregation, the raw humidity data first enters the data correction unit, which is responsible for multi-level preprocessing of the raw data. For missing data caused by temporary sensor failure, the correction unit performs weighted estimation to complete the data based on sensor point information in the nearby area, thereby maintaining the continuity and integrity of the data. For abnormal values ​​caused by environmental disturbances, the correction unit identifies and removes them using statistical methods to ensure the rationality of the dataset. For high-frequency noise or sudden fluctuations in the signal, the correction unit uses a combination of repeated sampling and smoothing to reduce noise and remove the influence of invalid fluctuations. Finally, the corrected data is uniformly aggregated to the central processing unit, where it completes standardization processing and storage, ensuring that data collected by different types of sensors can be integrated under a unified time and space reference, thereby forming a complete preprocessed dataset that can be used for subsequent analysis.

[0074] The diffusion modeling and feature extraction module is used to perform time series analysis and spatial interpolation estimation based on the preprocessed dataset, generate a humidity distribution matrix covering the entire area, and extract the infiltration rate, lag time, and spatial variance.

[0075] In the diffusion modeling and feature extraction module, the main purpose is to perform dynamic modeling and spatial distribution analysis on the preprocessed humidity data. First, the time series modeling unit performs time dimension fitting and prediction on the humidity data collected from different locations. This unit adopts a multi-segment fitting method to separate the short-term humidity fluctuations and long-term trends into separate models, which can accurately depict the evolution of seepage at different stages. Through this processing, not only can the overall change of humidity values ​​over time be revealed, but also the future direction of humidity development can be predicted, and the possible peak moments of seepage can be identified, providing early warning for building maintenance.

[0076] Secondly, the spatial interpolation unit estimates the humidity in areas of the wall where no sensors are installed, generating a three-dimensional humidity distribution matrix covering the entire monitoring area. This unit calculates the humidity value of unsampled points by combining the differences in values ​​of neighboring sensor points with their spatial position, thereby achieving spatial continuity of the data. When outputting the results, spatial interpolation can not only show the humidity distribution on the exterior wall surface, but also reveal the gradient of the change in penetration depth in the vertical direction, fully reflecting the diffusion path and range of seepage in space.

[0077] Finally, the feature parameter extraction unit extracts key feature indicators from the humidity distribution matrix, including water diffusion rate, time delay, and spatial variability. The diffusion rate measures the conduction efficiency of water in the exterior wall material, the time delay reflects the time difference required for water to travel from the surface to different depths, and the spatial variability evaluates the uniformity of water in different areas. By extracting and quantifying these feature parameters, the dynamic process and potential risks of water seepage in the exterior wall can be more accurately reflected, providing necessary input data for predicting the depth of seepage and assessing the risk level.

[0078] The permeability estimation and risk assessment module is used to calculate the predicted permeability depth of the building exterior wall based on the permeation rate, lag time, and spatial variance, generate a permeation distribution curve, compare the prediction results with the building safety threshold database, and finally output the permeation risk level and exterior wall safety assessment conclusion.

[0079] In the permeability estimation and risk assessment module, the permeability depth prediction unit first calculates the predicted permeability depth at different locations and time points based on the diffusion rate, time delay, and spatial variability output by the diffusion modeling and feature extraction module. This prediction not only considers the impact of environmental noise but also takes into account the heterogeneity of the wall material, thus generating stable and reliable prediction results. The evolution of permeability over time is then visually displayed through a spatially continuous curve.

[0080] Subsequently, the safety threshold comparison unit compares the predicted penetration depth value with the standard threshold in the building safety code. At the same time, it combines the diffusion rate and spatial difference to form a comprehensive risk index, which is used to measure whether the water seepage of the external wall has exceeded the allowable range and the degree of potential risk. Through this comparison, the system can quantitatively determine the water seepage hazard, avoiding the shortcomings of subjective judgment based solely on experience.

[0081] Finally, based on the results of the comprehensive risk indicators, the risk output unit divides the monitored area into low-risk, medium-risk, and high-risk levels, and outputs corresponding risk assessment conclusions. Low-risk areas indicate slight signs of water seepage with limited impact on wall safety; medium-risk areas suggest potential local water seepage hazards that require regular re-inspection; and high-risk areas indicate a significant water seepage trend that threatens the durability of the building structure and requires immediate repair measures. The risk output unit can not only generate graded conclusions but also output visualized 3D graphics and text reports to help building managers quickly grasp the overall risk status and formulate corresponding maintenance strategies.

[0082] It should be noted that, unless otherwise specified, the embodiments and features and technical solutions in the present invention can be combined with each other.

[0083] Obviously, the embodiments described above are merely some embodiments of the present invention, not all embodiments. The accompanying drawings show preferred embodiments of the present invention, but do not limit the patent scope of the present invention. The present invention can be implemented in many different forms; rather, these embodiments are provided to provide a more thorough and complete understanding of the disclosure of the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing specific embodiments, or make equivalent substitutions for some of the technical features. Any equivalent structures made using the content of this specification and drawings, directly or indirectly applied to other related technical fields, are similarly within the patent protection scope of this invention.

Claims

1. A method of measuring water penetration of an architectural exterior wall of a building, characterized by, The method comprises the following steps: Step S1, arranging a humidity sensor array at the preset monitoring points of the surface of the building outer wall and the internal structure, collecting real-time humidity original data at different spatial positions and different time points, and transmitting the data to a central processing unit, wherein the original data is subjected to abnormal point detection, missing data correction and noise reduction in the central processing unit to obtain a complete and reliable pretreatment data set; Step S2, inputting the pretreatment data set into a diffusion modeling module, using time series analysis and spatial distribution estimation method to fit and interpolate the dynamic process of the outer wall humidity change with time and space, generating a water seepage diffusion feature matrix, and extracting a key diffusion parameter set including water seepage rate, penetration lag time and spatial variance from the matrix, wherein the water seepage rate reflects the speed of water seepage diffusion, the penetration lag time reflects the delay effect of humidity at different levels, and the spatial variance reflects the difference degree of humidity between different regions; Step S3, inputting the key diffusion parameter set into a penetration depth estimation model, calculating a predicted value of the outer wall penetration depth based on a nonlinear regression method, and constructing a water seepage distribution curve in the monitoring area according to the predicted value, wherein the water seepage distribution curve shows the dynamic process of water seepage in the surface layer and the internal structure of the wall, so as to reflect the water seepage situation at different positions and different times; Step S4, based on the water seepage distribution curve, calling a dynamic risk judgment module, comparing the predicted value of the outer wall penetration depth with a building safety threshold, and combining the water seepage rate and the spatial variance, finally outputting a water seepage risk grade index, and obtaining the water seepage detection and risk evaluation result of the building outer wall.

2. The method for measuring water penetration of an exterior wall of a building according to claim 1, wherein The step S1 further comprises: A distributed humidity sensor array is arranged on the surface of the building outer wall and the internal structure layer, and the humidity original data set is formed by continuously collecting humidity original data at different positions and different time points through each monitoring point. Since there are often abnormal values caused by sensor signal fluctuation, data loss and sudden interference in the process of monitoring the outer wall, the humidity original data set needs to be systematically pretreated in the central processing unit. The pretreatment process includes repairing missing data, removing abnormal data and smoothing noise reduction. Specifically, the neighborhood information of the collection point is corrected and compensated to ensure the integrity of the data, the data points that do not conform to the overall change rule are removed through statistical discrimination of the mutation signal, and the instability caused by the repeated sampling and smoothing algorithm is reduced, and finally the pretreatment data set which can fully reflect the humidity change state of the building outer wall is obtained.

3. The method for measuring water penetration of an exterior wall of a building according to claim 1, wherein The step S2 further comprises: The processed humidity dataset is input into the diffusion modeling module, which uses time series modeling methods to fit the trend of humidity change over time, and combines spatial interpolation methods to estimate the humidity of areas without sensors, thereby generating a humidity distribution map covering the entire monitoring range. In this process, the diffusion modeling module can consider spatial location relationships and time evolution laws to gradually form a water seepage diffusion feature matrix that describes the water seepage process of the external wall. Through the water seepage diffusion feature matrix, not only the overall humidity distribution of the external wall can be obtained, but also representative diffusion characteristic parameters in the water seepage process can be extracted. The extraction of diffusion characteristic parameters provides key indicators for subsequent penetration depth prediction and enhances the model's explanatory power and adaptability to complex water seepage behaviors.

4. The method for measuring water penetration of an exterior wall of a building according to claim 1, wherein The step S3 further comprises: The key diffusion parameters obtained in step S2 are input into the penetration depth estimation model, and a multivariate prediction relationship is established using nonlinear regression methods to obtain the predicted value of the external wall penetration depth. In this prediction process, the model not only considers the influence of seepage speed and lag time on depth, but also combines spatial variance to ensure the fitting degree of the results to the actual situation. Subsequently, based on the predicted penetration depth data, a complete water seepage distribution curve is constructed at different monitoring points of the external wall. The water seepage distribution curve can intuitively reflect the seepage expansion with time and position changes, and show the dynamic process of water penetration in the surface and internal layers of the wall. Through the water seepage distribution curve, the propagation trend of water seepage in the external wall can be clearly identified, providing intuitive reference for building maintenance and repair.

5. The method for measuring water penetration of an exterior wall of a building according to claim 1, wherein The step S4 further comprises: The dynamic risk judgment module comprehensively analyzes the penetration depth, diffusion speed, and spatial distribution differences to generate an external wall water seepage risk level index. The external wall water seepage risk level index not only considers the comparison between the penetration depth and the safety limit, but also integrates the changes in diffusion speed and the stability of humidity differences between different regions, thereby obtaining a comprehensive risk judgment result. According to the evaluation results, the external wall monitoring area of the building can be divided into low-risk, medium-risk, and high-risk categories, and the corresponding detection conclusions are output. The low-risk area indicates that the water seepage has little impact on the building structure and can continue to be monitored. The medium-risk area suggests that preventive measures need to be taken, and the high-risk area requires immediate intervention and maintenance to avoid further damage to the safety of the external wall structure. This grading mechanism realizes a full-process closed loop from data modeling to risk assessment, enabling external wall water seepage detection not only to stay at the numerical analysis level, but also to be implemented in specific risk prevention and engineering decision-making.

Images