Wall surface falling risk assessment method and device, equipment and storage medium

Abstract

The invention discloses a wall surface falling risk assessment method, device and equipment and a storage medium, and relates to the technical field of building safety assessment, and the method comprises the steps: calculating a wall surface initial resistance value based on outer wall hyperspectral image data and a regression prediction model; calculating wall surface structure resistance according to the wall surface initial resistance value and a reduction coefficient corresponding to the wall surface initial resistance value, wherein the reduction coefficient is used for representing the inherent defect of the outer wall; simulating a structural load borne by the wall surface structure through a finite element agent model based on machine learning; and based on the structure load and the wall surface structure resistance, the wall surface falling risk probability is calculated through a Monte Carlo numerical simulation method by applying the structure reliability theory. The hyperspectral image can comprehensively capture the defect characteristics of the outer wall, and the initial resistance value is quantified by combining the regression model to supplement the traditional detection blind area. The reduction coefficient is used for associating inherent defects, the finite element agent model dynamically predicts the load to quantify the dynamic environment influence, and the comprehensiveness of wall falling risk identification is improved.

Description

Technical Field

[0001] The present application relates to the technical field of building safety assessment, and in particular to a wall fall risk assessment method, device, equipment and storage medium. Background Art

[0002] With the advancement of urbanization, a large number of existing buildings have entered the aging stage, and the falling of exterior wall tiles has become a hidden danger threatening public safety.

[0003] However, traditional manual visual inspection and tapping inspection methods have problems such as low efficiency and limited coverage. It is difficult to fully identify potential defects such as hollows and cracks, which makes it difficult to detect the risk of falling off in a timely manner.

[0004] Therefore, how to achieve comprehensive detection of the risk of exterior wall facing tiles falling off is a problem that urgently needs to be solved. Summary of the Invention

[0005] The main purpose of this application is to provide a wall fall risk assessment method, device, equipment and storage medium, aiming to solve the technical problem of incomplete detection of traditional external wall hidden dangers.

[0006] To achieve the above objectives, this application proposes a wall fall risk assessment method, which includes:

[0007] Calculate the initial resistance value of the wall based on the hyperspectral image data of the exterior wall and the regression prediction model;

[0008] Calculating the wall structure resistance based on the initial wall resistance value and a reduction coefficient corresponding to the initial wall resistance value, wherein the reduction coefficient is used to represent inherent defects of the exterior wall;

[0009] Simulate the structural loads borne by the wall structure through a finite element proxy model based on machine learning;

[0010] Based on the structural load and the wall structural resistance, the structural reliability theory is used to calculate the wall falling risk probability through the Monte Carlo numerical simulation method.

[0011] In one embodiment, the step of calculating the initial resistance value of the wall based on the exterior wall hyperspectral image data and the regression prediction model includes:

[0012] Acquire spectral characteristic parameters based on exterior wall hyperspectral image data;

[0013] Using machine learning and deep learning algorithms, the wall bond strength data and the spectral characteristic parameters are input into the regression prediction model to obtain the initial resistance value of the wall.

[0014] In one embodiment, the spectral characteristic parameters include a first spectral characteristic parameter and a second spectral characteristic parameter, and the step of acquiring the spectral characteristic parameters based on the exterior wall hyperspectral image data includes:

[0015] Collect hyperspectral images of the joints of exterior wall facing tiles at different aging levels;

[0016] Extracting a first spectral characteristic parameter of the bonding layer between the facing brick and the base layer from the hyperspectral image;

[0017] Real-time acquisition of hyperspectral images of on-site exterior wall facing tiles for feature evaluation to obtain second spectral feature parameters.

[0018] In one embodiment, the wall bond strength data includes a real bond strength value and a predicted bond strength value. The step of using a machine learning and deep learning algorithm to input the wall bond strength data and the spectral characteristic parameters into a regression prediction model to obtain an initial wall resistance value includes:

[0019] The true value of the bonding strength is measured by an on-site pull-out test, and a mapping relationship between the first spectral characteristic parameter and the true value of the bonding strength is established;

[0020] Based on the mapping relationship, a regression prediction model is trained through machine learning and deep learning algorithms;

[0021] The second spectral characteristic parameter is input into the regression prediction model to output a bonding strength prediction value, and the bonding strength prediction value is defined as the initial resistance value of the wall.

[0022] In one embodiment, the step of calculating the wall structure resistance based on the initial wall resistance value and the reduction coefficient corresponding to the initial wall resistance value includes:

[0023] Obtain the reduction factor corresponding to the initial resistance value of the wall according to the exterior wall inspection report;

[0024] The wall structure resistance is calculated based on the initial wall resistance value and the multiple reduction coefficients.

[0025] In one embodiment, the step of simulating the structural load borne by the wall structure using a finite element proxy model based on machine learning includes:

[0026] Establish a finite element calculation model based on the key design variables of exterior wall facing tiles;

[0027] Inputting the stress conditions of the facing bricks under different working conditions into the finite element calculation model to generate a simulation result data set;

[0028] Based on the simulation result data set, a finite element proxy model is constructed by a machine learning algorithm, wherein the finite element proxy model is used to accelerate the simulation calculation of the structural load;

[0029] The exterior wall service data is input into the finite element proxy model to obtain the structural load borne by the wall structure.

[0030] In one embodiment, the step of calculating the wall fall risk probability based on the structural load and the wall structural resistance using a Monte Carlo numerical simulation method using structural reliability theory includes:

[0031] Use structural reliability theory to establish structural limit state equations;

[0032] Based on the structural limit state equation, sampling the wall structure resistance and the structural load is performed using the Monte Carlo numerical simulation method to determine a probability distribution model;

[0033] Calculating a reliability index based on the probability distribution model;

[0034] The reliability index is converted into a falling probability, and the wall falling risk is evaluated according to the falling probability.

[0035] In addition, to achieve the above-mentioned purpose, the present application also proposes a wall fall risk assessment device, which includes:

[0036] The initial resistance calculation module is used to calculate the initial resistance value of the wall based on the exterior wall hyperspectral image data and regression prediction model;

[0037] a structural resistance calculation module, configured to calculate the wall structural resistance based on the initial wall resistance value and a reduction coefficient corresponding to the initial wall resistance value, wherein the reduction coefficient is used to represent inherent defects of the exterior wall;

[0038] Structural load calculation module, used to simulate the structural loads borne by wall structures through a finite element proxy model based on machine learning;

[0039] The falling risk assessment module is used to calculate the wall falling risk probability based on the structural load and the wall structural resistance, using structural reliability theory and a Monte Carlo numerical simulation method.

[0040] In addition, to achieve the above-mentioned purpose, the present application also proposes a wall fall risk assessment device, which includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the computer program is configured to implement the steps of the wall fall risk assessment method as described above.

[0041] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the wall fall risk assessment method as described above are implemented.

[0042] One or more technical solutions proposed in this application have at least the following technical effects:

[0043] The initial resistance of the wall is calculated using hyperspectral image data of the exterior wall and a regression prediction model. The structural resistance of the wall is calculated based on the initial resistance and a corresponding reduction factor, which accounts for inherent defects in the exterior wall. A machine learning-based finite element proxy model is used to simulate the structural loads borne by the wall structure. Based on the structural loads and the structural resistance of the wall, structural reliability theory is applied to calculate the probability of wall collapse risk using Monte Carlo numerical simulation. Hyperspectral imagery can more comprehensively capture the complex defect characteristics of the exterior wall. Combined with the regression model, the initial resistance is quantified, addressing the blind spots of traditional inspection at the material performance level. The reduction factor is used to correlate inherent defects, and load effects are dynamically predicted based on the finite element proxy model. This overcomes the difficulty of manual inspection in quantifying dynamic environmental impacts. Risk assessment is achieved through structural reliability theory, significantly improving the comprehensiveness and reliability of collapse risk identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0045] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0046] Figure 1 This is a flow chart of the first embodiment of the wall fall risk assessment method of the present application;

[0047] Figure 2 This is a flow chart of the second embodiment of the wall fall risk assessment method of the present application;

[0048] Figure 3 This is a flow chart of the third embodiment of the wall fall risk assessment method of the present application;

[0049] Figure 4 Schematic diagram of the reasoning process of the finite element proxy model in the embodiment of the present application;

[0050] Figure 5This is a flow chart of a fourth embodiment of the wall fall risk assessment method of the present application;

[0051] Figure 6 This is a schematic diagram of the module structure of the wall fall risk assessment device according to an embodiment of the present application;

[0052] Figure 7 Schematic diagram of the device structure of the hardware operating environment involved in the wall fall risk assessment method in the embodiment of the present application.

[0053] The purpose, features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0054] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not intended to limit the present application.

[0055] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0056] With advancements in science and technology and the economy, my country's urbanization has made significant progress. Many buildings, after years or even decades of use, have developed various defects due to natural deterioration or human factors. Traditional methods for detecting exterior wall defects rely primarily on manual visual inspection and close-range percussion testing, which is not only time-consuming and labor-intensive but also prone to incomplete inspections and omissions. Currently, visible light image-based building exterior wall defect detection technology has good detection performance for surface defects such as cracks, peeling, and leaks. Infrared image-based building exterior wall defect detection technology also has excellent detection results for hidden defects such as hollowing. However, converting building facade inspection results and correlating them with indicators of exterior wall tile loss risk still relies primarily on the subjective experience of inspectors. Although numerous researchers have attempted to assess exterior wall loss risk using comprehensive evaluation methods such as fault tree analysis (FTA), analytic hierarchy process (AHP), and fuzzy comprehensive evaluation, and while these evaluation methods have demonstrated a degree of scientific and systematic effectiveness, they still have limitations in terms of objectivity.

[0057] This application provides a solution that calculates the initial resistance value of the wall based on hyperspectral image data of the exterior wall and a regression prediction model; calculates the structural resistance of the wall based on the initial resistance value of the wall and the reduction coefficient corresponding to the initial resistance value of the wall, and the reduction coefficient is used to represent the inherent defects of the exterior wall; simulates the structural load borne by the wall structure through a finite element proxy model based on machine learning; and calculates the risk probability of wall fall-off through Monte Carlo numerical simulation method using structural reliability theory based on the structural load and wall structural resistance. Hyperspectral images can more comprehensively capture the characteristics of the composite defects of the exterior wall, and combined with the regression model to quantify the initial resistance value, fill the blind spots of traditional detection from the material performance level. The reduction coefficient can be used to associate inherent defects, and the load effect can be dynamically predicted based on the finite element proxy model, which makes up for the shortcoming that manual detection is difficult to quantify the impact of dynamic environment. Risk assessment is achieved through structural reliability theory, significantly improving the comprehensiveness of fall risk identification and the reliability of assessment.

[0058] Based on this, the embodiment of the present application provides a wall falling risk assessment method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the wall fall risk assessment method of the present application.

[0059] In this embodiment, the wall falling risk assessment method includes steps S10 to S40:

[0060] Step S10: Calculate the initial resistance value of the wall based on the exterior wall hyperspectral image data and the regression prediction model.

[0061] It should be noted that the exterior wall hyperspectral image data can be acquired using hyperspectral imaging technology, a method that uses electromagnetic spectral information to detect material properties. It can analyze the physical and chemical properties of an object by recording spectral reflectance information in different bands. By acquiring continuous narrowband spectral information, hyperspectral imaging technology can accurately analyze the composition and microstructure of a material. Each pixel corresponds to a complete spectral curve, which can reflect the unique spectral characteristics of the material. The regression prediction model can be a mathematical model built based on machine learning (such as random forests or neural networks). For example, features extracted from hyperspectral data (such as key band reflectance and texture statistics) can be input, and the corresponding output is the initial resistance value of the wall. The initial resistance value of the wall can represent the theoretical load-bearing capacity (such as tensile strength and shear strength) of the facing brick and base bonding system under ideal conditions, reflecting the mechanical properties of the material itself. It is understandable that the initial resistance value of the wall here ignores actual reduction factors such as construction defects and environmental aging.

[0062] Step S20 , calculating the wall structural resistance according to the initial wall resistance value and a reduction coefficient corresponding to the initial wall resistance value, where the reduction coefficient is used to represent inherent defects of the exterior wall.

[0063] It should be noted that the reduction coefficient can represent a correction factor with a value range of 0 to 1, which can be used to quantify the degree of weakening of the resistance of the inherent defects of the exterior wall. For example, hollowing defects (insufficient bonding area) can correspond to a reduction in shear strength and tensile strength. The reduction coefficient can be calibrated through a historical disease database or experiments (such as conducting destructive tests on specimens with different hollowing rates). The wall structure resistance can be understood as the effective bearing capacity under actual working conditions. It can be understood that the wall structure resistance comprehensively considers the influence of material properties and defects.

[0064] Step S30: Simulate the structural load borne by the wall structure through a finite element proxy model based on machine learning.

[0065] It should be noted that the finite element proxy model can be understood as an alternative model built based on machine learning (such as deep neural networks, Gaussian processes), which is used to quickly predict the structural response under complex loads. Structural loads can represent the dynamic external forces borne by the exterior wall. For example, the external loads mainly include wind loads and temperature loads. Among them, the wind load can be the wind pressure distribution acting on the surface of the facing brick according to relevant specifications (such as the "Building Structure Load Code"). The temperature load can be the thermal stress generated by the facing brick due to the simulated ambient temperature changes.

[0066] Step S40 , based on the structural load and the wall structural resistance, using the structural reliability theory, and using the Monte Carlo numerical simulation method, calculates the wall falling risk probability.

[0067] It should be noted that structural reliability theory is one of the core theories in the field of engineering structure design. It aims to quantify the safety performance of structures in uncertain environments through probabilistic and statistical methods. It can use mathematical means to describe the probability of an engineering structure completing its intended function (such as safety, applicability, and durability) under the uncertainty of factors such as loads, material properties, and the environment. The Monte Carlo numerical simulation method can approximate complex probabilistic problems through random sampling. In the risk assessment of exterior wall facing brick falling off, the Monte Carlo numerical simulation method is used to simulate the probability distribution of action effects (structural loads) and structural resistance, and to estimate the risk probability of facing brick falling off.

[0068] In this embodiment, the initial resistance of the wall is calculated based on hyperspectral image data of the exterior wall and a regression prediction model. The structural resistance of the wall is calculated based on the initial resistance value and the corresponding reduction factor, which is used to represent inherent defects in the exterior wall. The structural load borne by the wall structure is simulated using a finite element proxy model based on machine learning. Based on the structural load and the structural resistance of the wall, structural reliability theory is applied to calculate the probability of wall failure risk through Monte Carlo numerical simulation. Hyperspectral images can more comprehensively capture the complex defect characteristics of the exterior wall. Combined with the regression model, the initial resistance value is quantified, supplementing the blind spots of traditional inspection at the material performance level. The reduction factor can be used to correlate inherent defects, and load effects can be dynamically predicted based on the finite element proxy model. This overcomes the shortcoming of manual inspection in quantifying dynamic environmental influences. Risk assessment is achieved through structural reliability theory, significantly improving the comprehensiveness of failure risk identification and the reliability of assessment.

[0069] Reference Figure 2 , Figure 2 This is a flow chart of the second embodiment of the wall falling risk assessment method of this application, based on the above Figure 1 The first embodiment shown is a second embodiment of the wall falling risk assessment method of the present application.

[0070] In the second embodiment, step S10 includes:

[0071] Step S101: Acquire spectral characteristic parameters based on exterior wall hyperspectral image data.

[0072] It should be noted that the spectral characteristic parameters can be quantitative indicators extracted from the hyperspectral image, which are used to characterize material properties or defects. The spectral characteristic parameters include a first spectral characteristic parameter and a second spectral characteristic parameter, wherein the first spectral characteristic parameter can be used as training data for the regression prediction model, and the second spectral characteristic parameter can be used as actual prediction data for the regression prediction model. Exemplarily, before obtaining the spectral characteristic parameters based on the exterior wall hyperspectral image data, the collected hyperspectral data can be preprocessed, including: spectral smoothing to reduce noise interference. De-envelope analysis to correct spectral background effects. Based on this, the specific spectral characteristic parameters extracted can include IOR (refractive index) and average spectral curve.

[0073] Specifically, in one embodiment, step S101 includes: collecting hyperspectral images of joints of exterior wall facing tiles with different degrees of aging; extracting first spectral characteristic parameters of the bonding layer between the facing tiles and the base layer from the hyperspectral images; and collecting hyperspectral images of on-site exterior wall facing tiles in real time for feature evaluation to obtain second spectral characteristic parameters.

[0074] For example, the first spectral characteristic parameter can be based on historical data or samples. By analyzing the spectral curves of the joint area of exterior wall facing tiles with different degrees of aging (reflecting the state of the bonding layer), parameters such as the reflectivity peak and spectral slope in a specific band can be extracted. The second spectral characteristic parameter can be real-time on-site hyperspectral data.

[0075] In step S102 , machine learning and deep learning algorithms are used to input the wall bonding strength data and spectral characteristic parameters into a regression prediction model to obtain the initial resistance value of the wall.

[0076] It should be noted that the wall bond strength data can be a mechanical performance indicator of the bond interface resistance to detachment between the facing tile and the base layer (such as concrete or mortar). Step S102 includes: measuring the actual bond strength value through an on-site pull-out test, establishing a mapping relationship between the first spectral characteristic parameter and the actual bond strength value; training a regression prediction model based on this mapping relationship using machine learning and deep learning algorithms; inputting the second spectral characteristic parameter into the regression prediction model, outputting a predicted bond strength value, and defining the predicted bond strength value as the initial resistance value of the wall.

[0077] It should be noted that the on-site pull-out test is a destructive detection method for directly measuring the bond strength between the facing bricks and the base layer. For example, a vertical pull can be applied to the facing bricks in the selected area, and the maximum pull value (unit: MPa) when they are detached can be recorded as the true value of the bond strength. The mapping relationship can represent the quantitative association between the first hyperspectral feature parameter (such as the reflectivity and texture variance of the joint area in a specific band) and the true value of the bond strength. The supervised learning model constructed based on machine learning (such as support vector regression, SVR or K-nearest neighbor regression, KNN) or deep learning (such as multi-layer perceptron regression, MLP) takes the first spectral feature parameter (laboratory or historical data) as input and outputs the predicted value of the bond strength. The regression prediction model is optimized by minimizing the mean squared error (MSE) between the predicted value and the true value of the pull-out test. The predicted value of the bond strength can be understood as the estimated value of the bond strength calculated by the regression prediction model on the second spectral feature parameter collected in real time. Among them, the calculation formula of MSE is expressed as formula (1).

[0078]

[0079] In formula (1), n is the number of samples, x i is the true value of the i-th sample, y i is the model’s prediction value for the i-th sample. The smaller the mean square error (MSE), the better the model’s prediction performance.

[0080] In this embodiment, spectral characteristic parameters are obtained based on the hyperspectral image data of the exterior wall. The non-contact measurement method provides rich samples for model training without causing damage to the wall surface. Using machine learning and deep learning algorithms, the wall bonding strength data and spectral characteristic parameters are used as input to the regression prediction model to obtain the initial resistance value of the wall surface, realizing the quantitative correlation between spectral characteristics and resistance values, avoiding subjective misjudgment, and improving the accuracy and efficiency of the evaluation.

[0081] In one embodiment, the step of calculating the wall structure resistance based on the initial wall resistance value and the reduction coefficient corresponding to the initial wall resistance value includes: obtaining the reduction coefficient corresponding to the initial wall resistance value according to the exterior wall inspection report; and calculating the wall structure resistance based on the initial wall resistance value and multiple reduction coefficients.

[0082] For example, a reduction factor can be used to adjust the calculated value of the wall structure resistance. The reduction factor is determined based on data from the exterior wall inspection report, such as the location and number of cracks detected by visible light imaging, or the hollowing rate detected by infrared thermal imaging. The reduction factor can be determined by reference to the Analytic Hierarchy Process (AHP), expert experience, or actual engineering experience. The calculation of the wall structure resistance can be specifically expressed as Formula (2).

[0083] R=R0·k1·k2·k3·k n (2)

[0084] In formula (2), R represents the structural resistance of the wall, R0 represents the initial resistance value of the wall obtained based on hyperspectral imaging technology, k1 represents the reduction coefficient corresponding to the hollowing defect, k2 represents the reduction coefficient corresponding to the crack defect, k3 represents the reduction coefficient corresponding to the existing shedding area, and k n Indicates other reduction factors.

[0085] In this embodiment, by considering multiple influencing factors and using reduction coefficients for adjustment, the actual bearing capacity of the wall can be more accurately reflected. The use of unified detection methods and calculation steps also helps promote the standardized assessment of wall structural resistance, thereby improving the comprehensiveness and reliability of falling risk identification.

[0086] Reference Figure 3 , Figure 3 This is a flow chart of the third embodiment of the wall falling risk assessment method of this application, based on the above Figure 2 The second embodiment shown is a third embodiment of the wall falling risk assessment method of the present application.

[0087] In the third embodiment, step S30 includes:

[0088] Step S301: establishing a finite element calculation model based on key design variables of exterior wall facing tiles.

[0089] It should be noted that the key design variables may be the core parameters that affect the mechanical properties of exterior wall facing tiles. For example, the key design variables may include material properties (such as elastic modulus, Poisson's ratio, tensile strength, thermal expansion coefficient), geometric parameters (such as facing tile thickness, size, bonding layer thickness, anchor spacing), boundary conditions (such as wall support method, interaction between adjacent bricks), and environmental parameters (such as temperature gradient, humidity change rate), etc. The finite element calculation model can be understood as discretizing the exterior wall facing tiles into a finite number of units and solving the mathematical model of their force response through numerical methods. For example, modeling can be performed through processes such as geometric modeling, material assignment, mesh division, boundary and load application.

[0090] Step S302: input the stress conditions of the facing bricks under different working conditions into the finite element calculation model to generate a simulation result data set.

[0091] It should be noted that the working conditions can be understood as load combinations under different external action conditions, for example, wind load conditions (applying different wind pressure distributions to simulate the maximum stress and deformation of facing tiles under high wind speeds), temperature load conditions (applying different ambient temperature differences to evaluate the stress distribution caused by thermal expansion effects), multi-physics field coupling conditions (applying different wind, humidity, and heat to evaluate the stress and displacement of the facing tile bonding layer), etc. The simulation result data set can be understood as the physical response data generated by finite element calculations. For example, the simulation result data set can include the maximum stress value (indicating the location and working conditions where the facing tiles may fail) and the maximum deformation (characterizing the degree of deformation of the exterior surface). It is understandable that all analysis results are exported as structured data (such as txt or csv format) to provide input data for the subsequent training of the proxy model.

[0092] Step S303: Based on the simulation result data set, a finite element proxy model is constructed through a machine learning algorithm. The finite element proxy model is used to accelerate the simulation calculation of the structural load.

[0093] It should be noted that the finite element proxy model uses a simplified mathematical model constructed using a machine learning algorithm to replace the original finite element model to quickly predict structural responses. For example, the finite element proxy model can be constructed using finite element software, including but not limited to COMSOL and Abaqus.

[0094] Step S304: input the exterior wall service data into the finite element proxy model to obtain the structural load borne by the wall structure.

[0095] For example, Figure 4As shown in FIG, the exterior wall service data can be the environmental and load data monitored or recorded during actual use of the exterior wall, such as dimensions, temperature environment, wind pressure data, existing defects, and material information. Through automatic calculation of the proxy model, the structural load borne by the wall structure, such as maximum stress and maximum displacement, can be obtained.

[0096] In this embodiment, the use of a finite element proxy model reduces reliance on physical prototypes or field testing, saving material costs, labor costs, and testing time. By inputting stress conditions under different working conditions, it can fully simulate the various possible stress states of facing bricks in actual use, facilitating a more accurate assessment of the structure's load-bearing capacity and stability. By introducing a finite element proxy model and machine learning algorithms, the efficiency and accuracy of load assessment for exterior wall facing brick structures are effectively improved, reducing costs and enhancing design reliability and optimization capabilities.

[0097] Reference Figure 5 , Figure 5 This is a flow chart of the fourth embodiment of the wall falling risk assessment method of this application, based on the above Figure 3 The third embodiment shown is the fourth embodiment of the wall falling risk assessment method of the present application.

[0098] In the fourth embodiment, step S40 includes:

[0099] Step S401: Establishing a structural limit state equation using structural reliability theory.

[0100] For example, the structural limit state equation can be expressed as Z=RS, which describes the structural state, wherein Z represents the wall structural state, R represents the structural resistance, and S represents the action effect.

[0101] Step S402: Based on the structural limit state equation, sampling of wall resistance and structural load is performed by Monte Carlo numerical simulation method to determine a probability distribution model.

[0102] It should be noted that the Monte Carlo numerical simulation method can approximate complex probabilistic problems through random sampling. In the risk assessment of exterior wall facing tile falling off, the Monte Carlo numerical simulation method is used to simulate the probability distribution of the action effect (structural load) and the structural resistance, and estimate the risk probability of facing tile falling off. The probability distribution model can be used to describe the randomness of structural loads and structural resistance. By dynamically comparing a large number of random samples, the probability of facing tile falling off under specific working conditions is calculated.

[0103] Step S403: Calculate the reliability index based on the probability distribution model.

[0104] It should be noted that the reliability index can be used to reflect the level of structural safety. For example, the structural state is described by Z = RS, where Z represents the wall structure state, R represents the structural resistance, and S represents the effect. When Z > 0, the structure is safe. The reliability index can be understood as an indicator of structural safety, expressed as P(Z > 0).

[0105] Step S404: convert the reliability index into a falling probability, and evaluate the wall falling risk based on the falling probability.

[0106] It can be understood that when Z<0, shedding occurs, and the shedding probability can be expressed as P(Z<0).

[0107] For example, since the service environment of the exterior wall is dynamically changing, the action effect S is greatly affected by environmental factors (such as temperature and wind pressure). To more realistically reflect the complex environment in which the exterior wall facing tiles are located, the action effect S can be randomly sampled based on the environmental characteristics of the exterior wall location (such as the temperature range and wind pressure distribution) to construct a sample set. For example, assuming that N random samplings are performed, each time a set of action effect S and structural resistance R is selected, the calculation of the shedding risk probability is expressed as formula (3).

[0108]

[0109] In formula (3), N(S>R) represents the number of samples in which the action effect S exceeds the structural resistance R in the sampling, and N is the total number of random samples.

[0110] For example, the division of risk intervals can refer to the table shown in Table 1.

[0111] Table 1

[0112]

[0113] For example, a residential complex's exterior wall needs to undergo a wall fall-off risk assessment. Hyperspectral imaging technology can be used to measure the initial bond strength resistance, R0, of 0.4 MPa. Using an infrared thermal imager, the exterior wall finish layer's hollowing rate is 15%, the existing fall-off area is 5%, and the number of cracks is 30. Existing defects affect the resistance R through a reduction factor, α, which is 0.8 (i.e., a 20% reduction in resistance). Therefore, the actual structural resistance is R = R0 × α = 0.4 × 0.8 = 0.32 MPa.

[0114] Environmental effects such as temperature changes and wind pressure follow a certain distribution (e.g., normal distribution). Assume that N = 1000 random samplings are performed. In each sampling, a value is randomly drawn from the distribution of environmental effects such as temperature and wind pressure, and the effect S is calculated through the finite element proxy model. Assume that the effect S obtained from each sampling is uniformly distributed within the range of [0.3MPa, 0.6MPa]. Through random sampling, it is assumed that in the following 1000 simulations, 370 times the effect S exceeds the actual structural resistance R = 0.32R = 0.32R = 0.32MPa. Then the current risk probability of the exterior wall facing brick falling off is formula (4):

[0115]

[0116] The final assessment was medium risk, grade C.

[0117] In this embodiment, through comparative analysis of resistance and load, combined with statistical analysis methods such as Monte Carlo, an accurate assessment of the current risk probability of falling off of exterior wall facing tiles is achieved, providing a scientific basis for the investigation of potential safety hazards in buildings and a reliable quantitative reference for the pricing of housing quality insurance.

[0118] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the wall fall risk assessment method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0119] This application also provides a wall fall risk assessment device, please refer to Figure 6 , the wall falling risk assessment device comprises:

[0120] An initial resistance calculation module 10 is used to calculate the initial resistance value of the wall based on the external wall hyperspectral image data and the regression prediction model;

[0121] a structural resistance calculation module 20 for calculating the wall structural resistance based on the initial wall resistance value and a reduction coefficient corresponding to the initial wall resistance value, wherein the reduction coefficient is used to represent inherent defects of the exterior wall;

[0122] a structural load calculation module 30 for simulating the structural load borne by the wall structure through a finite element proxy model based on machine learning;

[0123] The falling risk assessment module 40 is used to calculate the wall falling risk probability based on the structural load and the wall structural resistance by using the structural reliability theory and the Monte Carlo numerical simulation method.

[0124] The wall fall risk assessment device provided in this application, utilizing the wall fall risk assessment method described in the aforementioned embodiments, can address the technical issue of incomplete detection and investigation of traditional exterior wall hidden dangers. Compared to the prior art, the beneficial effects of the wall fall risk assessment device provided in this application are the same as those of the wall fall risk assessment method described in the aforementioned embodiments. Other technical features of the wall fall risk assessment device are the same as those disclosed in the aforementioned embodiments and are not further elaborated here.

[0125] The present application provides a wall fall risk assessment device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the wall fall risk assessment method in the above-mentioned embodiment 1.

[0126] Reference below Figure 7 , which shows a schematic structural diagram of a wall fall risk assessment device suitable for implementing an embodiment of the present application. The wall fall risk assessment device in the embodiment of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 7 The wall fall risk assessment device shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0127] like Figure 7As shown, the wall fall risk assessment device may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes based on programs stored in a read-only memory (ROM) 1002 or programs loaded from a storage device 1003 into a random access memory (RAM) 1004. RAM 1004 also stores various programs and data required for the operation of the wall fall risk assessment device. Processing device 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the wall fall risk assessment device to communicate with other devices wirelessly or by wire to exchange data. Although Figure 7 The wall fall risk assessment device is shown with various systems, but it should be understood that it is not required to implement or have all of the systems shown. More or fewer systems may be implemented or have instead.

[0128] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0129] The wall fall risk assessment device provided in this application utilizes the wall fall risk assessment method described in the aforementioned embodiment, resolving the technical issue of incomplete inspection and detection of traditional exterior wall hidden dangers. Compared to the prior art, the beneficial effects of the wall fall risk assessment device provided in this application are the same as those of the wall fall risk assessment method described in the aforementioned embodiment. Other technical features of the wall fall risk assessment device are the same as those disclosed in the aforementioned embodiment and are not further elaborated here.

[0130] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0131] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

[0132] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, a computer program) stored thereon, and the computer-readable program instructions are used to execute the wall fall risk assessment method in the above-mentioned embodiment.

[0133] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0134] The computer-readable storage medium may be included in the wall fall risk assessment device; or may exist independently without being assembled into the wall fall risk assessment device.

[0135] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the wall fall risk assessment device, the wall fall risk assessment device: calculates the initial resistance value of the wall based on the exterior wall hyperspectral image data and the regression prediction model; calculates the wall structural resistance according to the initial wall resistance value and the reduction coefficient corresponding to the initial wall resistance value, and the reduction coefficient is used to represent the inherent defects of the exterior wall; simulates the structural load borne by the wall structure through a finite element proxy model based on machine learning; and calculates the wall fall risk probability based on the structural load and the wall structural resistance, using structural reliability theory and a Monte Carlo numerical simulation method.

[0136] Computer program code for performing the operations of the present application may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0137] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0138] The modules described in the embodiments of the present application may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.

[0139] The computer-readable storage medium provided in this application stores computer-readable program instructions (i.e., a computer program) for executing the aforementioned wall fall risk assessment method. This computer-readable storage medium can address the technical issue of incomplete inspection and detection of traditional exterior wall hazard hazards. Compared to the prior art, the beneficial effects of the computer-readable storage medium provided in this application are similar to those of the wall fall risk assessment method provided in the aforementioned embodiment, and are not further elaborated here.

[0140] The above description is only part of the embodiments of the present application and does not limit the patent scope of the present application. All equivalent structural transformations made by using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A wall falling risk assessment method, characterized in that: The method comprises: Calculate the initial resistance value of the wall based on the hyperspectral image data of the exterior wall and the regression prediction model; Calculating the wall structure resistance based on the initial wall resistance value and a reduction coefficient corresponding to the initial wall resistance value, wherein the reduction coefficient is used to represent inherent defects of the exterior wall; Simulate the structural loads borne by the wall structure through a finite element proxy model based on machine learning; Based on the structural load and the wall structural resistance, the structural reliability theory is used to calculate the wall falling risk probability through the Monte Carlo numerical simulation method.

2. The method according to claim 1, wherein The step of calculating the initial resistance value of the wall surface based on the exterior wall hyperspectral image data and the regression prediction model includes: Acquire spectral characteristic parameters based on exterior wall hyperspectral image data; Using machine learning and deep learning algorithms, the wall bond strength data and the spectral characteristic parameters are input into the regression prediction model to obtain the initial resistance value of the wall.

3. The method according to claim 2, wherein The spectral characteristic parameters include a first spectral characteristic parameter and a second spectral characteristic parameter. The step of acquiring the spectral characteristic parameters based on the exterior wall hyperspectral image data includes: Collect hyperspectral images of the joints of exterior wall facing tiles at different aging levels; Extracting a first spectral characteristic parameter of the bonding layer between the facing brick and the base layer from the hyperspectral image; Real-time acquisition of hyperspectral images of on-site exterior wall facing tiles for feature evaluation to obtain second spectral feature parameters.

4. The method according to claim 3, wherein The wall surface bonding strength data includes a real bonding strength value and a predicted bonding strength value. The step of using a machine learning and deep learning algorithm to input the wall surface bonding strength data and the spectral characteristic parameters into a regression prediction model to obtain an initial wall surface resistance value includes: The true value of the bonding strength is measured by an on-site pull-out test, and a mapping relationship between the first spectral characteristic parameter and the true value of the bonding strength is established; Based on the mapping relationship, a regression prediction model is trained through machine learning and deep learning algorithms; The second spectral characteristic parameter is input into the regression prediction model to output a bonding strength prediction value, and the bonding strength prediction value is defined as the initial resistance value of the wall.

5. The method according to claim 1, wherein The step of calculating the wall structure resistance according to the initial wall resistance value and the reduction coefficient corresponding to the initial wall resistance value includes: Obtain the reduction factor corresponding to the initial resistance value of the wall according to the exterior wall inspection report; The wall structure resistance is calculated based on the initial wall resistance value and the multiple reduction coefficients.

6. The method according to claim 1, wherein The step of simulating the structural load borne by the wall structure through the finite element proxy model based on machine learning includes: Establish a finite element calculation model based on the key design variables of exterior wall facing tiles; Inputting the stress conditions of the facing bricks under different working conditions into the finite element calculation model to generate a simulation result data set; Based on the simulation result data set, a finite element proxy model is constructed by a machine learning algorithm, wherein the finite element proxy model is used to accelerate the simulation calculation of the structural load; The exterior wall service data is input into the finite element proxy model to obtain the structural load borne by the wall structure.

7. The method according to any one of claims 1 to 6, characterized in that The step of calculating the wall falling risk probability based on the structural load and the wall structural resistance by using the structural reliability theory and the Monte Carlo numerical simulation method includes: Use structural reliability theory to establish structural limit state equations; Based on the structural limit state equation, sampling the wall structure resistance and the structural load is performed using the Monte Carlo numerical simulation method to determine a probability distribution model; Calculating a reliability index based on the probability distribution model; The reliability index is converted into a falling probability, and the wall falling risk is evaluated according to the falling probability.

8. A wall falling risk assessment device, characterized in that: The wall falling risk assessment device comprises: The initial resistance calculation module is used to calculate the initial resistance value of the wall based on the exterior wall hyperspectral image data and regression prediction model; a structural resistance calculation module, configured to calculate the wall structural resistance based on the initial wall resistance value and a reduction coefficient corresponding to the initial wall resistance value, wherein the reduction coefficient is used to represent inherent defects of the exterior wall; Structural load calculation module, used to simulate the structural loads borne by wall structures through a finite element proxy model based on machine learning; The falling risk assessment module is used to calculate the wall falling risk probability based on the structural load and the wall structural resistance, using structural reliability theory and a Monte Carlo numerical simulation method.

9. A wall falling risk assessment device, characterized in that: The wall fall risk assessment device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the wall fall risk assessment method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the wall fall risk assessment method according to any one of claims 1 to 7 are implemented.

Images