A building structure health detection method based on multimodal data

Abstract

This invention provides a method for structural health monitoring of buildings based on multimodal data, belonging to the field of structural health monitoring technology. It includes: comprehensively collecting multidimensional monitoring data on vibration, fiber optic strain, acoustic emission, temperature field, and deformation of the building structure using an advanced multimodal sensor array. The method first preprocesses the collected data and performs material performance tests to establish a material parameter database. The core technology is to use Bayesian networks to calculate the correlation between multimodal monitoring data and performance test data, constructing an accurate relationship function and establishing a set of structural health state equations. Through deep fitting of historical monitoring data, a highly intelligent structural health assessment model is developed, capable of accurately calculating key indices such as damage location, temperature anomalies, deformation degree, and cumulative damage; thus solving the technical problem that existing single monitoring methods are insufficient to comprehensively and accurately assess the overall health status of structures.

Description

Technical Field

[0001] This invention belongs to the field of building structural health testing technology, and more specifically, relates to a building structural health testing method based on multimodal data. Background Technology

[0002] Currently, building structural health monitoring and assessment technologies are widely used in the field of building engineering. These technologies provide a scientific basis for the safe operation of building structures and are of great significance for preventing and controlling major safety accidents.

[0003] Commonly used methods for monitoring the health of building structures include vibration monitoring, fiber optic strain monitoring, acoustic emission monitoring, temperature field monitoring, and deformation monitoring. Vibration monitoring can obtain the structure's dynamic characteristics, such as vibration frequency, mode shape, and damping ratio, reflecting changes in the overall structural performance. Fiber optic strain monitoring can accurately measure the strain distribution of key components, providing a basis for judging the structure's load-bearing capacity. Acoustic emission monitoring can capture acoustic emission signals released during microcrack propagation, used to locate damaged areas. Temperature field monitoring can reflect anomalies in the temperature distribution on the structure's surface and inside, providing clues for analyzing local failure mechanisms. Deformation monitoring can comprehensively reflect the overall deformation trends of the structure, such as displacement, tilt, and settlement, providing a reference for structural reinforcement. While each of these individual monitoring methods has its own characteristics, they are insufficient to comprehensively and accurately assess the overall health status of the structure. Summary of the Invention

[0004] In view of this, the present invention provides a method for detecting the health of building structures based on multimodal data, which can solve the technical problem that existing single monitoring methods are difficult to comprehensively and accurately assess the overall health status of structures.

[0005] This invention is implemented as follows:

[0006] This invention provides a method for structural health detection of buildings based on multimodal data, comprising the following steps:

[0007] S10. Deploy a multimodal sensor array to collect multimodal monitoring data of the building structure. The multimodal monitoring data includes vibration monitoring data, fiber optic strain monitoring data, acoustic emission signal data, temperature field monitoring data, and deformation monitoring data.

[0008] S20. Preprocess the multimodal monitoring data;

[0009] S30. Conduct material performance tests, establish a database of building structure material parameters, and obtain building structure performance test data;

[0010] S40. Calculate the correlation between the multimodal monitoring data and the performance test data using a Bayesian network to obtain the multimodal data correlation matrix;

[0011] S50. Select the corresponding functional relationship from the preset combination of relational functions to establish a set of equations for the health status of the building structure.

[0012] S60. Fit the set of equations for the health status of the building structure using historical monitoring data to obtain the fitted structural health assessment model.

[0013] S70. Using the fitted structural health assessment model, damage location identification data, temperature anomaly index data, deformation degree index data, and cumulative damage index data are calculated.

[0014] S80. Generate a building structure health status assessment report based on the damage location identification data, the temperature anomaly index data, the deformation degree index data, and the cumulative damage index data.

[0015] Based on the above technical solution, the method for detecting the structural health of a building based on multimodal data of the present invention can be further improved as follows:

[0016] The vibration monitoring data includes vibration frequency, mode shape data, and damping ratio data.

[0017] Furthermore, the fiber optic strain monitoring data includes fiber optic strain data and sensor temperature data.

[0018] Furthermore, the acoustic emission signal data includes acoustic emission amplitude data, acoustic emission frequency data, acoustic emission duration data, and acoustic emission energy data.

[0019] Furthermore, the temperature field monitoring data includes surface temperature data and ambient temperature data.

[0020] Furthermore, the deformation monitoring data includes displacement data, tilt angle data, and settlement data.

[0021] Furthermore, the preprocessing of the multimodal monitoring data specifically includes:

[0022] The vibration monitoring data is processed, including noise reduction of the vibration frequency, the mode shape data, and the damping ratio data.

[0023] The fiber optic strain monitoring data is processed, including temperature compensation of the fiber optic strain data using the sensor temperature data to obtain corrected fiber optic strain data.

[0024] The acoustic emission signal data is processed, including waveform feature extraction of the acoustic emission amplitude data, acoustic emission frequency data, acoustic emission duration data, and acoustic emission energy data;

[0025] The temperature field monitoring data is processed, including temperature correction of the surface temperature data using the ambient temperature data.

[0026] The deformation monitoring data is processed, including benchmarking the displacement data, tilt angle data, and settlement data.

[0027] Furthermore, the test data for the building structure performance includes structural stiffness data, material thermal conductivity data, surface emissivity data, stress intensity factor data, stress cycle count data, and damage threshold data.

[0028] Furthermore, the combination of relational functions includes at least linear relations, exponential relations, logarithmic relations, and power function relations.

[0029] Furthermore, the set of equations for the health status of the building structure includes vibration response equations, strain distribution equations, acoustic emission characteristic equations, temperature field distribution equations, crack propagation equations, structural deformation equations, and damage accumulation equations.

[0030] The vibration response equation inputs include the vibration frequency, the mode shape data, and the damping ratio data, and the output is structural modal parameters;

[0031] The strain distribution equation takes the corrected fiber strain data and the structural stiffness data as inputs and outputs structural strain distribution data as output.

[0032] The acoustic emission characteristic equation inputs include the acoustic emission amplitude data, the acoustic emission frequency data, the acoustic emission duration data, and the acoustic emission energy data, and the output is damage location identification data;

[0033] The temperature field distribution equation takes into account the surface temperature data, the ambient temperature data, the material thermal conductivity data, and the surface emissivity data as inputs, and outputs temperature anomaly index data.

[0034] The input to the crack propagation equation includes the structural strain distribution data and the stress intensity factor data, and the output is the crack propagation rate data.

[0035] The structural deformation equation inputs include the displacement data, the tilt angle data, and the settlement data, and the output is the deformation degree index data;

[0036] The damage accumulation equation takes into account the stress cycle count data, the damage threshold data, and the crack propagation rate data, and outputs the cumulative damage index data.

[0037] The steps for acquiring the multimodal monitoring data include:

[0038] The vibration monitoring data acquisition steps include deploying a piezoelectric accelerometer array at key nodes of the building structure, acquiring the vibration frequency using a 1000 Hz sampling frequency, calculating the mode shape data using experimental modal analysis, and calculating the damping ratio data using the half-power bandwidth method.

[0039] The fiber optic strain monitoring data acquisition steps include arranging a fiber optic grating sensor array along the axial direction on the surface of the main load-bearing components of the building structure, obtaining the fiber optic strain data by demodulating the fiber optic reflection spectrum through wavelength division multiplexing technology, and arranging a temperature sensor near the fiber optic grating sensor to collect the sensor temperature data.

[0040] The acoustic emission signal data acquisition step includes deploying a piezoelectric acoustic emission sensor array in areas prone to cracks in the building structure, acquiring the acoustic emission amplitude data through a preamplifier, extracting the acoustic emission frequency data through a short-time Fourier transform, recording the start and end times of the acoustic emission signal to obtain the acoustic emission duration data, and performing an integral operation on the acoustic emission signal to obtain the acoustic emission energy data.

[0041] The temperature field monitoring data acquisition steps include fixing an infrared thermal imager on the outer surface of the building structure to collect the surface temperature data, and deploying a temperature sensor array in the monitoring area to collect the ambient temperature data.

[0042] The deformation monitoring data acquisition steps include installing a total station on the top of the building structure and setting up prism measuring points on key components to obtain the displacement data, setting up a dual-axis tilt sensor to collect the tilt angle data, and setting up a level to measure the settlement data using a leveling method.

[0043] The testing steps for the performance of the building structural materials include:

[0044] The structural stiffness data testing steps include setting up displacement sensors at the loading points of the building structural components, using a static loading method to record the loading stress and deformation data, and calculating the structural stiffness data.

[0045] The material thermal conductivity data testing steps include applying a constant temperature difference to both ends of the building structure material sample, measuring the steady-state heat flow, and calculating the material thermal conductivity data according to Fourier's law of thermal conductivity.

[0046] The surface emissivity data testing steps include using a comparative method at a standard temperature to simultaneously measure the radiation intensity of the building structure material sample and the blackbody using an infrared thermal imager to obtain the surface emissivity data.

[0047] The stress intensity factor data testing steps include preparing a pre-crack on a standard specimen of building structural material, conducting a three-point bending test, recording the crack propagation length and load data during loading, and calculating the stress intensity factor data.

[0048] The stress cycle number data testing step includes conducting fatigue loading tests on building structure material samples, recording the number of cyclic loadings of the samples under different stress levels, and obtaining the stress cycle number data.

[0049] The damage threshold data testing steps include cyclically loading a building structure material sample, monitoring the crack initiation process using an acoustic emission sensor, recording the stress level when the acoustic emission signal is first detected, and obtaining the damage threshold data.

[0050] Furthermore, the equations or calculations involved in this invention are described in detail below:

[0051] 1. Vibration monitoring data preprocessing:

[0052] The vibration signal noise reduction process uses wavelet transform, as shown below:

[0053]

[0054] In the formula, f d (t) represents the noise-reduced vibration signal; ψ j,k (t) is the wavelet basis function; φ J,k (t) is the scaling function; d j,k These are wavelet coefficients; a J,k is the approximation coefficient; J is the number of decomposition layers, ranging from 3 to 5; k is the translation parameter.

[0055] 2. Fiber optic strain temperature compensation:

[0056] The temperature compensation equation is expressed as follows:

[0057] ε c =ε m +K T (T-T0);

[0058] In the formula, ε c This is the strain value after temperature compensation; ε m The original strain value measured; K T This is the temperature compensation coefficient, typically in the range of 1×10⁻⁶. -6 Up to 5×10 -6 Between; T is the current temperature; T0 is the reference temperature.

[0059] 3. Acoustic emission waveform feature extraction:

[0060] The specific equations for calculating acoustic emission characteristic parameters are as follows:

[0061]

[0062] In the formula, E AE V(t) represents the acoustic emission energy; V(t) represents the acoustic emission signal voltage; t1 and t2 represent the signal start and end times; f c X(f) is the center frequency; X(f) is the Fourier transform of the signal; f is the frequency.

[0063] 4. Temperature field correction:

[0064] The temperature field correction equation is expressed as follows:

[0065] T c =T s +α(T e -T ref )+β;

[0066] In the formula, T c The corrected temperature; T s For measuring surface temperature; T e The ambient temperature; T ref The reference ambient temperature is α; α is the temperature correction factor, ranging from 0.8 to 1.2; β is the correction bias term.

[0067] 5. Standardization of deformation monitoring data:

[0068] The standardization equation is specifically expressed as follows:

[0069]

[0070] In the formula, X norm X represents the benchmarked data; X represents the original data; X min X is the minimum value of the data. max This represents the maximum value of the data.

[0071] 6. Bayesian network correlation calculation:

[0072] The correlation calculation equation is expressed as follows:

[0073]

[0074] In the formula, P(H|E) is the posterior probability; P(E|H) is the likelihood probability; P(H) is the prior probability; P(E) is the evidence probability; R ij Let be the correlation between the i-th and j-th parameters; n is the number of samples.

[0075] 7. Vibration response equation:

[0076] Based on the finite element theory, the vibration response equation is specifically expressed as follows:

[0077]

[0078] In the formula, M is the mass matrix; C is the damping matrix; K is the stiffness matrix; u is the displacement vector; and F(t) is the external excitation force vector.

[0079] Modal parameter extraction equation:

[0080]

[0081] In the formula, φ i ω is the mode shape vector of the i-th order; i ξ is the i-th natural frequency; i Let be the damping ratio of the i-th order.

[0082] 8. Strain distribution equation:

[0083] Based on Hooke's law and the strain compatibility equation, the strain distribution equation is specifically expressed as follows:

[0084] ε total =ε elastic +ε plastic +ε thermal ;

[0085]

[0086] ε plastic =Kσ n ;

[0087] ε thermal =αΔT;

[0088]

[0089] In the formula, ε total For total strain; ε elastic For elastic strain; ε plastic For plastic strain; ε thermal σ is thermal strain; E is the elastic modulus; K is the strength coefficient; n is the strain hardening index; α is the coefficient of thermal expansion; ΔT is the temperature change; [ε] is the strain tensor.

[0090] 9. Acoustic emission characteristic equation:

[0091] Based on the theory of acoustic emission wave propagation, the characteristic equation of acoustic emission is specifically expressed as follows:

[0092]

[0093] In the formula, L is the positioning matrix; (x s ,ys ,z s (x) represents the coordinates of the sound source; i ,y i ,z i ) represents the coordinates of the i-th sensor; v represents the speed of sound propagation; t represents the speed of sound propagation. i t0 is the arrival time; t0 is the occurrence time; DI is the damage index; A i d is the amplitude; i For the distance of propagation.

[0094] 10. Temperature field distribution equation:

[0095] Based on Fourier's law of heat conduction, the temperature field distribution equation is specifically expressed as follows:

[0096]

[0097] In the formula, ρ is density; c is specific heat capacity; λ is thermal conductivity; q v Internal heat source; q r ε is the radiative heat flux density; ε is the emissivity; σ is the Stefan-Boltzmann constant; T s T represents the surface temperature. e Ambient temperature; TAI is the temperature anomaly index; T i Temperature at the measuring point; T ref The reference temperature is N; the number of measurement points is N.

[0098] 11. Crack propagation equation:

[0099] Based on fracture mechanics theory, the crack propagation equation is specifically expressed as follows:

[0100]

[0101] ΔK=K max -K min ;

[0102] In the formula, a is the crack length; N is the number of cycles; C, m, n are material constants; ΔK is the stress intensity factor amplitude; K max K is the maximum stress intensity factor. IC σ is the fracture toughness; F(a / W) is the stress; F(a / W) is the geometric correction factor; W is the specimen width.

[0103] 12. Structural Deformation Equation:

[0104] Based on the theory of elasticity, the structural deformation equation is specifically expressed as follows:

[0105]

[0106] In the formula, δ is the deformation vector; K is the stiffness matrix; F is the force vector; M is the moment vector; DI d w is the deformation index. i δ is the weighting coefficient. i The current deformation value; δ i0 This is the initial deformation value.

[0107] 13. Damage accumulation equation:

[0108] Based on the fatigue damage accumulation theory, the damage accumulation equation is expressed as follows:

[0109]

[0110] In the formula, D is the cumulative damage value; n i N represents the actual number of iterations. i To allow for a certain number of loops; a c σ is the critical crack length; i Stress level; C,m are material constants; A,n are crack propagation parameters; K I This is the stress intensity factor.

[0111] The principles and significance of establishing the above equations are explained below:

[0112] 1. The vibration response equation adopts the form of a second-order ordinary differential equation, considering the mass, damping and stiffness characteristics of the structure, and obtains the dynamic characteristics of the structure through modal analysis;

[0113] 2. The strain distribution equation considers the coupling effect of elastic, plastic and thermal strains and uses tensor form to describe the three-dimensional strain field distribution;

[0114] 3. The acoustic emission characteristic equation is based on the principle of acoustic wave propagation time difference positioning, and the damage positioning index is calculated by combining the attenuation law.

[0115] 4. The temperature field distribution equation takes into account heat conduction and radiation heat transfer, and uses partial differential equations to describe the unsteady temperature field;

[0116] 5. The crack propagation equation is based on Paris's law, taking into account the effects of stress ratio and fracture toughness, and describes the fatigue crack propagation behavior.

[0117] 6. The structural deformation equation is in matrix form to establish the relationship between load and deformation and to calculate the deformation degree index;

[0118] 7. The damage accumulation equation combines the Miner criterion and fracture mechanics theory to consider the coupling effect of fatigue damage and crack propagation.

[0119] These equations employ nonlinear relationships such as power functions and exponential functions, primarily based on the following considerations:

[0120] 1. The constitutive relation of materials exhibits nonlinear characteristics; for example, the strain hardening index reflects the nonlinearity of plastic deformation. In the prior art, the constitutive relation of a material refers to a mathematical model describing the relationship between internal stress and strain when the material is subjected to force or changes in external conditions. This relationship reflects the connection between the inherent properties of the material and its response under external loads.

[0121] 2. The damage evolution process has a cumulative effect, and an exponential function is needed to describe the accelerated degradation characteristics;

[0122] 3. Sound wave attenuation and heat conduction exhibit exponential attenuation characteristics;

[0123] 4. The crack propagation rate has a power function relationship with the stress intensity factor.

[0124] For multiple functional relationships, the mathematical expressions for different functional relationships are as follows:

[0125] 1. The basic form of a linear relationship is specifically represented as follows:

[0126] y = ax + b + ε;

[0127] In the formula, y is the dependent variable; x is the independent variable; a is the slope, representing the rate of change; b is the intercept; and ε is the random error term, which follows a normal distribution N(0, σ). 2 ).

[0128] 2. The basic form of the exponential relationship is specifically represented as follows:

[0129] y = ae bx +ε;

[0130] y = ae bx +ce dx +ε;

[0131] In the formula, y is the dependent variable; x is the independent variable; a, b, c, d are undetermined coefficients; e is the base of the natural logarithm; and ε is the random error term.

[0132] 3. The basic form of the logarithmic relation is specifically represented as follows:

[0133] y = alan(x) + b + ε;

[0134] y = aln(x) + bln(z) + c + ε;

[0135] In the formula, y is the dependent variable; x and z are independent variables; a, b, and c are undetermined coefficients; ln is the natural logarithm; and ε is the random error term.

[0136] 4. The basic form of the power function relationship is specifically represented as follows:

[0137] y = ax b +ω;

[0138] y = ax b +cz d +ε;

[0139] In the formula, y is the dependent variable; x and z are the independent variables; a, b, c, and d are undetermined coefficients; and ε is the random error term.

[0140] The methods for determining coefficients include the following two, both of which are general methods:

[0141] 1. Least squares method:

[0142]

[0143] In the formula, y i These are measured values; is the fitted value; n is the number of samples.

[0144] 2. Maximum likelihood estimation:

[0145]

[0146] In the formula, L(θ) is the likelihood function; θ is the parameter to be estimated; f(x) i |θ) is the probability density function.

[0147] The goodness-of-fit metrics include the following two methods, both of which are general approaches:

[0148] 1. Coefficient of determination:

[0149]

[0150] In the formula, This represents the average of the measured values.

[0151] 2. Root mean square error:

[0152]

[0153] Conditions for the applicability of each functional relationship:

[0154] 1. Linear relationships are suitable for situations where variables change proportionally;

[0155] 2. Exponential relationships are suitable for describing accelerating or declining processes;

[0156] 3. Logarithmic relationships are suitable for describing processes with diminishing marginal returns;

[0157] 4. Power function relationships are suitable for describing scaling laws or fractal properties.

[0158] Compared with existing technologies, the beneficial effects of the multimodal data-based building structure health monitoring method provided by this invention are as follows: First, multiple sensor arrays are deployed to comprehensively collect monitoring indicators such as vibration response, strain distribution, temperature field distribution, acoustic emission characteristics, and structural deformation. Based on this, preprocessing techniques such as wavelet transform, temperature compensation, and waveform feature extraction effectively eliminate the influence of environmental interference factors on the monitoring data. Then, based on the vibration response equation, strain distribution equation, temperature field distribution equation, crack propagation equation, and structural deformation equation, a comprehensive mathematical model reflecting the coupling of multiple physical fields is constructed. Using this model, combined with Bayesian network analysis to analyze the correlation between monitoring data and structural performance parameters, an evaluation equation set describing the structural health status is established. Finally, comprehensive evaluation indicators such as damage location index, temperature anomaly index, deformation degree index, and cumulative damage index are extracted from the evaluation equation set, comprehensively reflecting the structural damage status, local failure risk, and overall deterioration trend.

[0159] Compared with existing technologies, this invention has the following significant advantages: 1) Through data preprocessing and environmental factor compensation, the reliability and accuracy of monitoring data are effectively improved, laying a solid foundation for subsequent health status assessment; 2) The established multi-physics coupling model more comprehensively and accurately describes the evolution law of structural health status, providing a scientific basis for fault diagnosis and status prediction; 3) The proposed comprehensive evaluation index system can more comprehensively reflect the damage and deterioration of the structure, providing an important reference for management departments to formulate maintenance strategies, and solving the technical problem that existing single monitoring methods are difficult to comprehensively and accurately assess the overall health status of the structure. Attached Figure Description

[0160] Figure 1 A flowchart of the method provided by the present invention. Detailed Implementation

[0161] like Figure 1 The diagram shown is a flowchart of a building structure health detection method based on multimodal data provided by the present invention. The specific implementation steps of the present invention are described in detail below:

[0162] The specific implementation of step S10 is as follows: First, multiple sensor arrays are deployed at key nodes of the building structure to collect multimodal monitoring data, including vibration, fiber optic strain, acoustic emission, temperature field, and deformation. Specifically, vibration monitoring data collection includes: deploying piezoelectric accelerometer arrays at key nodes of the building structure, acquiring vibration signals using a 1000 Hz sampling frequency, extracting vibration frequency and mode shape data using experimental modal analysis, and calculating damping ratio data using the half-power bandwidth method. Fiber optic strain monitoring data collection includes: deploying fiber optic grating sensor arrays along the axial direction on the surface of the main load-bearing components of the building structure, demodulating the fiber optic reflection spectrum using wavelength division multiplexing (WDM) technology to obtain fiber optic strain data, and simultaneously deploying temperature sensors near the fiber optic grating sensors to obtain sensor temperature data. Acoustic emission signal data collection includes: deploying piezoelectric acoustic emission sensor arrays in areas prone to cracking in the building structure, acquiring acoustic emission amplitude data through a preamplifier, extracting acoustic emission frequency data using short-time Fourier transform, recording the start and end times of the acoustic emission signal to obtain acoustic emission duration data, and performing integral calculations on the acoustic emission signal to obtain acoustic emission energy data. The acquisition of temperature field monitoring data includes: installing an infrared thermal imager on the outer surface of the building structure to obtain surface temperature data, and simultaneously deploying a temperature sensor array in the monitoring area to collect ambient temperature data. The acquisition of deformation monitoring data includes: installing a total station on the top of the building structure and deploying prism measuring points on key components to obtain displacement data; deploying a dual-axis tilt sensor to collect tilt angle data; and using a level to measure settlement data. This multimodal monitoring data comprehensively reflects the dynamic response of the building structure and environmental effects, laying the foundation for subsequent health status assessments.

[0163] The specific implementation of step S20 is as follows: Preprocessing the collected multimodal monitoring data to improve data quality. First, noise reduction is performed on the vibration monitoring data using wavelet transform. By selecting appropriate wavelet basis functions and decomposition levels, high-frequency noise is filtered out while preserving the intrinsic vibration characteristics of the structure. Temperature compensation is applied to the fiber optic strain monitoring data. Using sensor temperature data and empirical coefficients, the accurate strain value after temperature compensation is calculated. Waveform feature extraction is performed on the acoustic emission signal data, including calculating parameters such as acoustic emission amplitude, center frequency, duration, and energy, providing a basis for subsequent damage analysis. Temperature field monitoring data is corrected using ambient temperature data and empirical correction coefficients to eliminate the influence of ambient temperature changes on surface temperature. Deformation monitoring data is standardized by normalizing the displacement, tilt, and settlement data of different measuring points to the [0,1] interval, providing standardized input for comprehensive evaluation. Through the above preprocessing, environmental interference can be effectively eliminated, highlighting the physical response characteristics of the structure itself, laying a good foundation for the next step of health status assessment.

[0164] In existing technologies, fiber optic strain monitoring technology is a high-precision measurement method based on the principle of fiber optic sensing. When an optical fiber is subjected to external stress, the optical signal inside it changes, including the propagation speed and phase of light. By measuring these changes, the strain of the object can be accurately calculated. Methods for acquiring fiber optic strain monitoring data include:

[0165] 1. Fiber optic installation: One or more specially designed sensing optical fibers are laid on the structure being monitored. These optical fibers can sense the strain changes of the structure.

[0166] 2. Signal injection: Light signals are injected into the sensing optical fiber through a light source. These signals will propagate in the optical fiber and interact with the surrounding environment.

[0167] 3. Signal Acquisition: When optical signals propagate in optical fibers, they are affected by environmental factors such as strain and temperature, resulting in phenomena such as scattering or frequency shift. Using a suitable receiver, these altered optical signals can be captured.

[0168] 4. Data Processing: The acquired optical signals need to undergo data processing and analysis to extract accurate information about the strain. This typically involves using algorithms to analyze characteristics such as signal intensity and spectrum.

[0169] The specific implementation of step S30 is as follows: Acquire performance test data of the building structure, including indicators such as structural stiffness, material thermal conductivity, surface emissivity, stress intensity factor, stress cycle count, and damage threshold. Specifically, the structural stiffness test involves placing displacement sensors at the loading points of the building structure components, using a static loading method, recording the loading stress and deformation data, and then calculating the structural stiffness. The material thermal conductivity test involves applying a constant temperature difference to both ends of the building structure material sample, measuring the steady-state heat flow, and calculating the material thermal conductivity according to Fourier's law of thermal conductivity. The surface emissivity test involves using a comparative method at a standard temperature, simultaneously measuring the radiation intensity of the building structure material sample and a blackbody using an infrared thermal imager to obtain the surface emissivity. The stress intensity factor test involves preparing a pre-existing crack on a standard building structure material sample, conducting a three-point bending test, recording the crack propagation length and load data during loading, and calculating the stress intensity factor. The stress cycle count test involves conducting a fatigue loading test on the building structure material sample, recording the number of cyclic loading cycles under different stress levels. Damage threshold testing involves cyclically loading structural material samples, monitoring crack initiation using acoustic emission sensors, and recording the stress level at which the first acoustic emission signal is detected to obtain the damage threshold. These structural performance parameters reflect the mechanical properties of the building materials and provide important information for health status assessment.

[0170] The specific implementation of step S40 is as follows: A Bayesian network method is used to calculate the correlation between multimodal monitoring data and building structural performance data, resulting in a multimodal data correlation matrix. Specifically, firstly, nodes and edges of the Bayesian network are established, where nodes include various monitoring data and material performance parameters, and edges represent causal relationships between data. Then, based on historical monitoring sample data, the conditional probability distribution between each node is calculated using the maximum likelihood estimation method to obtain the posterior probability. Finally, the correlation coefficient between any two nodes is calculated based on the posterior probability to construct the multimodal data correlation matrix. This correlation analysis method based on probabilistic reasoning can effectively characterize the coupling effects of various factors in complex systems, laying the foundation for establishing a health status assessment model.

[0171] The specific implementation of step S50 is as follows: Select the corresponding functional relationship from a preset combination of relational functions to establish a set of health state equations for the building structure. The preset combination of relational functions includes linear, exponential, logarithmic, and power functions. Linear relationships are suitable for describing proportional changes between variables; exponential relationships are suitable for describing accelerated growth or decay processes; logarithmic relationships are suitable for describing processes with diminishing marginal effects; and power functions are suitable for describing scaling laws or fractal characteristics. These functional relationships can reflect the inherent laws among various response parameters of the building structure, such as vibration response, strain distribution, temperature field distribution, crack propagation, and structural deformation. By selecting appropriate functional relationships, a set of health state equations covering multi-physics coupling is established, laying the foundation for evaluating the accuracy of the model.

[0172] The specific implementation of step S60 is as follows: The established set of equations for the structural health status of the building is fitted with parameters using historical monitoring data to obtain a fitted structural health assessment model. Specifically, the least squares method or maximum likelihood estimation method is used to determine the unknown coefficients in each equation, minimizing the sum of squares error between the fitted values ​​and the measured values. Simultaneously, goodness-of-fit indices, such as the coefficient of determination R^2 and root mean square error RMSE, are calculated to evaluate the model's predictive accuracy. When the goodness-of-fit meets the requirements, an assessment model describing the structural health status of the building is obtained. This model fitting method based on historical data can fully utilize existing information and improve the accuracy and reliability of health status assessment.

[0173] The specific implementation of step S70 is as follows: using the fitted structural health assessment model, damage location identification data, temperature anomaly index data, deformation degree index data, and cumulative damage index data are calculated. Specifically, the damage location identification data is based on the acoustic emission characteristic equation, combined with the wave propagation time difference positioning principle and attenuation law, to calculate the sound source coordinates and damage indicators. The temperature anomaly index data is based on the temperature field distribution equation, considering heat conduction and radiative heat transfer effects, to calculate the degree of temperature anomaly relative to the reference temperature. The deformation degree index data is based on the structural deformation equation, establishing a matrix relationship between load and deformation, to calculate a comprehensive index of structural deformation. The cumulative damage index data is based on the damage accumulation equation, combined with fatigue damage and crack propagation theories, to calculate the overall cumulative damage degree of the structure. These health status indicators comprehensively reflect the degree of damage and deterioration trend of the building structure, providing crucial basis for subsequent comprehensive assessment.

[0174] The specific implementation of step S80 is as follows: A building structure health status assessment report is generated based on damage location identification data, temperature anomaly index data, deformation degree index data, and cumulative damage index data. First, the damage location identification data is used to identify key areas of damage in the building structure, providing targeted guidance for subsequent inspection and maintenance. Second, hotspot areas are identified based on the temperature anomaly index data, and possible local failure mechanisms are analyzed. Third, the deformation degree index data is combined with an assessment of the overall structural deformation risk, providing a basis for formulating reinforcement measures. Finally, the cumulative damage index data is comprehensively considered to predict the remaining service life of the building structure, providing decision support for the formulation of maintenance and management plans. This health status assessment report comprehensively summarizes the damage status, deterioration trends, and safety hazards of the building structure, providing a scientific basis for owners or management departments to ensure the safe operation of the building structure.

[0175] In summary, the core of this method lies in establishing a structural health status assessment model under multi-physics coupling, enabling comprehensive analysis based on multi-source monitoring data. Through preprocessing to eliminate environmental interference, employing Bayesian network analysis for correlation, and selecting appropriate functional relationships to fit the health status equations, multiple comprehensive indicators reflecting the degree of structural damage and deterioration trends are ultimately obtained. These indicators provide a scientific basis for the safety management of building structures and have strong practicality. Compared with existing technologies, the innovation of this method is reflected in three aspects: 1) It establishes a mathematical model of multi-physics coupling, more accurately characterizing the structural response; 2) It proposes a correlation analysis method based on probabilistic reasoning, enhancing the expressive power of the coupling relationship between parameters; 3) It generates comprehensive assessment indicators that fully reflect the health status, providing effective support for structural maintenance and management. In conclusion, this method has strong theoretical and applied value and broad prospects for promotion in the field of building structural health monitoring and assessment.

[0176] Specifically, the principle of this invention is: a method for assessing the structural health status of buildings based on multimodal monitoring data. The key to this method lies in establishing a mathematical model reflecting the coupling effects of multiple physics fields and utilizing Bayesian network analysis technology to achieve correlation analysis between monitoring data and structural performance parameters. Ultimately, a comprehensive assessment index system reflecting the overall structural health status is generated. The principle and implementation logic of this method are as follows:

[0177] 1. Acquisition and Preprocessing of Multimodal Monitoring Data: First, various sensor arrays, including vibration sensors, fiber optic strain sensors, acoustic emission sensors, temperature sensors, and displacement sensors, are deployed at key locations on the building structure to comprehensively collect various physical response indicators of the structure. To ensure the quality of the monitoring data, the acquired raw data needs to be preprocessed. For vibration monitoring data, wavelet transform is used for noise reduction to effectively remove high-frequency interference components; for fiber optic strain data, temperature compensation is performed using sensor temperature information to eliminate measurement errors caused by temperature changes; for acoustic emission signals, characteristic parameters such as amplitude, frequency, duration, and energy are extracted to lay the foundation for subsequent damage location analysis; for temperature field monitoring data, ambient temperature information is used for correction to eliminate the influence of ambient temperature changes; for deformation monitoring data, normalization is performed to unify the deformation amounts in different dimensions to the [0,1] interval. Through the above preprocessing, the quality and reliability of the monitoring data can be effectively improved.

[0178] 2. Testing of Building Structural Performance Parameters: In addition to multimodal monitoring data, this invention also requires obtaining the mechanical performance parameters of the building structural materials, including structural stiffness, thermal conductivity, surface emissivity, stress intensity factor, stress cycle life, and damage threshold. These parameters reflect the mechanical properties of the building materials and are important bases for establishing a health status model. Specific testing methods include: static loading tests to measure structural stiffness, heat conduction tests to determine material thermal conductivity, infrared radiation comparison methods to measure surface emissivity, three-point bending tests to determine the stress intensity factor, fatigue loading tests to obtain stress cycle life, and acoustic emission monitoring methods to determine the damage threshold. The above structural performance parameters, together with the multimodal monitoring data, will serve as inputs to the health status assessment model.

[0179] 3. Bayesian Network-Based Correlation Analysis: To establish a mathematical model describing the structural health status of buildings, it is necessary to first analyze the correlation between multimodal monitoring data and structural performance parameters. This invention employs the Bayesian network method for this analysis. Specifically, a node network containing various monitoring data and material performance parameters is first established, and the conditional probability distribution between each node is calculated using the maximum likelihood estimation method based on historical sample data. Then, the posterior probability distribution is calculated using Bayes' theorem, thereby obtaining the correlation coefficient between any two parameters. This probabilistic reasoning-based analysis method can effectively characterize the coupling relationships of various factors in complex systems, providing a reliable data foundation for the establishment of a health status assessment model.

[0180] 4. Establishment of a Health Status Assessment Model: Based on the above correlation analysis results, this invention selects a suitable mathematical model from a pre-defined combination of functional relationships to establish a set of equations describing the health status of the building structure. These equations cover multiple physical processes such as vibration response, strain distribution, temperature field distribution, crack propagation, and structural deformation, accurately reflecting the intrinsic relationship between multimodal monitoring data and structural performance parameters. Specifically, they include: 1) Vibration response equations, describing the structure's natural frequencies, mode shapes, and damping characteristics; 2) Strain distribution equations, describing the strain state during structural loading; 3) Temperature field distribution equations, describing the heat conduction and radiation processes under ambient temperature; 4) Crack propagation equations, describing the propagation law of fatigue cracks; and 5) Structural deformation equations, describing the overall deformation characteristics under external loads. By fitting historical monitoring data, the unknown parameters in each equation can be determined, establishing a comprehensive assessment model describing the health status of the building structure.

[0181] 5. Comprehensive Assessment of Structural Health Status: Based on the aforementioned health status assessment model, this invention extracts four key comprehensive assessment indicators: 1) Damage Location Index: using acoustic emission characteristics analysis to identify critical areas of damage within the structure; 2) Temperature Anomaly Index: combining temperature field distribution analysis to assess local failure risk; 3) Deformation Degree Index: assessing structural safety status based on overall deformation characteristics; 4) Cumulative Damage Index: combining fatigue damage theory to predict the remaining service life of the structure. These indicators comprehensively reflect the damage status, local failure risk, and overall deterioration trend of the building structure, providing important basis for management departments to formulate maintenance plans.

[0182] The following is a specific embodiment 1 of the present invention. The specific implementation of each step in this embodiment 1 is described in detail below: The specific implementation of step S10 is as follows: First, multiple sensor arrays are deployed at key nodes of the building structure to collect multimodal monitoring data such as vibration, fiber optic strain, acoustic emission, temperature field, and deformation of the building structure. Among them, the acquisition of vibration monitoring data includes: deploying piezoelectric accelerometer arrays at key nodes of the building structure, acquiring vibration signals using a sampling frequency of 1000 Hz, and then calculating the vibration frequency ω using experimental modal analysis. i And mode shape data φ i The damping ratio ξ was calculated using the half-power bandwidth method. i The basic form of the vibration response equation is: Where M is the mass matrix, C is the dust-blocking matrix, K is the stiffness matrix, u is the displacement vector, and F(t) is the external excitation force vector. Modal parameters φ can be extracted through modal analysis. i ,ω i ,ξ i The acquisition of fiber optic strain monitoring data includes: arranging fiber optic grating sensor arrays axially on the surfaces of the main load-bearing components of the building structure, and using wavelength division multiplexing (WDM) technology to demodulate the fiber optic reflection spectrum to obtain fiber optic strain data ε. m Simultaneously, a temperature sensor is deployed near the fiber Bragg grating sensor to acquire the sensor temperature data T. The strain distribution equation can be expressed as ε. total =ε elastic +ε plastic +ε thermal , where ε elastic =σ / E,ε plastic =Kσ n ,ε thermal =αΔT. Acoustic emission signal data acquisition includes: deploying a piezoelectric acoustic emission sensor array in areas prone to structural cracks in the building, and acquiring acoustic emission amplitude data A through a preamplifier. i The acoustic emission frequency data f is extracted using short-time Fourier transform. c The acoustic emission duration data is obtained by recording the start and end times of the acoustic emission signal, and the acoustic emission energy data E is obtained by integrating the acoustic emission signal. AE The acoustic emission characteristic equation can be expressed as: and The acquisition of temperature field monitoring data includes: fixing an infrared thermal imager on the outer surface of the building structure to obtain surface temperature data T. s Simultaneously, an array of temperature sensors was deployed in the monitoring area to collect ambient temperature data (T). e The temperature field distribution equation can be expressed as: and in The collection of deformation monitoring data includes: installing a total station on the top of the building structure and setting up prism measuring points on key components to obtain displacement data δ. x ,δ y ,δ z Deploy dual-axis tilt sensors to collect tilt angle data θ x ,θ y ,θ z Settlement data were obtained using a level instrument. The structural deformation equation can be expressed as follows: and

[0183] The specific implementation of step S20 is as follows: Preprocessing the collected multimodal monitoring data to improve data quality. First, noise reduction processing is performed on the vibration monitoring data using wavelet transform, by selecting an appropriate wavelet basis function ψ. j,k (t) and the number of decomposition levels J can be expressed as Where d j,k For wavelet coefficients, α J,k As approximation coefficients, high-frequency noise is filtered out while preserving the intrinsic vibration characteristics of the structure. Temperature compensation is applied to the fiber optic strain monitoring data, utilizing sensor temperature data T and empirical coefficient K. T , can be represented as ε c =ε m +K T (T-T0) yields the corrected fiber strain data ε c Waveform features are extracted from acoustic emission signal data to calculate acoustic emission energy. Center frequency The temperature field monitoring data was corrected using the ambient temperature data T. e The empirical correction coefficients α and β can be expressed as T c =T s +α(T e -T ref )+β, to obtain the corrected surface temperature data T c The deformation monitoring data, after benchmarking, can be expressed as follows: Displacement δ at different measuring points x ,δ y ,δ z , tilt θ x ,θ y ,θ z The settlement data were normalized to the [0,1] interval.

[0184] The specific implementation of step S30 is as follows: Obtain performance test data of the building structure. The test method for structural stiffness data is as follows: Displacement sensors are installed at the loading points of the building structure components. A static loading method is used to record the loading stress σ and deformation data δ, from which the structural stiffness K = σ / δ can be calculated. The test method for material thermal conductivity data is as follows: A constant temperature difference ΔT is applied to both ends of the building structure material sample. The steady-state heat flow q is measured, and the material thermal conductivity can be calculated according to Fourier's law of thermal conductivity. Where L represents the sample thickness. The surface emissivity data is tested using a comparative method at standard temperature, simultaneously measuring the radiation intensity I of the building structure material sample and a blackbody using an infrared thermal imager. s and I b The surface emissivity ε = I can be calculated. s / I b The method for testing stress intensity factor data is as follows: A pre-existing crack is prepared on a standard specimen of building structural material, a three-point bending test is performed, and the crack propagation length *a* and load data *P* are recorded during loading. The stress intensity factor can then be calculated. Where σ is the stress, W is the specimen width, and F(a / W) is the geometric correction factor. The method for testing the stress cycle number data is as follows: fatigue loading tests are performed on building structure material specimens, and the stress σ of the specimens at different stress levels is recorded. i The number of times N is loaded in the loop. i Paris's Law can be used. The method for testing damage threshold data is as follows: Cyclic loading is applied to structural material samples, and the crack initiation process is monitored using an acoustic emission sensor. The stress level at which the first acoustic emission signal is detected is recorded, which is the damage threshold σ. th .

[0185] The specific implementation of step S40 is as follows: A Bayesian network method is used to calculate the correlation between multimodal monitoring data and building structural performance data, obtaining a multimodal data correlation matrix. The basic idea of ​​a Bayesian network is to calculate the conditional probability distribution P(E|H) and prior probability distribution P(H) between each node based on historical sample data using the maximum likelihood estimation method, and then apply Bayes' theorem... The posterior probability distribution is obtained. Finally, the correlation coefficient between any two nodes is calculated based on the posterior probability. Construct a multimodal data association matrix R. This association analysis method based on probabilistic reasoning can effectively characterize the coupling effects of various factors in complex systems.

[0186] The specific implementation of step S50 is as follows: Select the corresponding functional relationship from the preset combination of relational functions to establish a set of equations for the health status of the building structure. The preset combination of relational functions includes the linear relationship y = ax + b + ε and the exponential relationship y = ae bx +ε and y=aebx +ae dx +ε, the logarithmic relations y=aln(x)+b+ε and y=aln(x)+bln(z)+c+ε, and the power function relation y=ax b +ε and y=ax b +cz d +ε. These functional relationships can reflect the inherent laws among various response parameters of a building structure, such as vibration response, strain distribution, temperature field distribution, crack propagation, and structural deformation. By selecting appropriate functional relationships, a set of health state equations covering multi-physics coupling can be established.

[0187] The specific implementation of step S60 is as follows: The established set of building structural health state equations is fitted with parameters using historical monitoring data to obtain the fitted structural health assessment model. The least squares method can be used for parameter estimation, and the objective function is... Where y i These are measured values. The fitted value is denoted as n, where n is the sample size. A goodness-of-fit index, such as the coefficient of determination, is also calculated. and root mean square error The prediction accuracy of the model is evaluated. When the goodness of fit meets the requirements, an evaluation model describing the structural health status of the building can be obtained.

[0188] The specific implementation of step S70 is as follows: using the fitted structural health assessment model, damage location identification data, temperature anomaly index data, deformation degree index data, and cumulative damage index data are calculated. Damage location identification data DI is calculated based on the acoustic emission characteristic equation, combined with the wave propagation time difference positioning principle and attenuation law. Temperature anomaly index data TAI is calculated based on the temperature field distribution equation, considering heat conduction and radiation heat transfer effects. Deformation degree index data DI… d The load-deformation matrix relationship is established based on the structural deformation equation. The cumulative damage index D is calculated based on the damage accumulation equation, combined with fatigue damage and crack propagation theories. These health status indicators comprehensively reflect the degree of damage and deterioration trend of the building structure.

[0189] The specific implementation of step S80 is as follows: Based on the various health status indicators calculated above, a building structure health status assessment report is generated. First, the damage location identification data (DI) is used to determine the key areas of damage in the building structure. Second, hotspot areas are identified based on the temperature anomaly index data (TAI), and possible local failure mechanisms are analyzed. Furthermore, the deformation degree index data (DI) is combined with... dAssess the overall structural deformation risk. Finally, considering the cumulative damage index data D, predict the remaining service life of the building structure. The above health status assessment report comprehensively summarizes the damage status, deterioration trend, and safety hazards of the building structure, providing a scientific basis for owners or management departments to ensure the safe operation of the building structure.

[0190] To better understand and implement this invention, a specific application scenario is provided below as Example 2: A high-rise residential building in a certain city was completed in 2015, with a total construction area of ​​50,000 square meters, 25 floors above ground and 2 floors underground. Located in the city center, the building is surrounded by a complex environment and is affected by various environmental factors such as traffic vibrations and temperature changes. To ensure the safe operation of the building, the owner decided to adopt the building structure health detection method based on multimodal data proposed in this invention to comprehensively assess the building's health status.

[0191] First, multiple sensor arrays were deployed at key locations in the high-rise residential building, including:

[0192] 1. Vibration monitoring sensor array: A total of 15 piezoelectric accelerometers are installed at key nodes of the main load-bearing walls and floor slabs of the building to collect data at a sampling frequency of 1000 Hz and obtain dynamic parameters such as vibration frequency, mode shape and damping ratio.

[0193] 2. Fiber Optic Strain Monitoring Sensor Array: Twenty fiber optic grating sensors are deployed axially along the surface of the main load-bearing components of the building to acquire strain data using wavelength division multiplexing (WDM) technology. Simultaneously, ten temperature sensors are deployed near the fiber optic sensors to collect the temperature of the sensor bodies.

[0194] 3. Acoustic emission monitoring sensor array: Twelve piezoelectric acoustic emission sensors are deployed in areas of the building prone to cracks, such as the junction of floor slabs and walls, and beam-column connection nodes, to collect parameters such as the amplitude, frequency, duration, and energy of the acoustic emission signal.

[0195] 4. Temperature Field Monitoring Sensor Array: A total of 20 infrared thermal imagers were deployed on the exterior wall surface of the building to acquire surface temperature distribution data. Simultaneously, 15 temperature sensors were deployed in the monitoring area to collect ambient temperature data.

[0196] 5. Deformation monitoring sensor array: One total station was installed on the roof of the building, and 30 prism measuring points were installed on the surface of key components to acquire displacement data. In addition, 10 biaxial tilt sensors and 5 levels were installed on different floors of the building to collect tilt angle and settlement data.

[0197] The deployment of the aforementioned multimodal monitoring sensor array is shown in Table 1:

[0198] Table 1. Deployment of the multimodal monitoring sensor array

[0199]

[0200] After a year of continuous monitoring, a wealth of multimodal monitoring data was accumulated. To improve the quality and reliability of this raw monitoring data, preprocessing was performed, specifically including:

[0201] 1. Vibration monitoring data preprocessing:

[0202] The vibration signal is denoised using wavelet transform, and the specific formula is as follows:

[0203]

[0204] In the formula, f d (t) represents the noise-reduced vibration signal; ψ j,k (t) is the wavelet basis function; φ J,k (t) is the scaling function; d j,k These are wavelet coefficients; a J,k is the approximation coefficient; J is the number of decomposition layers, ranging from 3 to 5; k is the translation parameter. By using appropriate wavelet basis functions and decomposition layers, high-frequency interference can be effectively filtered out while preserving the intrinsic vibration characteristics of the structure.

[0205] 2. Temperature compensation for fiber optic strain data:

[0206] Temperature compensation is performed on the raw fiber optic strain data using synchronously acquired sensor temperature data, as shown in the following formula:

[0207] ε c =ε m +K T (T-T0);

[0208] In the formula, ε c This is the strain value after temperature compensation; ε m The original strain value measured; K T This is the temperature compensation coefficient, with a value range of 1×10. -6 Up to 5×10 -6 T represents the current temperature; T0 represents the reference temperature. This eliminates the influence of temperature changes on strain measurement.

[0209] 3. Acoustic emission signal waveform feature extraction:

[0210] The waveform characteristic parameters of the acquired acoustic emission signal are calculated, including the energy E. AE Center frequency f c The formula is as follows:

[0211]

[0212] In the formula, V(t) is the acoustic emission signal voltage; t1 and t2 are the signal start and end times; and X(f) is the Fourier transform of the signal. These parameters provide a basis for subsequent damage localization analysis.

[0213] 4. Temperature field monitoring data correction:

[0214] The surface temperature measurement results are corrected using ambient temperature data, as shown in the following formula:

[0215] T c =T s +α(T e -T ref )+β;

[0216] In the formula, T c The corrected temperature; T s For measuring surface temperature; T e The ambient temperature; T ref The reference ambient temperature is used; α is the temperature correction factor, ranging from 0.8 to 1.2; β is the correction bias term. This eliminates the influence of ambient temperature changes on surface temperature measurement.

[0217] 5. Standardization of deformation monitoring data:

[0218] Deformation monitoring data from different dimensions, such as displacement, tilt, and settlement, are uniformly standardized using the following formula:

[0219]

[0220] In the formula, X norm X represents the benchmarked data; X represents the original data; X min X is the minimum value of the data. max This represents the maximum value of the data. This normalizes the deformation in different dimensions to the [0,1] interval, providing standardized input for comprehensive evaluation.

[0221] After the above preprocessing, high-quality multimodal monitoring data were obtained, laying the foundation for subsequent health status assessment.

[0222] At the same time, the structural material performance parameters of the high-rise residential building were also tested, including:

[0223] 1. Structural stiffness testing:

[0224] Ten displacement sensors were installed at the loading points of the main load-bearing components of the building. A static loading method was used to record the loading stress σ and deformation δ, and the structural stiffness K = σ / δ was calculated. The test results showed that the average structural stiffness of the building was 3.5 GPa.

[0225] 2. Material thermal conductivity testing:

[0226] A constant temperature difference of 20℃ was applied to both ends of a sample of the building's exterior wall material. The steady-state heat flux density q was measured to be 85 W / m². The thermal conductivity of the material was calculated based on Fourier's law of thermal conductivity. It is 0.8 W / (m·K).

[0227] 3. Surface emissivity test:

[0228] The radiation intensity of a building exterior wall material sample and a standard blackbody at 25℃ was measured using an infrared thermal imager, and the surface emissivity ε was calculated to be 0.85.

[0229] 4. Stress intensity factor test:

[0230] A 30mm pre-existing crack was prepared on a standard specimen of the main load-bearing component of the building. A three-point bending test was conducted, and the crack propagation length 'a' and load data 'P' during loading were recorded. The stress intensity factor was then calculated. for

[0231] 5. Stress cycle test:

[0232] Fatigue loading tests were conducted on the material samples of the main load-bearing components of the building, and the number of cyclic loading N of the samples under a stress level of 80MPa was recorded as 5×10^5.

[0233] 6. Damage threshold test:

[0234] Cyclic loading tests were conducted on material samples of the main load-bearing components of the building. The crack initiation process was monitored using acoustic emission sensors. The stress level at which the first acoustic emission signal was detected was recorded as 60 MPa, which is the damage threshold σ. th .

[0235] The test results of the above structural material performance parameters are shown in Table 2:

[0236] Table 2 Test results of structural material performance parameters

[0237]

[0238] With abundant multimodal monitoring data and structural material performance parameters, the next step is to analyze the correlations between them in order to establish a mathematical model describing the health status of the building structure. Here, a Bayesian network method is used for analysis, and the specific steps are as follows:

[0239] 1. First, establish a node network that includes various monitoring data and material performance parameters, such as vibration response, strain distribution, temperature field distribution, acoustic emission characteristics, deformation characteristics, structural stiffness, thermal conductivity, emissivity, etc.

[0240] 2. Based on historical monitoring sample data, calculate the conditional probability distribution P(E|H) and prior probability distribution P(H) between each node using the maximum likelihood estimation method.

[0241] 3. Using Bayes' theorem The posterior probability distribution is obtained.

[0242] 4. Finally, calculate the correlation coefficient between any two nodes based on the posterior probability. Construct a multimodal data association matrix.

[0243] The above analysis revealed the correlation between various monitoring data and structural performance parameters, laying the foundation for the subsequent establishment of a health status assessment model.

[0244] Based on the obtained multimodal monitoring data and structural performance parameters, a mathematical model describing the health status of the high-rise residential building was then established. Specifically, this includes:

[0245] 1. Vibration response equation:

[0246]

[0247] In the formula, M is the mass matrix; C is the damping matrix; K is the stiffness matrix; u is the displacement vector; and F(t) is the external excitation force vector. Through experimental modal analysis, the first five natural frequencies of the building were extracted to be 0.85 Hz.

[0248] The damping ratios for 1.35Hz, 2.05Hz, 3.15Hz, and 4.25Hz are 2.5%, 3.0%, 3.5%, 4.0%, and 4.5%, respectively.

[0249] 2. Strain distribution equation:

[0250] ε total =ε elastic +ε plastic +ε thermal ;

[0251]

[0252] ε plastic =Kσ 0.3 ;

[0253] ε thermal =1.2×10 -5 ΔT;

[0254] In the formula, ε total For total strain; ε elastic For elastic strain; ε plastic For plastic strain; ε thermalσ represents thermal strain; E represents the elastic modulus at 3.5 GPa; K represents the strength coefficient at 550 MPa; and ΔT represents the temperature change. Based on fiber optic strain monitoring data, the maximum strain value of the main load-bearing components of the building was calculated to be 650 microstrain.

[0255] 3. Temperature field distribution equation:

[0256]

[0257] In the formula, ρ is the density of 2300 kg / m²; c is the specific heat capacity of 840 J / (kg·K); λ is the thermal conductivity of 0.8 W / (m·K); q v Internal heat source; q r ε is the radiative heat flux density; ε is the emissivity of 0.85; σ is the Stefan-Boltzmann constant; T s The surface temperature of the exterior wall; T e The ambient temperature is represented by TAI, which is the Temperature Anomaly Index, calculated from monitoring data to have a maximum value of 0.15.

[0258] 4. Acoustic emission characteristic equation:

[0259]

[0260] In the formula, L is the positioning matrix; (x s ,y s ,z s (x) represents the coordinates of the sound source; i ,y i ,z i ) represents the coordinates of the i-th sensor; v is the sound wave propagation speed of 4500 m / s; t i t0 represents the arrival time; t0 represents the occurrence time; DI represents the damage index. Based on acoustic emission monitoring data, the acoustic emission damage index DI for the building in the crack-prone area was calculated to be 18.

[0261] 5. Structural deformation equation:

[0262]

[0263] In the formula, δ is the displacement and tilt angle vector; K is a 6×6 stiffness matrix, calculated based on monitoring data; F and M are the force and moment vectors, respectively; DI d The value of the deformation index is 0.12, calculated from the monitoring data.

[0264] 6. Crack propagation equation:

[0265]

[0266] ΔK=K max -Kmin ;

[0267] In the formula, a is the crack length; N is the number of cycles; ΔK is the stress intensity factor amplitude; K max K is the maximum stress intensity factor. IC for The fracture toughness is σ; stress is F(a / W); and geometric correction factor is F(a / W). Based on monitoring data and material performance parameters, the crack propagation rate of the main load-bearing components of the building is predicted to be 0.01 mm / 10,000 cycles under a stress level of 80 MPa.

[0268] 7. Damage accumulation equation:

[0269]

[0270] In the formula, D is the cumulative damage value; n i N represents the actual number of iterations. i To allow for a certain number of loops; a c The critical crack length is 30 mm; σ i For stress level; K I This is the stress intensity factor. Based on the above parameters, it is predicted that the cumulative damage value of the building will reach the critical value of 0.8 within 5 years under a stress level of 80MPa.

[0271] Combining the above analytical equations forms a comprehensive assessment model describing the health status of the high-rise residential building. Using this model, the following comprehensive assessment indicators were calculated:

[0272] 1. The damage location index DI = 18 indicates that the building has a certain degree of damage in the crack-prone area.

[0273] 2. The Temperature Anomaly Index (TAI) = 0.15, indicating that there are relatively serious local temperature anomalies in certain areas of the building.

[0274] 3. Deformation Index (DI) d =0.12, indicating that the overall risk of deformation of the building is low and it is in a safe state.

[0275] 4. The cumulative damage index D = 0.6, indicating that the building will reach the critical damage value of 0.8 within the next 5 years and will require repair and reinforcement.

[0276] It should be noted that the variables involved in the description of this invention are explained as shown in Table 3 below:

[0277] Table 3. Variable Explanation Table

[0278]

[0279]

[0280] The above description is only a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed by the present invention, which should be covered by the scope of protection of the present invention.

Claims

1. A method for structural health detection of buildings based on multimodal data, characterized in that, Includes the following steps: S10. Deploy a multimodal sensor array to collect multimodal monitoring data of the building structure. The multimodal monitoring data includes vibration monitoring data, fiber optic strain monitoring data, acoustic emission signal data, temperature field monitoring data, and deformation monitoring data. S20. Preprocess the multimodal monitoring data; S30. Conduct material performance tests, establish a database of building structure material parameters, and obtain building structure performance test data; S40. The correlation between the multimodal monitoring data and the performance test data is calculated using a Bayesian network to obtain a multimodal data correlation matrix. Specifically, this includes: first, establishing the nodes and edges of the Bayesian network, where the nodes include various monitoring data and material performance parameters, and the edges represent the causal relationships between the data; then, based on historical monitoring sample data, the conditional probability distribution between each node is calculated using the maximum likelihood estimation method to obtain the posterior probability; finally, the correlation coefficient between any two nodes is calculated based on the posterior probability to construct a multimodal data correlation matrix, which can characterize the coupling effect of various factors in a complex system and lay the foundation for establishing a health status assessment model. S50. Select the corresponding functional relationship from the preset combination of relational functions to establish a set of equations for the health status of the building structure. S60. Fit the set of equations for the health status of the building structure using historical monitoring data to obtain the fitted structural health assessment model. S70. Using the fitted structural health assessment model, damage location identification data, temperature anomaly index data, deformation degree index data, and cumulative damage index data are calculated. S80. Generate a building structure health status assessment report based on the damage location identification data, the temperature anomaly index data, the deformation degree index data, and the cumulative damage index data. The set of equations for the health status of the building structure includes vibration response equation, strain distribution equation, acoustic emission characteristic equation, temperature field distribution equation, crack propagation equation, structural deformation equation, and damage accumulation equation. The vibration response equation inputs include vibration frequency, mode shape data, and damping ratio data, and outputs structural modal parameters. The strain distribution equation takes into account the corrected fiber strain data and structural stiffness data as inputs, and outputs structural strain distribution data as output. The acoustic emission characteristic equation inputs include acoustic emission amplitude data, acoustic emission frequency data, acoustic emission duration data, and acoustic emission energy data, and outputs damage location identification data. The temperature field distribution equation takes as input surface temperature data, ambient temperature data, material thermal conductivity data, and surface emissivity data, and outputs temperature anomaly index data. The input to the crack propagation equation includes the structural strain distribution data and stress intensity factor data, and the output is crack propagation rate data. The structural deformation equation inputs include displacement data, tilt angle data, and settlement data, and the output is deformation degree index data. The damage accumulation equation takes stress cycle count data, damage threshold data, and crack propagation rate data as inputs and outputs cumulative damage index data.

2. The method for detecting the structural health of a building based on multimodal data according to claim 1, characterized in that, The vibration monitoring data includes vibration frequency, mode shape data, and damping ratio data.

3. The method for detecting the structural health of a building based on multimodal data according to claim 2, characterized in that, The fiber optic strain monitoring data includes fiber optic strain data and sensor temperature data.

4. The method for detecting the structural health of a building based on multimodal data according to claim 3, characterized in that, The acoustic emission signal data includes acoustic emission amplitude data, acoustic emission frequency data, acoustic emission duration data, and acoustic emission energy data.

5. The method for detecting the structural health of a building based on multimodal data according to claim 4, characterized in that, The temperature field monitoring data includes surface temperature data and ambient temperature data.

6. The method for detecting the structural health of a building based on multimodal data according to claim 5, characterized in that, The deformation monitoring data includes displacement data, tilt angle data, and settlement data.

7. The method for detecting the structural health of a building based on multimodal data according to claim 6, characterized in that, The preprocessing of the multimodal monitoring data specifically includes: The vibration monitoring data is processed, including noise reduction of the vibration frequency, the mode shape data, and the damping ratio data. The fiber optic strain monitoring data is processed, including temperature compensation of the fiber optic strain data using the sensor temperature data to obtain corrected fiber optic strain data. The acoustic emission signal data is processed, including waveform feature extraction of the acoustic emission amplitude data, acoustic emission frequency data, acoustic emission duration data, and acoustic emission energy data; The temperature field monitoring data is processed, including temperature correction of the surface temperature data using the ambient temperature data. The deformation monitoring data is processed, including benchmarking the displacement data, tilt angle data, and settlement data.

8. The method for detecting the structural health of a building based on multimodal data according to claim 7, characterized in that, The structural performance test data of the building includes structural stiffness data, material thermal conductivity data, surface emissivity data, stress intensity factor data, stress cycle count data, and damage threshold data.

9. A method for detecting the structural health of a building based on multimodal data according to claim 8, characterized in that, The combination of relational functions includes at least linear, exponential, logarithmic, and power functions.

Images