A bridge crack expansion assessment method and system based on acoustic emission signals

Abstract

The present invention belongs to the technical field of bridge beam monitoring and discloses a bridge crack expansion assessment method and system based on acoustic emission signals. The method comprises: deploying an acoustic emission sensor array at a preset position of the bridge to collect original acoustic emission signals within a preset time period; using a bandpass filter to obtain filtered acoustic emission signals, and using empirical mode decomposition technology to separate the filtered acoustic emission signals to obtain effective acoustic emission signals; using time-frequency transformation to transform the effective acoustic emission signals to obtain a signal time-frequency graph; constructing a crack expansion assessment model to obtain crack expansion rate and severity level; obtaining crack spatial positioning results through crack spatial positioning; and performing weighted fusion on the crack expansion rates and severity levels of J sensors, combining the results with the spatial positioning results with a bridge model to present them in three dimensions. The present invention can obtain more accurate crack locations.

Description

Technical Field

[0001] The present invention relates to the technical field of bridge beam monitoring, and more particularly to a bridge crack propagation assessment method and system based on acoustic emission signals. Background Art

[0002] Traditional bridge inspection methods, such as visual inspection, ultrasonic testing, and strain gauge measurement, have limitations in crack detection. Visual inspection relies on the inspector's experience and subjective judgment, making it difficult to detect small cracks or those hidden within the structure. Ultrasonic testing requires manual point-by-point scanning, resulting in low efficiency and limited effectiveness for complex structures. Strain gauge measurement primarily detects stress changes in the structure and is ineffective for early detection and assessment of crack expansion.

[0003] Patent application publication number CN117607266A discloses a bridge beam crack monitoring method and system based on acoustic emission: Step S1: Install an acoustic emission signal acquisition device, specifically, the acoustic emission signal acquisition device includes an acoustic emission sensor and an acquisition control unit, and at least two acoustic emission monitoring lines are arranged on the bridge beam along the length direction of the bridge beam. The acoustic emission monitoring lines are provided with multiple acoustic emission sensors, and all acoustic emission sensors are located on the plane below the bridge beam and are arranged in series with the acquisition control unit; Step S2: Position the acoustic emission sensors, specifically, construct a plane rectangular coordinate system and number each acoustic emission sensor, The coordinates of each acoustic emission sensor are measured based on the plane rectangular coordinate system. Step S3: Monitoring the bridge beam. Specifically, the acoustic emission sensors collect the acoustic emission ring count, acoustic emission energy, and signal acquisition time to determine whether the bridge beam is at risk of cracking. If so, the process proceeds to Step S4. Step S4: Locating the acoustic emission source. Specifically, based on the acoustic emission ring count and acoustic emission energy, multiple acoustic emission sensors near the acoustic emission source are identified. Based on the signal acquisition time, the time difference between the acoustic emission elastic wave reaching the acoustic emission source detected by these multiple acoustic emission sensors is calculated. The horizontal and vertical coordinates of the acoustic emission source are then calculated using the acoustic emission source calculation formula. This technical solution enables full-section monitoring and precise location of cracks in bridge beams, and also provides an early warning function. Workers can view online data in real time to prevent structural safety accidents.

[0004] Although the above methods can meet most scenarios, research and practical application of the above methods and existing technologies have revealed that the above methods and existing technologies have at least the following defects:

[0005] The quantitative assessment of crack growth rate and the classification of severity levels are not perfect, making it impossible to further clarify the crack growth rate in the future and the specific impact of the crack on the safety of the beam structure. The crack monitoring results are only presented in the form of data reports or simple two-dimensional graphics, which lack intuitiveness and integrity, making it difficult for users to quickly understand and grasp the overall situation of bridge cracks.

[0006] In view of this, the present invention proposes a bridge crack propagation assessment method and system based on acoustic emission signals to solve the above problems. Summary of the Invention

[0007] In order to overcome the above-mentioned defects of the prior art, the present invention provides the following technical solution: a bridge crack propagation assessment method based on acoustic emission signals, comprising the following steps:

[0008] An acoustic emission sensor array is deployed at a preset location on the bridge to collect original acoustic emission signals within a preset period of time;

[0009] A bandpass filter is used to remove low-frequency environmental noise and high-frequency sensor interference from the original acoustic emission signal to obtain a filtered acoustic emission signal. The filtered acoustic emission signal is separated using the empirical mode decomposition technique to obtain an effective acoustic emission signal.

[0010] Use time-frequency transformation to transform the effective acoustic emission signal and obtain the signal time-frequency diagram;

[0011] A crack growth assessment model was constructed, using the signal time-frequency diagram as input to obtain the crack growth rate and corresponding severity level. The crack growth assessment model includes a feature extraction network and an improved Paris crack growth model.

[0012] The crack growth rates and severity levels of J sensors are weighted and fused to obtain weighted crack growth rates and severity levels. The weighted crack growth rates and severity levels are then combined with the bridge model and presented in three-dimensional form.

[0013] Furthermore, the method further includes: monitoring the original acoustic emission signal through a multi-channel sensor to perform spatial positioning of the crack to obtain a spatial positioning result of the crack; combining the spatial positioning result of the crack with the bridge model to present the result in a three-dimensional form;

[0014] The method for obtaining the crack spatial positioning result comprises:

[0015] Step A: Calculate the time difference Δt between the original acoustic emission signal and any two sensors u and v uv , use the time difference positioning formula to locate the crack source:

[0016] Step B: Based on the time difference Δtuv Construct a probability distribution model of crack positions and obtain the results of crack spatial positioning;

[0017] Methods for obtaining crack spatial positioning results include:

[0018] Step B1: Obtain the crack source located in step A to obtain the crack position (x, y);

[0019] Step B2: Obtain the corresponding value range [x min ,y min ]×[x max ,y max ], where x min is the minimum lateral position of the crack on the bridge; y min is the minimum longitudinal position of the crack in the bridge; x max is the maximum transverse position of the crack on the bridge; max is the maximum longitudinal position of the crack in the bridge; obtain the corresponding prior probability distribution

[0020] Step B3: Calculate all values ​​of the crack position (x, y) according to the time difference positioning formula; for the crack position (x, y), the time difference Δt uv Obey the normal distribution and calculate the corresponding time difference Δt uv Likelihood function Among them, σ uv is the time difference Δt uv The standard deviation of the measurement error; e is a mathematical constant; is the actual observed time difference; is the theoretical time difference calculated based on the crack position (x, y); based on the L group time difference Δt uv (u, v = 1, 2, ..., L, u ≠ v) Calculate the total likelihood function P (Δt | x, y) = Π u≠v P ( Δt uv |x,y);

[0021] Step B4: Integrate all crack positions (x, y) to obtain crack position evidence P(Δt) = ∫∫P(Δt|x, y)P(x, y)dxdy; where P(Δt) is the crack position evidence, i.e., the integral value obtained by integrating all crack positions (x, y);

[0022] Step B5: Calculate the posterior probability distribution corresponding to the crack position (x, y) according to the Bayesian formula to obtain a crack position probability distribution model, and take the position corresponding to the maximum value of the posterior probability distribution in the crack position probability distribution model as the crack spatial positioning result.

[0023] Furthermore, the method for obtaining the crack growth rate and the corresponding severity level includes:

[0024] Step 1.1: Build a feature extraction network based on a convolutional neural network. The feature extraction network includes an input layer, n1 convolutional layers, n2 pooling layers, a self-attention module, a fully connected layer, and an output layer. Use the signal time-frequency graph as the input of the feature extraction network to obtain the output feature vector. The convolutional layer and the pooling layer are used to extract the local time-frequency features of the signal time-frequency graph to obtain the feature graph R. In the self-attention module, the feature graph R obtained after the convolutional layer and the pooling layer is linearly transformed to obtain the query matrix Q, the key matrix K, and the value matrix V. The attention score Score is calculated based on the query matrix Q, the key matrix K, and the value matrix V. The attention output is obtained by multiplying the attention score by the value matrix.

[0025] Step 1.2, obtain the stress intensity factor range based on the eigenvector;

[0026] Step 1.3: Calculate the crack growth rate based on the improved Paris crack growth model, compare the crack growth rate with the crack growth rate interval corresponding to the preset growth severity level, and obtain the corresponding severity level.

[0027] Furthermore, the method of obtaining the query matrix Q, key matrix K and value matrix V includes:

[0028] Q=R·W Q ;

[0029] K=R·W K ;

[0030] V=R·W V ;

[0031] Among them, W Q 、W K and W V are the weight matrices corresponding to the query matrix Q, key matrix K, and value matrix V respectively;

[0032] The method for obtaining the attention score Score includes:

[0033]

[0034] Among them, μ k is the dimension of the key matrix K; T is the transpose of the vector; softmax is the normalized mapping function;

[0035] The method for obtaining the attention output includes:

[0036] A=Score×V;

[0037] Among them, A is the attention output.

[0038] Furthermore, the method for obtaining the stress intensity factor range includes:

[0039] Step 2.1, obtain the historical eigenvector and the corresponding stress intensity factor;

[0040] Step 2.2: Establish a nonlinear model of historical eigenvectors and corresponding stress intensity factors;

[0041] Step 2.3, fitting the nonlinear model based on the historical eigenvectors and the corresponding historical stress intensity factor range, and optimizing with the goal of minimizing the residual sum of squares to obtain corresponding nonlinear model parameter values, and substituting the corresponding nonlinear model parameter values ​​into the nonlinear model to obtain a fitted nonlinear model;

[0042] Step 2.4: Use the eigenvector as the input of the fitted nonlinear model to obtain the corresponding minimum stress intensity factor and maximum stress intensity factor, and use the difference between the maximum stress intensity factor and the minimum stress intensity factor as the stress intensity factor range.

[0043] Furthermore, the method for obtaining the improved Paris crack propagation model includes:

[0044] A correction coefficient corresponding to the Paris crack propagation model is obtained based on the compressive strength, elastic modulus and crack width of bridge concrete. A fatigue test data set consisting of test values ​​within a stress intensity factor range is obtained. The fatigue crack propagation rate corresponding to each stress intensity factor test value in the fatigue test data set is obtained. The first material constant C, second material constant m and correction coefficient in the improved Paris crack propagation model are fitted using the least squares method. The Paris crack propagation model is corrected based on the fitted first material constant C, second material constant m and correction coefficient to obtain an improved Paris crack propagation model.

[0045] Furthermore, the method for obtaining an effective acoustic emission signal includes:

[0046] Step 3.1, determining a local extreme point by comparing the size relationship between each data point in the filtered acoustic emission signal and the corresponding two adjacent data points. If the data point is larger than the corresponding two adjacent data points, the data point is a local maximum point; conversely, if the data point is smaller than the corresponding two adjacent data points, the data point is a local minimum point;

[0047] Step 3.2: Connect all local maximum points to form the upper envelope bl max(τ), τ is time; connect all local minimum points to form the lower envelope bl min (τ);

[0048] Step 3.3, calculate the average value of the upper envelope and the lower envelope Calculate the difference between the filtered acoustic emission signal g(τ) and the average value m(τ) to obtain a difference signal h(τ)=g(τ)-m(τ); where g(τ) is the filtered acoustic emission signal;

[0049] Step 3.4: Check whether the difference signal h(τ) satisfies the IMF condition; if not, use the difference signal h(τ) as the new filtered first acoustic emission signal, and repeat steps 3.1 to 3.3 until the IMF condition is met to obtain the first IMF; if so, directly obtain the first IMF and mark it as c1(τ);

[0050] Step 3.5: Subtract the first IMF c1(τ) from the filtered acoustic emission signal g(τ) to obtain a first residual signal r1(τ)=g(τ)-c1(τ);

[0051] Step 3.6: Use the first residual signal r1(τ) as the new filtered second acoustic emission signal, repeat step 3.4 to obtain the second IMF, mark the second IMF as c2(τ), and repeat step 3.5 to calculate the second residual signal r2(τ)=r1(τ)-c2(τ);

[0052] Step 3.7, repeat step 3.6 until the residual component When it becomes a monotonic function or the number of extreme points does not exceed two, the decomposition process ends; the filtered acoustic emission signal g(τ) is expressed as Among them, c i (τ) is IMF; is the residual component; n g is the number of IMFs into which the filtered acoustic emission signal g(τ) is divided;

[0053] Step 3.8: Perform fast Fourier transform on each IMF to obtain the corresponding spectrum range. Extract the IMF as the effective component according to the preset effective signal frequency range, and reconstruct the effective component to obtain the useful signal g. eff (τ)=∑ i∈S c i (τ), where S is the index set of IMF containing effective components; the useful signal g eff (τ)=∑ i∈S c i (τ) is taken as the effective acoustic emission signal.

[0054] Furthermore, the IMF conditions include: within the entire data segment of the acoustic emission signal, the number of extreme points and the number of zero-crossing points must be equal or differ by at most one; at any data point, the average value of the upper envelope and the lower envelope defined by the local maximum point and the local minimum point is zero.

[0055] Furthermore, the method for obtaining a signal time-frequency diagram includes:

[0056] Step 4.1: The effective acoustic emission signal g eff (τ) is divided into d small frames, and the length of each frame is n fft , frame shift is hop length ,

[0057] Step 4.2: Apply a preset window function w(τ) to each frame of valid acoustic emission signal;

[0058] Step 4.3, applying a fast Fourier transform to each frame of valid acoustic emission signals after applying the preset window function w(τ), converting the time domain signal of each frame of valid acoustic emission signals after applying the preset window function w(τ) into a frequency domain signal, and combining the frequency domain signals to obtain a spectrum matrix;

[0059] The method for obtaining the spectrum matrix comprises:

[0060] Construct a spectrum matrix framework in which the rows correspond to the number of signal frames of the effective acoustic emission signal and the columns correspond to the number of frequency points of the effective acoustic emission signal;

[0061] Fill the fast Fourier transform result of each frame of effective acoustic emission signal into the spectrum matrix frame to obtain the spectrum matrix;

[0062] Step 4.4: Based on the amplitude values ​​of the elements in the spectrum matrix representing the intensity of the signal time-frequency diagram, that is, the pixel values ​​corresponding to the signal time-frequency diagram, map the time in the spectrum matrix to the horizontal axis of the signal time-frequency diagram, and map the frequency in the spectrum matrix to the vertical axis of the signal time-frequency diagram. According to the intensity of the signal time-frequency diagram, map each element value in the spectrum matrix to the corresponding position of the signal time-frequency diagram to obtain the signal time-frequency diagram.

[0063] Furthermore, the method for obtaining the weighted crack growth rate and severity level includes:

[0064] The weighted crack growth rate of J sensors is obtained by weighting the crack growth rate Among them, α k is the crack growth rate of the kth sensor; w 1,k is α kCorresponding weights; weight the severity levels of J sensors to obtain the weighted severity level Among them, β k is the severity level of the kth sensor; w 2,k is α k The corresponding weight.

[0065] A bridge crack propagation assessment system based on acoustic emission signals, used to implement the bridge crack propagation assessment method based on acoustic emission signals, comprising:

[0066] Data acquisition module: an acoustic emission sensor array is deployed at a preset location on the bridge to collect the original acoustic emission signal within a preset period of time;

[0067] Preprocessing module: Use bandpass filter to remove low-frequency environmental noise and high-frequency sensor interference from the original acoustic emission signal to obtain filtered acoustic emission signal. Use empirical mode decomposition technology to separate the filtered acoustic emission signal to obtain effective acoustic emission signal.

[0068] Feature extraction module: Use time-frequency transformation to transform the effective acoustic emission signal to obtain the signal time-frequency diagram;

[0069] Extension Assessment Module: This module constructs a crack extension assessment model, uses the signal time-frequency diagram as input, and obtains the crack extension rate and corresponding severity level. The crack extension assessment model includes a feature extraction network and an improved Paris crack extension model.

[0070] Crack location module: Use multi-channel sensors to monitor the original acoustic emission signals to locate the crack space and obtain the crack space location results;

[0071] Visualization module: The crack growth rate and severity level of J sensors are weighted and fused to obtain the weighted crack growth rate and severity level. The weighted crack growth rate, weighted severity level and spatial positioning results are combined with the bridge model and presented in three-dimensional form.

[0072] The technical effects and advantages of the bridge crack expansion assessment method and system based on acoustic emission signals of the present invention are as follows:

[0073] The present invention comprehensively considers factors related to crack expansion, conducts in-depth analysis of acoustic emission signals, and combines physical models to more comprehensively evaluate information such as crack expansion rate and severity level, thereby more accurately grasping the development dynamics of cracks and the degree of impact on bridge structures. It also obtains accurate spatial positioning results based on the time difference positioning formula combined with the crack position probability distribution model, and improves positioning accuracy and robustness through a weighted fusion mechanism of multi-channel sensors to obtain more accurate crack locations. At the same time, the probability distribution positioning method can take into account the uncertainty in the positioning process and provide the probability distribution of cracks at different locations, further improving the reliability of positioning. The crack expansion degree, severity level and spatial positioning results are also combined with the bridge model to intuitively display the crack distribution and trend in three-dimensional form, making the evaluation results more intuitive and easy to understand, facilitating bridge management and maintenance personnel to quickly obtain key information and make decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Figure 1 This is a flow chart of a bridge crack propagation assessment method based on acoustic emission signals according to the present invention;

[0075] Figure 2 A schematic flow chart of the method for obtaining crack growth rate and severity level according to the present invention;

[0076] Figure 3 A schematic flow chart of a method for obtaining a stress intensity factor range according to the present invention;

[0077] Figure 4 This is a block diagram of a bridge crack expansion assessment system based on acoustic emission signals according to the present invention;

[0078] Figure 5 This is a schematic diagram of the interface of a bridge crack extension assessment system based on acoustic emission signals according to the present invention. DETAILED DESCRIPTION

[0079] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0080] Example 1

[0081] See also Figure 1 As shown, the bridge crack propagation assessment method based on acoustic emission signals described in this embodiment includes the following steps:

[0082] Acoustic emission sensor arrays are deployed at pre-set locations on the bridge to collect raw acoustic emission signals over a pre-set time period. When cracks develop on the bridge, tiny acoustic emission signals are generated. By deploying sensor arrays at pre-set locations, these weak signals can be captured, enabling early detection of cracks. This facilitates further analysis of the crack growth rate, severity level, and spatial location of the cracks, helping to promptly identify potential safety hazards and effectively prevent further crack expansion and structural damage.

[0083] A bandpass filter is used to remove the low-frequency environmental noise and high-frequency sensor interference of the original acoustic emission signal to obtain the filtered acoustic emission signal. The empirical mode decomposition technology is used to separate the filtered acoustic emission signal to obtain the effective acoustic emission signal.

[0084] By using a bandpass filter to process the original signal, the optimal passband frequency range of the bandpass filter can be selected according to the frequency characteristics of the original acoustic emission signal, and noise and interference components outside the passband frequency range can be removed. The signal can be filtered quickly and accurately without introducing additional distortion or delay, which helps to improve the accuracy of subsequent analysis of the crack growth rate, severity level and spatial positioning results of the bridge.

[0085] Methods for obtaining effective acoustic emission signals include:

[0086] The local extreme point is determined by comparing the size relationship between each data point in the filtered acoustic emission signal and the corresponding two adjacent data points. If the data point is larger than the corresponding two adjacent data points, the data point is a local maximum point; conversely, if the data point is smaller than the corresponding two adjacent data points, the data point is a local minimum point.

[0087] Connect all local maximum points to form the upper envelope bl max (τ), τ is time; connect all local minimum points to form the lower envelope bl min (τ).

[0088] Calculate the average value of the upper and lower envelopes The difference between the filtered acoustic emission signal g(τ) and the average value m(τ) is calculated to obtain a difference signal h(τ)=g(τ)-m(τ); wherein g(τ) is the filtered acoustic emission signal.

[0089] Check whether the difference signal h(τ) meets the IMF condition (in the entire data segment of the acoustic emission signal, the number of extreme points and the number of zero-crossing points must be equal or differ by at most one; at any data point, the average value of the upper envelope and the lower envelope defined by the local maximum point and the local minimum point is zero); if not, use the difference signal h(τ) as the new filtered first acoustic emission signal until the IMF condition is met to obtain the first IMF; if it is met, directly obtain the first IMF and mark the first IMF as c1(τ).

[0090] The first IMF c1(τ) is subtracted from the filtered acoustic emission signal g(τ) to obtain a first residual signal r1(τ)=g(τ)-c1(τ).

[0091] The first residual signal r1(τ) is used as the new filtered second acoustic emission signal, and step 4 is repeated to obtain the second IMF, which is marked as c2(τ). The second residual signal r2(τ)=r1(τ)-c2(τ) is calculated.

[0092] Until the residual When it becomes a monotonic function or the number of extreme points does not exceed two, the decomposition process ends; the filtered acoustic emission signal g(τ) is expressed as Among them, c i (τ) is IMF; is the residual component; n g is the number of IMFs into which the filtered acoustic emission signal g(τ) is divided.

[0093] Perform fast Fourier transform on each IMF to obtain the corresponding spectrum range, extract the IMF as the effective component according to the preset effective signal frequency range, and reconstruct the effective component to obtain the useful signal g eff (τ)=∑ i∈S c i (τ), where S is the index set of IMF containing effective components; the useful signal g eff (τ)=∑ i∈S c i (τ) is taken as the effective acoustic emission signal.

[0094] The effective acoustic emission signal is transformed using time-frequency transformation to obtain the signal time-frequency diagram.

[0095] Methods for obtaining signal time-frequency diagrams include:

[0096] The effective acoustic emission signal g eff (τ) is divided into d small frames, and the length of each frame is n fft , frame shift is hop length ,

[0097] A preset window function w(τ) is applied to each frame of valid acoustic emission signal.

[0098] Fast Fourier transform is applied to each frame of valid acoustic emission signal after applying the preset window function w(τ), and the time domain signal of each frame of valid acoustic emission signal after applying the preset window function w(τ) is converted into a frequency domain signal. The frequency domain signals are combined to obtain a spectrum matrix, which represents the intensity and phase of the signal in time and frequency; wherein the row represents time and the column represents frequency.

[0099] Construct a spectrum matrix framework in which the rows correspond to the number of signal frames of the effective acoustic emission signal and the columns correspond to the number of frequency points of the effective acoustic emission signal;

[0100] The fast Fourier transform result of each frame of effective acoustic emission signal is filled into the spectrum matrix frame to obtain the spectrum matrix.

[0101] Based on the amplitude value of the elements in the spectrum matrix representing the intensity of the signal time-frequency diagram, that is, the pixel value corresponding to the signal time-frequency diagram, the time in the spectrum matrix is ​​mapped to the horizontal axis of the signal time-frequency diagram, and the frequency in the spectrum matrix is ​​mapped to the vertical axis of the signal time-frequency diagram. According to the intensity of the signal time-frequency diagram, each element value in the spectrum matrix is ​​mapped to the corresponding position of the signal time-frequency diagram to obtain the signal time-frequency diagram.

[0102] A crack propagation assessment model is constructed, and the signal time-frequency diagram is used as the input of the crack propagation assessment model to obtain the crack propagation rate and severity level; the crack propagation assessment model includes a feature extraction network and the Paris crack propagation model.

[0103] Reference Figure 2 , the methods for obtaining the crack growth rate and the corresponding severity level include:

[0104] A feature extraction network is built based on a convolutional neural network. The feature extraction network includes an input layer, n1 convolutional layers, n2 pooling layers, a self-attention module, a fully connected layer, and an output layer. The signal time-frequency diagram is used as the input of the feature extraction network to obtain the output feature vector. The convolutional layer and the pooling layer are used to extract local time-frequency features to obtain the feature map R. In the self-attention module, the feature map R obtained after the convolutional layer and the pooling layer is linearly transformed to obtain the query matrix Q, the key matrix K, and the value matrix V. The attention score Score is calculated based on the query matrix Q, the key matrix K, and the value matrix V. The attention output is obtained by multiplying the attention score with the value matrix. The self-attention module can capture the global characteristics of the signal and enhance the model's ability to identify crack expansion characteristics.

[0105] Methods for obtaining the query matrix Q, the key matrix K, and the value matrix V include:

[0106] Q=R·W Q ;

[0107] K=R·W K ;

[0108] V=R·W V ;

[0109] Among them, W Q 、W K and W V are the weight matrices corresponding to the query matrix Q, key matrix K, and value matrix V respectively.

[0110] The methods for obtaining the attention score Score include:

[0111]

[0112] Among them, μ k is the dimension of the key matrix K; T is the transpose of the vector; softmax is the normalized mapping function.

[0113] Methods for obtaining attention output include:

[0114] A=Score×V;

[0115] Among them, A is the attention output.

[0116] The stress intensity factor range is obtained based on the eigenvector.

[0117] Reference Figure 3 , methods for obtaining the range of stress intensity factors include:

[0118] Step 2.1: Obtain the historical eigenvector and the corresponding stress intensity factor.

[0119] Step 2.2: Establish a nonlinear model between the historical eigenvectors and the corresponding stress intensity factors.

[0120] Methods for building nonlinear models include:

[0121]

[0122] Where D is the stress intensity factor; is the model parameter; n a is the highest order eigenvector; X is the eigenvector.

[0123] Step 2.3: Fit the above nonlinear model based on the historical eigenvector and the corresponding historical stress intensity factor, and optimize it with the goal of minimizing the residual sum of squares to obtain the corresponding model parameter values. Substitute the corresponding model parameter values ​​into the nonlinear model to obtain the fitted nonlinear model.

[0124] Step 2.4: Use the eigenvector as the input of the fitted nonlinear model to obtain the corresponding minimum stress intensity factor and maximum stress intensity factor, and use the difference between the maximum stress intensity factor and the minimum stress intensity factor as the stress intensity factor range.

[0125] The corresponding correction coefficient is obtained according to the compressive strength, elastic modulus and crack width of the bridge concrete.

[0126]

[0127] in, is the compressive strength correction factor; kc is the compressive coefficient, which reflects the degree of influence of compressive strength on crack expansion; f c0 is the baseline compressive strength; nc is the compressive index; f c is the compressive strength;

[0128]

[0129] Among them, β E is the elastic modulus correction coefficient; E0 is the reference elastic modulus; E is the elastic modulus;

[0130] β cw =1+k cw ×cw;

[0131] Among them, β cw is the crack width correction coefficient; cw is the crack width; k cw is the crack width coefficient, which reflects the influence of crack width on the acceleration of crack expansion;

[0132] An improved Paris crack propagation model is obtained based on the correction coefficient;

[0133] The improved Paris crack propagation model is as follows:

[0134]

[0135] Where a is the crack length; Y is the number of cycles; α is the crack growth rate, that is, the length of the crack growth per cycle; ΔK is the stress intensity factor range, and C and m are both material constants. The material constant C is used to reflect the ability of the bridge material to resist fatigue crack growth, and the material constant m is used to characterize the degree of influence of the stress intensity factor range on the fatigue crack growth rate.

[0136] A fatigue test data set consisting of test values ​​within a range of stress intensity factors is obtained, and the fatigue crack growth rate corresponding to each stress intensity factor test value in the fatigue test data set is obtained. The first material constant C, the second material constant m, and the correction coefficient in the improved Paris crack growth model are fitted using the least squares method; and the Paris crack growth model is corrected based on the fitted first material constant C, the second material constant m, and the correction coefficient to obtain an improved Paris crack growth model.

[0137] The crack growth rate in the bridge is calculated based on the stress intensity factor range, the fitted first material constant C, and the fitted second material constant m. The crack growth rate is calculated using the improved Paris crack growth model and compared with the crack growth rate range corresponding to preset growth severity levels (such as mild, moderate, and severe) to obtain the corresponding severity level.

[0138] The crack spatial positioning result is obtained by monitoring the original acoustic emission signal through a multi-channel sensor.

[0139] Methods for obtaining crack spatial positioning results include:

[0140] Calculate the time difference Δt between the original acoustic emission signal and any two sensors u and v uv , use the time difference positioning formula to locate the crack source:

[0141]

[0142] Where (x, y) is the crack position, and x and y correspond to the horizontal and vertical positions of the crack on the bridge, respectively; is the sound wave propagation speed; (x1, y1) and (x2, y2) are the coordinates of the first sensor and the second sensor, respectively. x1 and y1 correspond to the lateral position and longitudinal position of the first sensor on the bridge, respectively. x2 and y2 correspond to the lateral position and longitudinal position of the second sensor on the bridge, respectively.

[0143] The crack location probability distribution model is constructed based on the time difference Δt of the original acoustic emission signal arriving at different sensors to obtain the crack spatial positioning result.

[0144] Methods for constructing a crack location probability distribution model include:

[0145] The crack position (x, y) is obtained according to the located crack source.

[0146] According to the crack position (x, y), the corresponding value range [x min ,y min ]×[x max ,y max ], where xmin is the minimum lateral position of the crack on the bridge; y min is the minimum longitudinal position of the crack in the bridge; x max is the maximum transverse position of the crack on the bridge; max is the maximum longitudinal position of the crack on the bridge; obtain the corresponding prior probability distribution P(x,y).

[0147] Methods for obtaining the corresponding prior probability distribution P(x,y) include:

[0148]

[0149] All values ​​of the crack position (x, y) are calculated according to the time difference positioning formula; for the crack position (x, y), the time difference Δt uv Obey the normal distribution and calculate the corresponding time difference Δt uv Likelihood function P(Δt uv |x,y) is:

[0150]

[0151] Among them, σ uv is the time difference Δt uv The standard deviation of the measurement error; e is a mathematical constant; is the actual observed time difference; is the theoretical time difference calculated based on the crack position (x, y).

[0152] Based on L groups of time difference Δt uv (u, v = 1, 2, ..., L, u ≠ v) The total likelihood function P(Δt|x, y) is calculated as follows:

[0153] P(Δt|x,y)=Π u≠v P ( Δt uv |x,y);

[0154] The crack location evidence is obtained by integrating all crack locations (x, y).

[0155] Methods for obtaining evidence of crack location include:

[0156] P(Δt)=∫∫P(Δt|x,y)P(x,y)dxdy;

[0157] Where P(Δt) is the crack position evidence, that is, the integral value obtained by integrating all crack positions (x, y).

[0158] The posterior probability distribution corresponding to the crack position (x, y) is calculated according to the Bayesian formula to obtain the crack position probability distribution model. The position corresponding to the maximum value of the posterior probability distribution in the crack position probability distribution model is taken as the crack spatial positioning result.

[0159] The Bayesian formula is as follows:

[0160]

[0161] Where P(x,y|Δt) is the posterior probability distribution corresponding to the crack location (x,y).

[0162] The crack growth rates and severity levels of J sensors are weighted and fused to obtain weighted crack growth rates and weighted severity levels. The weighted crack growth rates, weighted severity levels, and spatial positioning results are combined with the bridge model and presented in three-dimensional form, which can intuitively display the crack distribution and trends.

[0163] Methods for obtaining weighted crack growth rates and severity levels include:

[0164] The weighted crack growth rate of J sensors is obtained by weighting the crack growth rate Among them, α k is the crack growth rate of the kth sensor; w 1,k is α k Corresponding weight. Weight the severity levels of J sensors to obtain the weighted severity level Among them, β k is the severity level of the kth sensor; w 2,k is α k The corresponding weight. Weight w 1,k 、w 2,k and w 3,k It can be determined based on the signal-to-noise ratio and reliability of the acoustic propagation signal.

[0165] Example 2

[0166] See also Figure 4-Figure 5 As shown, the bridge crack propagation assessment system based on acoustic emission signals described in this embodiment includes:

[0167] Data acquisition module: an acoustic emission sensor array is deployed at a preset location on the bridge to collect the original acoustic emission signal within a preset period of time;

[0168] Preprocessing module: Use bandpass filter to remove low-frequency environmental noise and high-frequency sensor interference from the original acoustic emission signal to obtain filtered acoustic emission signal. Use empirical mode decomposition technology to separate the filtered acoustic emission signal to obtain effective acoustic emission signal.

[0169] Feature extraction module: Use time-frequency transformation to transform the effective acoustic emission signal to obtain the signal time-frequency diagram;

[0170] Extension assessment module: Build a crack extension assessment model, use the signal time-frequency diagram as input to obtain the crack extension rate and the corresponding severity level; the crack extension assessment model includes a feature extraction network and a Pars crack extension model;

[0171] Crack location module: Use multi-channel sensors to monitor the original acoustic emission signals to locate the crack space and obtain the crack space location results;

[0172] Visualization module: The crack growth rate and severity level of J sensors are weighted and fused to obtain the weighted crack growth rate and severity level. The weighted crack growth rate, weighted severity level and spatial positioning results are combined with the bridge model and presented in three-dimensional form.

[0173] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

[0174] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A bridge crack expansion assessment method based on acoustic emission signals, characterized in that: The steps include: An acoustic emission sensor array is deployed at a preset location on the bridge to collect original acoustic emission signals within a preset period of time; A bandpass filter is used to remove low-frequency environmental noise and high-frequency sensor interference from the original acoustic emission signal to obtain a filtered acoustic emission signal. The filtered acoustic emission signal is separated using the empirical mode decomposition technique to obtain an effective acoustic emission signal. Use time-frequency transformation to transform the effective acoustic emission signal and obtain the signal time-frequency diagram; A crack growth assessment model was constructed, and the signal time-frequency diagram was used as input to obtain the crack growth rate and the corresponding severity level. The crack propagation assessment model includes a feature extraction network and an improved Paris crack propagation model; The crack growth rates and severity levels of J sensors are weighted and fused to obtain weighted crack growth rates and severity levels. The weighted crack growth rates and severity levels are combined with the bridge model and presented in three-dimensional form. The method for obtaining the improved Paris crack propagation model includes: A correction coefficient corresponding to the Paris crack growth model is obtained based on the compressive strength, elastic modulus, and crack width of the bridge concrete. A fatigue test data set consisting of test values ​​within a stress intensity factor range is obtained. The fatigue crack growth rate corresponding to each stress intensity factor test value in the fatigue test data set is obtained. The first material constant C, the second material constant m, and the correction coefficient in the improved Paris crack growth model are fitted using the least squares method. The Paris crack growth model is corrected based on the fitted first material constant C, the second material constant m, and the correction coefficient to obtain an improved Paris crack growth model. The method for obtaining a signal time-frequency diagram comprises: Step 4.1, dividing the effective acoustic emission signal into d small frames, with the frame shift being half of the preset length of each frame; Step 4.2: Apply a preset window function w(τ) to each frame of valid acoustic emission signal; Step 4.3: Apply fast Fourier transform to each frame of valid acoustic emission signal after applying the preset window function w(τ), convert the time domain signal of each frame of valid acoustic emission signal after applying the preset window function w(τ) into a frequency domain signal, and combine the frequency domain signals to obtain a spectrum matrix.

2. The bridge crack propagation assessment method based on acoustic emission signals according to claim 1 is characterized in that: The method further includes: monitoring the original acoustic emission signal by a multi-channel sensor to perform spatial positioning of the crack, obtaining a spatial positioning result of the crack, and combining the spatial positioning result of the crack with the bridge model to present the result in a three-dimensional form; The method for obtaining the crack spatial positioning result comprises: Step A: Calculate the time difference Δt between the original acoustic emission signal and any two sensors u and v uv , use the time difference positioning formula to locate the crack source: Step B: Based on the time difference Δt uv Construct a probability distribution model of crack positions and obtain the results of crack spatial positioning; Methods for obtaining crack spatial positioning results include: Step B1: Obtain the crack source located in step A to obtain the crack position (x, y); Step B2: Obtain the corresponding value range [x min ,y min ]×[x max ,y max ], where x min is the minimum lateral position of the crack on the bridge; y min is the minimum longitudinal position of the crack in the bridge; x max is the maximum transverse position of the crack on the bridge; max is the maximum longitudinal position of the crack in the bridge; obtain the corresponding prior probability distribution; Step B3: Calculate all values ​​of the crack position (x, y) according to the time difference positioning formula; for the crack position (x, y), the time difference Δt uv Obey the normal distribution and calculate the corresponding time difference Δt uv Likelihood function based on L groups of time differences Δt uv (u, v = 1, 2, ..., L, u ≠ v) calculate the total likelihood function; Step B4: Integrate all crack positions (x, y) to obtain crack position evidence; Step B5: Calculate the posterior probability distribution corresponding to the crack position (x, y) according to the Bayesian formula to obtain a crack position probability distribution model, and take the position corresponding to the maximum value of the posterior probability distribution in the crack position probability distribution model as the crack spatial positioning result.

3. The bridge crack propagation assessment method based on acoustic emission signals according to claim 1 is characterized in that: The method for obtaining the crack growth rate and the corresponding severity level includes: Step 1.1: Build a feature extraction network based on a convolutional neural network. The feature extraction network includes an input layer, n1 convolutional layers, n2 pooling layers, a self-attention module, a fully connected layer, and an output layer. Use the signal time-frequency graph as the input of the feature extraction network to obtain the output feature vector. The convolutional layer and the pooling layer are used to extract the local time-frequency features of the signal time-frequency graph to obtain the feature graph R. In the self-attention module, the feature graph R obtained after the convolutional layer and the pooling layer is linearly transformed to obtain the query matrix Q, the key matrix K, and the value matrix V. The attention score Score is calculated based on the query matrix Q, the key matrix K, and the value matrix V. The attention output is obtained by multiplying the attention score by the value matrix. Step 1.2, obtain the stress intensity factor range based on the eigenvector; Step 1.3: Calculate the crack growth rate based on the improved Paris crack growth model, compare the crack growth rate with the crack growth rate interval corresponding to the preset growth severity level, and obtain the corresponding severity level.

4. The bridge crack propagation assessment method based on acoustic emission signals according to claim 3 is characterized in that: The method for obtaining the stress intensity factor range includes: Step 2.1, obtain the historical eigenvector and the corresponding stress intensity factor; Step 2.2: Establish a nonlinear model of historical eigenvectors and corresponding stress intensity factors: Step 2.3, fitting the nonlinear model based on the historical eigenvectors and the corresponding historical stress intensity factor range, and optimizing with the goal of minimizing the residual sum of squares to obtain corresponding nonlinear model parameter values, and substituting the corresponding nonlinear model parameter values ​​into the nonlinear model to obtain a fitted nonlinear model; Step 2.4: Use the eigenvector as the input of the fitted nonlinear model to obtain the corresponding minimum stress intensity factor and maximum stress intensity factor, and use the difference between the maximum stress intensity factor and the minimum stress intensity factor as the stress intensity factor range.

5. The bridge crack propagation assessment method based on acoustic emission signals according to claim 1 is characterized in that: The method for obtaining an effective acoustic emission signal comprises: Step 3.1, determining a local extreme point by comparing the size relationship between each data point in the filtered acoustic emission signal and the corresponding two adjacent data points. If the data point is larger than the corresponding two adjacent data points, the data point is a local maximum point; conversely, if the data point is smaller than the corresponding two adjacent data points, the data point is a local minimum point; Step 3.2: Connect all local maximum points to form the upper envelope bl max (τ), τ is time; connect all local minimum points to form the lower envelope bl min (τ); Step 3.3, calculate the average value m(τ) of the upper envelope and the lower envelope, and calculate the difference between the filtered acoustic emission signal g(τ) and the average value m(τ) to obtain the difference signal h(τ); Step 3.4: Check whether the difference signal h(τ) satisfies the IMF condition; if not, use the difference signal h(τ) as the new filtered first acoustic emission signal, and repeat steps 3.1 to 3.3 until the IMF condition is met to obtain the first IMF; if so, directly obtain the first IMF and mark it as c1(τ); Step 3.5, subtract c1(τ) from the filtered acoustic emission signal g(τ) to obtain a first residual signal r1(τ); Step 3.6: Use the first residual signal r1(τ) as the new filtered second acoustic emission signal, repeat step 3.4 to obtain the second IMF, mark the second IMF as c2(τ), and repeat step 3.5 to calculate the second residual signal r2(τ); Step 3.7, repeat step 3.6 until the residual component When it becomes a monotonic function or the number of extreme points does not exceed two, the decomposition process ends; the filtered acoustic emission signal g(τ) is expressed as a g The form of the IMF and residual components; Step 3.8: Perform fast Fourier transform on each IMF to obtain the corresponding spectrum range. Extract the IMF as the effective component according to the preset effective signal frequency range, and reconstruct the effective component to obtain the useful signal g. eff (τ), the useful signal g eff (τ) is taken as the effective acoustic emission signal.

6. The bridge crack propagation assessment method based on acoustic emission signals according to claim 5, characterized in that: The IMF conditions include: within the entire data segment of the acoustic emission signal, the number of extreme points and the number of zero-crossing points must be equal or differ by at most one; at any data point, the average value of the upper envelope and the lower envelope defined by the local maximum point and the local minimum point is zero.

7. The bridge crack propagation assessment method based on acoustic emission signals according to claim 5, characterized in that: The method for obtaining the spectrum matrix comprises: Construct a spectrum matrix framework in which the rows correspond to the number of signal frames of the effective acoustic emission signal and the columns correspond to the number of frequency points of the effective acoustic emission signal; Fill the fast Fourier transform result of each frame of effective acoustic emission signal into the spectrum matrix frame to obtain the spectrum matrix; Step 4.4: Based on the amplitude values ​​of the elements in the spectrum matrix representing the intensity of the signal time-frequency diagram, that is, the pixel values ​​corresponding to the signal time-frequency diagram, map the time in the spectrum matrix to the horizontal axis of the signal time-frequency diagram, and map the frequency in the spectrum matrix to the vertical axis of the signal time-frequency diagram. According to the intensity of the signal time-frequency diagram, map each element value in the spectrum matrix to the corresponding position of the signal time-frequency diagram to obtain the signal time-frequency diagram.

8. The bridge crack propagation assessment method based on acoustic emission signals according to claim 1, characterized in that: The method for obtaining the weighted crack growth rate and severity level includes: Weighting the crack growth rates of J sensors to obtain a weighted crack growth rate; The severity levels of the J sensors are weighted to obtain a weighted severity level.

9. A bridge crack extension assessment system based on acoustic emission signals, used to implement the bridge crack extension assessment method based on acoustic emission signals according to any one of claims 1 to 8, characterized in that: include: Data acquisition module: an acoustic emission sensor array is deployed at a preset location on the bridge to collect the original acoustic emission signal within a preset period of time; Preprocessing module: Use bandpass filter to remove low-frequency environmental noise and high-frequency sensor interference from the original acoustic emission signal to obtain filtered acoustic emission signal. Use empirical mode decomposition technology to separate the filtered acoustic emission signal to obtain effective acoustic emission signal. Feature extraction module: Use time-frequency transformation to transform the effective acoustic emission signal to obtain the signal time-frequency diagram; Extension Assessment Module: This module constructs a crack extension assessment model, uses the signal time-frequency diagram as input, and obtains the crack extension rate and corresponding severity level. The crack extension assessment model includes a feature extraction network and an improved Paris crack extension model. Crack location module: Use multi-channel sensors to monitor the original acoustic emission signals to locate the crack space and obtain the crack space location results; Visualization module: The crack growth rate and severity level of J sensors are weighted and fused to obtain the weighted crack growth rate and severity level. The weighted crack growth rate, weighted severity level and spatial positioning results are combined with the bridge model and presented in three-dimensional form.

Images