A method for controlling the evolution trend of acoustic emission simulation signals

Abstract

The present invention discloses a method for regulating the evolution trend of an acoustic emission simulation signal, which relates to the field of non-destructive testing of composite materials. The method first obtains an actual acoustic emission signal and screens out a signal of a specific damage pattern through a fast Fourier transform (FFT); then, the collected acoustic emission signal is subjected to wavelet packet denoising, and then a representative acoustic emission signal is extracted as a target signal using principal component analysis (PCA); then, a BP neural network model is constructed for training to predict the envelope of the acoustic emission signal; the optimal fitting model is selected for envelope fitting by comparing the R-square value; the mutation point is determined by a threshold and sliding window technique, and a specific curve segment of the optimal fitting model is intercepted; finally, the optimal loading evolution trend regulation time point is selected through a weighted evaluation of the root mean square error (RMSE) and the characteristic frequency change value. In response to the problem that the acoustic emission signal simulated by finite element simulation does not match the actual signal, the present invention proposes a method for regulating the evolution trend of an acoustic emission signal, corrects the simulated signal, effectively improves the accuracy, and realizes trend matching between the composite material acoustic emission simulation signal and the actual signal.

Description

Technical Field

[0001] The invention belongs to the field of acoustic emission nondestructive testing, and in particular relates to a method for regulating the evolution trend of an acoustic emission simulation signal. Background Art

[0002] Glass fiber reinforced plastics (GFRP) have been widely used in key fields such as aerospace, petrochemicals, and automobiles due to their high specific strength and fatigue corrosion resistance. During use, composite materials are subjected to various complex stresses and environmental factors for a long time, and are prone to damage such as matrix cracking, fiber breakage, and delamination. If these damages are not discovered and treated in time, they may lead to serious accidents such as blade breakage and container rupture, which will not only cause huge economic losses, but also endanger the lives of people. If the damage can be monitored and assessed in time, a maintenance or replacement plan can be formulated in time to reduce economic losses. Among the various existing detection methods, acoustic emission technology has good application prospects in structural health monitoring due to its advantages such as dynamic monitoring, high sensitivity, and strong real-time performance.

[0003] In actual processes, the characteristic frequency bands of acoustic emission signals generated by different materials and different types of damage are different. For each material, a large number of damage experiments need to be carried out in advance to determine the various types of damage characteristics. This is not only time-consuming and labor-intensive, but also inefficient. Obtaining acoustic emission signals with different damage characteristics through finite element simulation can greatly reduce work intensity and improve work efficiency.

[0004] However, finite element simulation cannot directly incorporate attenuation changes when acquiring acoustic emission signals, which leads to significant differences between the simulated signals and the actual signals. The acoustic emission signals do not attenuate and show a trend of infinitely increasing amplitude, which seriously deviates from the actual monitoring situation, thus affecting the accuracy and reliability of monitoring. Summary of the Invention

[0005] To solve the above technical problems, the present invention provides a method for controlling the evolution trend of an acoustic emission simulation signal, which is used to correct the acoustic emission simulation signal to achieve trend matching with the actual acoustic emission signal, specifically:

[0006] Step 1: Obtain the actual acoustic emission signal, filter out the signal of the specific damage pattern through fast Fourier transform (FFT), and perform wavelet packet noise reduction processing to remove noise interference and improve signal quality;

[0007] Step 2: Use principal component analysis (PCA) to obtain the target signal, build a BP neural network model, train the neural network, and predict the envelope of the acoustic emission signal;

[0008] Step 3: Fit the predicted envelope and compare the R-squared value to ensure the effectiveness of the fitting model;

[0009] Step 4: Use threshold and sliding window technology to detect the mutation points of the simulated signal and the actual signal;

[0010] Step 5: Match the sampling rates of the simulated signal and the actual acoustic emission signal, apply the fitting model, and intercept the attenuation curve segment for subsequent evolution trend control;

[0011] Step 6: A comprehensive evaluation method using a weighted evaluation of the root mean square error (RMSE) between the signal after trend control and the actual signal and the change in the characteristic frequency before and after processing is used to determine the starting time of the evolution trend control and to control the evolution trend of the acoustic emission simulation signal with infinite increase characteristics.

[0012] Compared to existing technologies, this invention addresses the problem of acoustic emission signals acquired through finite element simulations, which fail to account for signal attenuation, leading to significant discrepancies between simulated and actual signals. This method proposes a method for controlling the evolution trend of simulated acoustic emission signals. A BP neural network is constructed to predict the signal envelope, fit the envelope, and extract attenuation curve segments. Combining a weighted evaluation of the root mean square error (RMS) and the change in characteristic frequency, the optimal time point for load evolution trend control is automatically selected to achieve evolution trend control of the acoustic emission signal. The proposed method is effective and feasible, with a high degree of signal matching. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] By describing in detail the embodiments shown in conjunction with the accompanying drawings, the drawings described below are only some embodiments of the present invention. In the drawings:

[0014] Figure 1 The overall flow chart of a method for controlling the evolution trend of acoustic emission simulation signals is as follows;

[0015] Figure 2 This is the constructed BP neural network training graph;

[0016] Figure 3 is the regression coefficient graph of BP neural network;

[0017] Figure 4 Normalized envelope diagram: (a) actual acoustic emission signal envelope; (b) predicted acoustic emission signal envelope

[0018] Figure 5 It is a comparison chart of different fitting models and prediction envelopes;

[0019] Figure 6 It is a histogram of R-squared values ​​of different fitting models;

[0020] Figure 7This is the simulated signal diagram of acoustic emission for matrix damage;

[0021] Figure 8 This is the acoustic emission signal diagram of matrix damage obtained in the experiment;

[0022] Figure 9 This is the simulated signal diagram of acoustic emission of matrix damage after evolution trend control;

[0023] Figure 10 Spectrum diagram of acoustic emission simulation signal before and after processing; DETAILED DESCRIPTION

[0024] The present invention is further explained below with reference to the accompanying drawings and specific embodiments. The present invention proposes a method for controlling the evolution trend of acoustic emission simulation signals. Figure 1 The following is a flowchart of this method. After acquiring the actual acoustic emission signal, a fast Fourier transform (FFT) is used to filter out signals with specific damage patterns. After wavelet packet noise reduction, principal component analysis (PCA) is used to extract the target signal. A BP neural network is constructed to predict the envelope, and the envelope is fitted. A threshold and sliding window technique are used to determine the mutation point, and the attenuation curve segment of the optimal fitting model is intercepted. The root mean square error and characteristic frequency weighted evaluation are used to determine the starting time for evolution trend control. Evolution trend control is then applied to the simulated acoustic emission signal to achieve trend matching with the actual acoustic emission signal.

[0025] The design and fabrication of the prefabricated composite pressure vessel laminate [45°] specimen in this example was based on GB / T 1446-2005, General Rules for Testing Methods of Fiber-Reinforced Plastics. The specimen had a 45° layup, seven layers, and dimensions of 100 mm in length, 100 mm in width, and 5 mm in thickness.

[0026] The prepared laminate [45°] layup specimen was mounted on a universal testing machine, with the support roller length set to 40 mm. An acoustic emission sensor was placed on the upper edge of the specimen to collect the acoustic emission signal throughout the bending process. The sensor was 40 mm from the center and coupled and secured using a special coupling agent. The sensor was then connected to an amplifier with a designed amplifier parameter of 40 dB. The acoustic emission acquisition parameters were adjusted as shown in Table 1.

[0027] Table 1 Acoustic emission acquisition parameter settings

[0028] Parameter name Parameter value Threshold 45dB Preamplifier gain 45dB Sampling rate 1MSPS(1MHz) Filter range 1KHz~500KHz

[0029] After the acoustic emission equipment was prepared, bending loading was then initiated at a rate of 1 mm / min. Simultaneously, acoustic emission sensors were used to monitor the acoustic emission signals generated throughout the tensile process. The tensile machine was stopped until the specimen broke.

[0030] All acoustic emission signals obtained in the experiment were processed by fast Fourier transform (FFT) to obtain acoustic emission signals with characteristic frequencies falling between 20kHz and 60kHz (i.e., acoustic emission signals of matrix damage), and a data set was obtained for the BP neural network.

[0031] Select dB5 as the wavelet basis function and decompose it into 4 layers, and then use the universal threshold method to calculate the threshold: Where σ is the standard deviation of noise, N is the signal length, and then the coefficients smaller than the threshold are set to zero to perform noise reduction. Finally, the retained significant coefficients are used for inverse transformation to obtain the denoised signal.

[0032] The obtained multiple groups of noise-reduced acoustic emission signals are organized into a matrix X, where each row represents a sample and each column represents a time point, and the data is centered. Calculate the covariance matrix: Then, the eigenvalues ​​and eigenvectors of the covariance matrix are solved to obtain the projection values ​​of all signals on the first principal component, and the signal with the largest projection in the direction of the first principal component is selected as the target signal.

[0033] The denoised acoustic emission signal is subjected to Hilbert transform to obtain the analytical signal, and the absolute value of the analytical signal is taken to obtain the envelope, and the envelope amplitude is normalized.

[0034] Set the number of hidden layers to 18, and then set the transfer function. The hidden layer uses the tansig hyperbolic tangent S-type function, the output layer uses the purelin linear function, and the Levenberg-Marquardt (trainlm) algorithm. Divide 70% into a training set, 15% into a validation set, and 15% into a test set. The parameter settings are as follows: Figure 2 As shown in the figure, the maximum number of training rounds is set to 500, the maximum number of verification failures is set to 6, and the initial value of the learning rate is 0.01. The entire training process is as follows: the input data is the preprocessed envelope, the target output is the target signal selected by principal component analysis (PCA), the network weights are adjusted by back propagation, and the predicted envelope is obtained by using the trained network for prediction. Finally, Figure 3 The regression coefficient shown is used to evaluate the training effect. If the regression coefficient is lower than 0.9, the training is repeated. The predicted results after training are as follows Figure 4 shown.

[0035] Fitting is performed on the obtained prediction envelope, including polynomial fitting, sine fitting, Fourier fitting, Gaussian fitting and rational function fitting, such as Figure 5 As shown, the polynomial fitting tried polynomials of order 1-10, and the R square values ​​of these five fitting models were compared, as shown in Figure 6 As shown, the best fitting model is selected.

[0036] The signal mutation point is detected by threshold and sliding window technology, and the acoustic emission simulation signal is imported ( Figure 7 ) and actual acoustic emission signal data ( Figure 8 ) A smoothed analog signal and actual signal are obtained through moving average filtering and low-pass filtering. The dynamic threshold is calculated by multiplying the standard deviation of the smoothed signal by the set amplitude mutation threshold. The signal change is calculated and the absolute value array of the change is traversed using a sliding window method. The first point that exceeds the dynamic threshold is the mutation point. If the analog signal does not detect a mutation point, fault tolerance is implemented by halving the dynamic threshold and re-detecting the mutation point.

[0037] Calculate the ratio of the actual signal's mutation point to the total signal length and extract the corresponding data segment from the simulated signal. Linearly interpolate and resample the actual signal to match the sampling rate of the simulated signal. Intercept the normalized fitting model from its maximum value to the model endpoint as the decay curve segment for subsequent evolution trend control.

[0038] The weight of the root mean square error (RMSE) is set to 0.7, and the weight of the frequency change is set to 0.3. Attempt to load the attenuation curve segment at different positions of the simulated signal for evolution trend control. After each application, calculate the RMSE of the actual signal and the frequency characteristic changes before and after processing. Combine these two indicators through weights to form a comprehensive evaluation score. The lower the score, the better the control effect. After traversing all possible starting positions, select the position with the lowest score as the optimal time starting point for evolution trend control. The evolution control results are as follows: Figure 9 As shown in the figure, the influence of evolution trend control on the original acoustic emission simulation signal is Figure 10 It can be determined from the figure that the evolution trend control does not change the characteristic frequency of the acoustic emission signal and does not affect the characteristic identification of the damage pattern.

[0039] Finally, it is necessary to point out here that the above-mentioned specific embodiments of the present invention are only used to illustrate or explain the principles of the present invention, and do not constitute a limitation of the present invention. Some non-essential improvements and adjustments made by those skilled in the art based on the above-mentioned contents of the present invention are within the scope of protection of the present invention.

Claims

1. A method for controlling the evolution trend of an acoustic emission simulation signal, characterized in that: The method comprises the following steps: Step 1: Obtain the actual acoustic emission signal, filter out the signal of the specific damage pattern through fast Fourier transform (FFT), and perform wavelet packet noise reduction processing to remove noise interference and improve signal quality. The specific steps are as follows: Step 1.1: Perform a three-point bending test on the composite laminate and use an acoustic emission sensor to collect acoustic emission signals during the loading process; Step 1.2: Perform fast Fourier transform (FFT) on the collected acoustic emission signal to extract the acoustic emission signal of the characteristic frequency of the specific damage pattern; Step 1.3: Perform wavelet packet denoising on all collected acoustic emission signals, set dB5 as the wavelet basis function and decompose it into 4 layers, and use the universal threshold method to calculate the threshold: Where σ represents the standard deviation of noise, N is the signal length, and then the coefficients smaller than the threshold are set to zero to complete the noise reduction operation. Finally, the inverse transform is performed using the retained significant coefficients to obtain the denoised signal. Step 2: Use principal component analysis (PCA) to obtain the target signal, build a BP neural network model, train the neural network, and predict the envelope of the acoustic emission signal; Step 3: Fit the predicted envelope and compare the R-squared value to ensure the effectiveness of the fitting model; Step 4: Use threshold and sliding window technology to detect the mutation points of the simulated signal and the actual signal; Step 5: Match the sampling rates of the simulated and actual acoustic emission signals, apply the fitting model, and intercept the attenuation curve segment for subsequent evolution trend control; Step 6: A comprehensive evaluation method using a weighted evaluation of the root mean square error (RMSE) between the signal after trend control and the actual signal and the change in the characteristic frequency before and after processing is used to determine the starting time of the evolution trend control and to control the evolution trend of the acoustic emission simulation signal with infinite increase characteristics.

2. The method for controlling the evolution trend of an acoustic emission simulation signal according to claim 1, wherein: In step 2, the principal component analysis (PCA) method is used to obtain the target signal, build a BP neural network model, train the neural network, and predict the acoustic emission signal envelope. The specific steps are as follows: Step 2.1: Arrange the denoised acoustic emission signals into a matrix X, where each row corresponds to a sample and each column corresponds to a time point. After centering the data, calculate the covariance matrix: Where n is the number of rows in the matrix X. Then, the eigenvalues ​​and eigenvectors of the covariance matrix are solved to obtain the projection values ​​of all signals on the first principal component, and the signal with the largest projection in the direction of the first principal component is selected as the target signal; Step 2.2: Use Hilbert transform to transform the denoised acoustic emission signal to obtain the analytical signal. Then, take the absolute value of the analytical signal to obtain the envelope, and normalize the envelope amplitude. Step 2.3: Construct a BP neural network, set the number of hidden layer nodes to 18, configure the transfer function, use the tansig hyperbolic tangent sigmoid function for the hidden layer, and the purelin linear function for the output layer. Use the Levenberg-Marquardt (trainlm) algorithm for training, divide the signal into a 70% training set, a 15% validation set, and a 15% test set. Set the maximum number of training rounds to 500, the maximum number of validation failures to 6, and the initial learning rate to 0.

01. Step 2.4: Take the envelope as input and the target signal selected by principal component analysis (PCA) as output, adjust the network weights through the back propagation algorithm, train the network and obtain the predicted envelope.

3. The method for controlling the evolution trend of an acoustic emission simulation signal according to claim 1, wherein: In step 3, the predicted envelope is fitted, and the effect of the fitting model is ensured by comparing the R square value. The specific steps are as follows: Step 3.1: Based on the predicted envelope obtained in step 2, use 1st to 10th order polynomial fitting, sine fitting, Fourier fitting, Gaussian fitting, and rational function fitting respectively; Step 3.2: Compare and analyze the R-squared values ​​of the fitted models and select the best fitting model.

4. The method for controlling the evolution trend of an acoustic emission simulation signal according to claim 1, wherein: In step 4, a threshold and sliding window technique are used to detect the mutation points of the simulated signal and the actual signal. The specific steps are as follows: Step 4.1: Obtain smoothed analog and actual signals through moving average filtering and low-pass filtering. Calculate the dynamic threshold by multiplying the standard deviation of the smoothed signal by the set amplitude mutation threshold. Step 4.2: Calculate the change in the signal and use the sliding window method to traverse the absolute value array of the change. The first point that is greater than the dynamic threshold is the mutation point. If the simulation signal does not detect the mutation point, fault tolerance processing is performed, the dynamic threshold is halved, and the mutation point is re-detected.

5. The method for controlling the evolution trend of an acoustic emission simulation signal according to claim 1, wherein: In step 5, the sampling rates of the simulated signal and the actual acoustic emission signal are matched, the fitting model is applied, and the attenuation curve segment is intercepted for subsequent evolution trend control. The specific steps are as follows: Step 5.1: Calculate the ratio of the actual signal mutation point position to the total signal length, and extract the corresponding data segment from the simulated signal; Step 5.2: Perform linear interpolation sampling on the actual signal to match the sampling rate of the analog signal; Step 5.3: Perform amplitude normalization on the simulated signal and the actual signal. In the normalized fitting model, the interval from the maximum point to the end point of the model is intercepted as the attenuation curve segment for subsequent evolution trend control.

6. The method for controlling the evolution trend of an acoustic emission simulation signal according to claim 1, wherein: In step 6, a comprehensive evaluation method of weighted evaluation of the root mean square error (RMSE) between the trend-controlled signal and the actual signal and the change in the characteristic frequency before and after processing is adopted to determine the starting time of the evolution trend control, and to control the evolution trend of the acoustic emission simulation signal with infinite increase characteristics. The specific steps are as follows: Step,6.1: Set the weight of root mean square error (RMSE) to 0.7 and the weight of frequency change to 0.3; Step 6.2: Use the attenuation curve segments to control the evolution trend at different locations of the simulated signal. Calculate the RMSE after each control and the change in frequency characteristics before and after the treatment. Combine these two indicators according to the weights to form a comprehensive evaluation score. The lower the score, the better the control effect. Step 6.3: After traversing all possible starting positions, select the position with the lowest score as the optimal evolution trend control time starting point to control the simulation signal of infinitely increasing characteristics.

Images