Acoustic emission monitoring data acquisition and processing method for pressure-bearing special equipment

Abstract

The invention relates to the technical field of electrical digital data processing, in particular to a pressure-bearing special equipment acoustic emission monitoring data acquisition and processing method, which comprises the following steps of: determining IMF segmented signals of original acoustic wave signals emitted by pressure-bearing special equipment; determining the signal truth degree and the distortion degree of the IMF segmented signal; determining a reference frequency curve and an abnormal frequency curve by using the distortion degree and the frequency spectrum curve; determining the equipment defect significance of the pressure-bearing special equipment by using the reference frequency curve, the abnormal frequency curve and the frequency peak value; determining the reconstruction importance of the IMF component signal by using the correlation between the original sound wave signal and the IMF segment signal and the equipment defect saliency; and determining the IMF component signal which needs to be removed or reserved by using the reconstruction importance so as to reconstruct the original sound wave signal. According to the method, noise signals are removed more accurately, defect signals of pressure-bearing special equipment are reserved more accurately, and the accuracy degree of noise reduction and reconstruction of the acoustic emission signals is improved.

Description

Technical Field

[0001] The invention relates to the technical field of electric digital data processing, and in particular to a method for collecting and processing acoustic emission monitoring data of pressure-bearing special equipment. Background Art

[0002] At present, online detection and monitoring technologies for pressure-bearing special equipment are very scarce. Common detection methods such as X-ray, ultrasound, and infrared imaging have problems such as high cost, offline testing, and great environmental impact. They cannot realize online monitoring of damage that occurs during the operation of pressure-bearing special equipment. Therefore, it is particularly important to monitor the safety status of pressure-bearing special equipment in a timely manner. Acoustic emission detection technology can monitor the overall structural defects of pressure-bearing special equipment, and has been maturely applied to regular offline detection of pressure-bearing special equipment to determine the defect status.

[0003] However, due to the complexity of on-site monitoring noise, the collected signal components are complex, and the equipment defect signal and environmental noise signal are mixed in the original sound wave signal. It is difficult to effectively extract and identify the equipment defect signal, and the reliability of system monitoring and early warning is not high. At present, the detection methods used for pressure-bearing special equipment are mostly offline detection, which has low detection efficiency and high cost. In addition, the signal processing methods used remain in traditional methods such as wavelet denoising and Fourier transform, which are not ideal for signal noise reduction and cannot truly reflect the equipment defect signal. Although the vmd (Variational Mode Decomposition) method can achieve a certain degree of denoising, due to the complexity of the noise, the reconstructed sound wave signal still cannot accurately reflect the actual structural defects of pressure-bearing special equipment. Since both the noise signal and the equipment defect signal appear as abnormal signals in the original sound wave signal, the noise signal is an interference signal and needs to be excluded in the reconstruction, while the equipment defect signal needs to be retained in the reconstruction process. It is difficult for various current noise reduction methods to distinguish between noise signals and equipment defect signals, resulting in low accuracy of defect detection of pressure-bearing special equipment in the reconstructed sound wave signal. Summary of the invention

[0004] In order to solve the technical problem that it is difficult to distinguish the noise signal from the equipment defect signal in the acoustic wave signal, resulting in low accuracy of defect detection for pressure-bearing special equipment in the reconstructed acoustic wave signal, the purpose of the present invention is to provide a method for collecting and processing acoustic emission monitoring data for pressure-bearing special equipment. The technical scheme adopted is as follows: The present invention provides a method for collecting and processing acoustic emission monitoring data of pressure-bearing special equipment, the method comprising: Determine the IMF component signal of the original sound wave signal emitted by the pressure-bearing special equipment and the IMF segmented signal divided therefrom; Determine the signal authenticity of the IMF segmented signal, and use the signal authenticity to determine the distortion degree of the IMF segmented signal; Using the distortion degree and spectrum curve of the IMF segmented signal, the corresponding reference frequency curve and abnormal frequency curve are determined; Determine the significance of equipment defects of pressure-bearing special equipment by using the reference frequency curve, abnormal frequency curve and their corresponding frequency peaks; The importance of reconstructing the IMF component signals is determined by using the correlation between the original acoustic wave signal and the IMF segmented signal and the significance of the equipment defects. The reconstruction importance is used to determine the IMF component signals that need to be removed or retained to reconstruct the original sound wave signal.

[0005] Further, the determining of the signal authenticity of the IMF segmented signal includes: Get the RMS and average signal levels of the IMF segmented signal; Using the RMS and average signal levels, the signal authenticity is calculated.

[0006] Further, the method of determining the distortion degree of the IMF segmented signal by using the signal authenticity degree includes: Determine the difference in signal authenticity between each IMF segment signal; The distortion degree of IMF segmented signal is determined by using the difference in the true degree of the signal.

[0007] Further, the use of the distortion degree and the spectrum curve of the IMF segmented signal to determine the corresponding reference frequency curve and the abnormal frequency curve includes: Determine an IMF segment normal signal and an IMF segment abnormal signal corresponding to the IMF segment signal; The reference frequency curve of the IMF component signal is calculated by using the distortion degree and spectrum curve of the IMF segmented normal signal; The abnormal frequency curve of the IMF component signal is calculated using the distortion degree and spectrum curve of the IMF segmented abnormal signal.

[0008] Further, the determining of the IMF segment normal signal and the IMF segment abnormal signal corresponding to the IMF segment signal includes: Input the IMF segmented signal into the box plot to obtain the corresponding IMF segmented normal signal and IMF segmented abnormal signal; The IMF segmented normal signal and the IMF segmented abnormal signal are respectively subjected to short-time Fourier transform to obtain a frequency spectrum curve of the IMF segmented normal signal and a frequency spectrum curve of the IMF segmented abnormal signal.

[0009] Furthermore, the use of the reference frequency curve and the abnormal frequency curve and their corresponding frequency peaks to determine the significance of equipment defects of the pressure-bearing special equipment includes: Determining the degree of deformation between the reference frequency curve and the abnormal frequency curve with respect to the frequency distribution; The significance of equipment defects of pressure-bearing special equipment is calculated by using the frequency peaks and deformation degrees corresponding to the reference frequency curve and the abnormal frequency curve.

[0010] Further, the determining of the degree of deformation between the reference frequency curve and the abnormal frequency curve with respect to the frequency distribution includes: Determine a reference frequency bandwidth of a reference frequency curve and a frequency segment interval into which the reference frequency bandwidth is divided; Determine the difference in cumulative amount between the reference frequency curve and the abnormal frequency curve in each same frequency segment interval; The difference between each cumulative amount is used to determine the degree of deformation of the reference frequency curve and the abnormal frequency curve in the frequency distribution.

[0011] Furthermore, the use of the frequency peaks and deformation degrees corresponding to the reference frequency curve and the abnormal frequency curve to calculate the significance of equipment defects of the pressure-bearing special equipment includes: Obtaining first total maximum values ​​corresponding to the reference frequency curve and the abnormal frequency curve respectively; Determine the fitting curve corresponding to the first global maximum; Determine the frequency peak value corresponding to the second maximum value in the fitting curve; The significance of equipment defects of pressure-bearing special equipment is calculated by using the frequency peaks, peak numbers and deformation degrees corresponding to the reference frequency curve and the abnormal frequency curve.

[0012] Furthermore, the use of the correlation between the original acoustic wave signal and the IMF segmented signal and the significance of the equipment defects to determine the importance of reconstructing the IMF component signal includes: The reconstruction importance of the IMF component signal is calculated using the Pearson correlation coefficient between the original acoustic wave signal and the IMF segmented signal at the same segmented position and the significance of equipment defects.

[0013] Further, the use of reconstruction importance to determine the IMF component signal that needs to be removed or retained to reconstruct the original sound wave signal includes: The IMF component signals whose reconstruction importance is less than a preset importance threshold are removed, and the IMF component signals whose reconstruction importance is greater than or equal to the preset importance threshold are retained to reconstruct the original sound wave signal.

[0014] The present invention has the following beneficial effects: The present invention obtains IMF segmented signals by segmenting each IMF component signal after decomposing the original sound wave signal of the pressure-bearing special equipment, analyzing the acoustic emission data characteristics of each segment, comparing the stability of the change of the characteristics in the time series, obtaining the distortion of the signal, combining the different performances of equipment defects and noise in frequency, obtaining the performance ability of each IMF segmented signal for equipment defects and the performance of noise, obtaining the significance of equipment defects, using it as a weight, adjusting the correlation threshold judgment between the IMF component signal and the original sound wave signal, completing the screening of the IMF component, more accurately realizing the removal of noise signals and the retention of defect signals of pressure-bearing special equipment, and significantly improving the accuracy of noise reduction and reconstruction of acoustic emission signals. At the same time, based on the implementation of the present invention, online real-time detection of pressure-bearing special equipment can be achieved, improving detection efficiency and reducing detection costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 A flowchart of a method for collecting and processing acoustic emission monitoring data for pressure-bearing special equipment provided by an embodiment of the present invention; Figure 2 A detailed flow chart of step S2 in a method for collecting and processing acoustic emission monitoring data for pressure-bearing special equipment provided by one embodiment of the present invention; Figure 3 A detailed flow chart of step S3 in a method for collecting and processing acoustic emission monitoring data for pressure-bearing special equipment provided by one embodiment of the present invention; Figure 4 A detailed flow chart of step S4 in a method for collecting and processing acoustic emission monitoring data for pressure-bearing special equipment provided by one embodiment of the present invention; Figure 5 It is a structural schematic diagram of the hardware operating environment of the acoustic emission monitoring data acquisition and processing equipment for pressure-bearing special equipment involved in the embodiment of the present invention; Figure 6 It is a schematic diagram of the framework structure of the acoustic emission monitoring data acquisition and processing system for pressure-bearing special equipment involved in the embodiment of the present invention; Figure 7 It is a schematic diagram of a reference frequency curve and an abnormal frequency curve involved in the embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the specific implementation method, structure, features and effects of a method for collecting and processing acoustic emission monitoring data of pressure-bearing special equipment proposed by the present invention in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0018] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0019] The following is a detailed description of a method for collecting and processing acoustic emission monitoring data for pressure-bearing special equipment provided by the present invention in conjunction with the accompanying drawings.

[0020] Embodiment 1: For the data collection and processing method for acoustic emission monitoring of pressure-bearing special equipment provided by the present invention, please refer to Figure 1 , which shows a flowchart of the steps of a method for collecting and processing acoustic emission monitoring data for pressure-bearing special equipment provided by an embodiment of the present invention.

[0021] The method comprises: Step S1, determining the IMF component signal of the original sound wave signal emitted by the pressure-bearing special equipment and the IMF segmented signal obtained by dividing the original sound wave signal; In this embodiment, the original sound wave signal emitted by the pressure-bearing special equipment as an acoustic emission source can be obtained through the acoustic emission sensor, and the corresponding sampling frequency can be 50HZ.

[0022] The existing particle swarm optimization algorithm can be used to obtain the number of modes and penalty factors of the variational mode decomposition vmd algorithm. The original sound wave signal is decomposed by the vmd parameters obtained above to obtain multiple IMF (Intrinsic Mode Function) component signals of the original sound wave signal. The center frequency of each IMF component signal can also be obtained at the same time. The IMF component signals are sorted from small to large (low frequency to high frequency) according to their center frequencies, and are recorded as IMF1, IMF2, etc.; then, the IMF component signals are segmented using an autocorrelation algorithm to obtain IMF segmented signals.

[0023] Step S2, determining the signal authenticity of the IMF segmented signal, and using the signal authenticity to determine the distortion degree of the IMF segmented signal; For details, please refer to Figure 2 , the step S2 comprises: Step S21, obtaining the root mean square and average signal level of the IMF segmented signal; Step S22, using the root mean square and the average signal level, calculate the signal authenticity.

[0024] If there are no defects in the pressure-bearing special equipment and it is in normal and stable operating conditions, the corresponding signal amplitude fluctuation is small. For example, in the normal pressure range of the pressure vessel, the amplitude of the acoustic emission signal generated by the lattice slip and dislocation inside the material is relatively fixed, so the amplitude change of the IMF component after VMD decomposition should also be stable, and the amplitude of the component remains stable in time. If there is environmental noise, the monitored signal will have significant irregular fluctuations, randomly increase or decrease the amplitude, and cover up the real signal changes.

[0025] Based on the above-mentioned law of the influence of noise on the acoustic wave signal, the amplitude corresponding to the IMF component signal data at each acquisition moment is obtained. For the segmentation of the IMF component signal, if the RMS (Root Mean Square) of the signal amplitude under the segment is higher, the signal level ASL (Average Signal Level) of the corresponding segment is smaller, the more it reflects the real and normal signal of the pressure-bearing special equipment corresponding to the IMF component, that is, the greater the authenticity of the signal. Therefore, the signal authenticity of the IMF segmented signal can be reflected specifically in the following ways: Indicates the authenticity of the jth segment signal of the ith IMF component; represents the jth segment under the i-th IMF component; Indicates the RMS value of this segment; Represents the ASL value under this segment; it should be noted that, in order to ensure that the calculation result is meaningful, when performing fractional operations in the embodiment of the present invention, when the denominator is 0, it is necessary to add a parameter adjustment factor greater than 0 to the denominator to prevent the denominator from being 0. The value of the parameter adjustment factor is set by the implementer according to the actual situation, and this application does not impose any special restrictions.

[0026] Different IMF components correspond to normal operating signals with different frequency characteristics. IMF components with larger amplitudes may correspond to energy release at a specific frequency when the equipment is operating normally, while smaller ASL indicates that this energy release is within a normal, short-term range without continuous high-intensity signal interference, which is consistent with the characteristics of normal structural operation of the equipment. The smaller the ASL and the larger the RMS amplitude, the IMF belongs to the normal acoustic emission signal of pressure-bearing special equipment, otherwise it belongs to an abnormal signal, that is, the true normality of the signal can be reflected by the size of the signal's true degree. The larger the value, the more true and normal the signal is, and vice versa, the more abnormal the signal is.

[0027] In addition, the method of determining the distortion degree of the IMF segmented signal by using the signal authenticity degree includes: Determine the difference in signal authenticity between each IMF segment signal; The distortion degree of IMF segmented signal is determined by using the difference in the true degree of the signal.

[0028] When pressure-bearing special equipment is operating normally, its internal physical processes, such as the flow of the medium and the normal friction between components, will generate relatively stable acoustic emission signals (sound wave signals). These signals have specific frequency and energy characteristics. The same IMF component obtained by VMD decomposition represents a signal component with similar frequency characteristics. Due to the stability of the normal operation process, the signal energy and amplitude changes corresponding to the IMF component are also relatively stable, which makes the ASL and RMS relatively stable in time series. Therefore, the signal authenticity under the same IMF mentioned above should remain stable under normal circumstances. Environmental noise is usually generated randomly, and its frequency and amplitude change irregularly over time. These noise signals will be superimposed on the acoustic emission signals generated by the normal operation of the equipment, thereby destroying the regularity of the signal. When the mixed signal containing noise is decomposed by VMD, the noise will affect the signal characteristics of the same IMF component. In this regard, the degree of abnormal signal distortion of each IMF segmented signal can be further evaluated by the following specific methods: The signal authenticity of the jth segment is compared with the signal authenticity of the other segments under the same IMF component. If there is a significant difference between the authenticity of the same frequency band and the authenticity of the other frequency bands, the two different segments themselves have a higher signal authenticity. Therefore, the IMF segment signal reflects the local anomaly of the IMF component of the VMD decomposition of the pressure-bearing special equipment in the time series.

[0029] In the above formula, Indicates the distortion degree of the jth segment signal of the i-th IMF component; represents the number of segments of the i-th IMF component; represents the true degree of the jth segment signal representing the i-th IMF component, represents the first IMF component The authenticity of a segmented signal.

[0030] By comparing the authenticity of the same IMF segment signal with that of the remaining segments, if there is significant environmental noise in the signal, the IMF signal of this segment will be obviously distorted. It reflects the local distortion of the signal in this segment. The larger the value, the more obvious the RMS and ASL differences between the jth segment and the remaining segments under the same IMF segmentation. As a result, the waveform of the signal in this segment is significantly different from that of the remaining segments, and there is significant signal distortion. On the contrary, the smaller the value, the stronger the consistency of the signals in each time period under the IMF component, and the less likely it is to be abnormal. This means that the IMF signal in this segment has no significant distortion and is a normal VMD decomposition signal in the acoustic emission detection process.

[0031] Step S3, using the distortion degree and spectrum curve of the IMF segmented signal to determine the corresponding reference frequency curve and abnormal frequency curve; For details, please refer to Figure 3 , the step S3 comprises: Step S31, determining an IMF segment normal signal and an IMF segment abnormal signal corresponding to the IMF segment signal; More specifically, the step S31 includes: Input the IMF segmented signal into the box plot to obtain the corresponding IMF segmented normal signal and IMF segmented abnormal signal; The IMF segmented normal signal and the IMF segmented abnormal signal are respectively subjected to short-time Fourier transform to obtain a frequency spectrum curve of the IMF segmented normal signal and a frequency spectrum curve of the IMF segmented abnormal signal.

[0032] If there are defects in pressure-bearing special equipment, such as crack expansion, corrosion, etc., a certain periodic acoustic emission signal will be generated, and as the defects develop, the energy release will gradually increase and the ASL will increase. For example, during the crack defect expansion process of pressure-bearing special equipment, new fracture surfaces will continue to be generated, and energy will be continuously released, so that the acoustic emission signal will maintain high intensity for a long time, thereby increasing the ASL value of the signal. However, environmental noise in acoustic emission detection also causes the signal ASL value to be too large. Since the importance of the signal cannot be judged, the IMF component selection for signal reconstruction is inaccurate, which interferes with the performance of the acoustic emission detection signal for the detection of defects in pressure-bearing special equipment.

[0033] In this regard, in this embodiment, one of the IMF component signals is selected, and a box plot anomaly detection algorithm is used. The segmented signal and distortion degree of each segment of the component signal are used as the input of the box plot, and the abnormal segment in the IMF component signal is output. Thus, the IMF segmented normal signal and the IMF segmented abnormal signal in the time series are obtained. The IMF segmented abnormal signal here represents a signal segment with noise interference or a signal segment reflecting the defects of pressure-bearing special equipment.

[0034] The IMF segmented normal signal and the IMF segmented abnormal signal are transformed by STFT (Short-Time Fourier Transform) respectively to obtain the spectral characteristics and spectral curves corresponding to the IMF segmented normal signal and the IMF segmented abnormal signal respectively.

[0035] Step S32, using the distortion degree and spectrum curve of the IMF segmented normal signal, calculate and obtain the reference frequency curve of the IMF component signal; Step S33, using the distortion degree and frequency spectrum curve of the IMF segmented abnormal signal, calculate and obtain the abnormal frequency curve of the IMF component signal.

[0036] Since different segments of the same IMF component signal are in the same frequency bandwidth, if the equipment is operating normally, it will vibrate at its natural frequency or a specific frequency related to the working state to generate an acoustic emission signal. Therefore, the frequencies of the acoustic emission signals generated in different time periods are consistent. For example, when a pressure vessel is under stable pressure, the vibration frequency of its shell is relatively fixed. These natural vibration frequencies make the acoustic emission signal centralized in frequency. After VMD decomposition, the frequency of the IMF component will also show a centralized characteristic.

[0037] In the above case, if there is environmental noise, it will be superimposed on the acoustic emission signal of the normal operation of the equipment. The IMF component originally concentrated near a specific frequency will be interfered by the noise, making the frequency distribution wider and the energy distribution divergent. If it appears as a crack defect in pressure-bearing special equipment, the equipment crack defect will generate an acoustic emission signal of a specific frequency during the expansion process. These signals are related to factors such as the size of the crack, the expansion speed, and the material properties. In the spectrum diagram of the IMF component, obvious peaks will appear at specific frequencies related to the crack. For example, when the crack expands rapidly, significant peaks may appear in the frequency band of 800kHz-1MHz. These peaks reflect the rapid release of energy during the crack expansion process.

[0038] In this regard, taking the reference frequency curve as an example, the following methods can be used to obtain the reference frequency curve: F represents the reference frequency curve of the IMF component signal; The spectrum curve representing the j-th signal of the IMF component signal (here refers to any IMF segment normal signal); It represents the inverse of the distortion degree of the j-th segment signal. The smaller the distortion degree, the greater the reference value of the spectrum curve, which reflects the corresponding spectrum curve under normal conditions of the equipment. is the weight of the jth signal segment; the frequency spectrum curves of all IMF segmented normal signals of the IMF component are summed to obtain the reference frequency curve F of the IMF component, which reflects the frequency characteristics of the IMF component of the pressure-bearing special equipment in the normal state during the acoustic emission detection process. A curve can be represented by a sequence of data points.

[0039] Similarly, the abnormal frequency curve of the IMF component signal can also be obtained , I will not go into details here.

[0040] Step S4, using the reference frequency curve and the abnormal frequency curve and their corresponding frequency peaks, determining the significance of equipment defects of the pressure-bearing special equipment; For details, please refer to Figure 4 , the step S4 comprises: Step S41, determining the degree of deformation between the reference frequency curve and the abnormal frequency curve with respect to the frequency distribution; More specifically, the step S41 includes: Determine a reference frequency bandwidth of a reference frequency curve and a frequency segment interval into which the reference frequency bandwidth is divided; Determine the difference in cumulative amount between the reference frequency curve and the abnormal frequency curve in each same frequency segment interval; The difference between each cumulative amount is used to determine the degree of deformation of the reference frequency curve and the abnormal frequency curve in the frequency distribution.

[0041] Please refer to Figure 7 , get the reference frequency bandwidth of the reference frequency curve, the reference frequency bandwidth is the minimum value of the frequency in the frequency curve and maximum value The interval formed , the reference frequency bandwidth is evenly divided to obtain each frequency segment interval.

[0042] Select any frequency segmentation interval to obtain the deformation degree of the reference frequency distribution under the frequency segmentation interval and the abnormal frequency distribution under the segmentation interval: It indicates the degree of deformation, reflects the difference between the abnormal IMF segmentation signal and the normal IMF segmentation signal in the frequency segmentation interval, reflects the degree of deformation of the frequency distribution, and also reflects the interference of noise on the IMF component signal; F represents the reference frequency curve of the IMF component signal, Indicates abnormal frequency curve; represents the integral over frequency, ∈ ,and In the range Any equally divided frequency segment interval.

[0043] If all deformation degrees are similar within the reference frequency bandwidth of the IMF component signal, the possibility of environmental noise is greater; on the contrary, if there are significant differences between the deformation degrees, it means that there is an obvious change in the frequency distribution, and thus the possibility of a real defect of the pressure-bearing special equipment is greater.

[0044] The standard deviation of the deformation can also be obtained: Indicates the standard deviation of the deformation degree of different frequency segments under the reference frequency bandwidth.

[0045] Step S42, using the frequency peaks and deformation degrees corresponding to the reference frequency curve and the abnormal frequency curve, respectively, to calculate the significance of equipment defects of the pressure-bearing special equipment.

[0046] More specifically, the step S42 includes: Obtaining first total maximum values ​​corresponding to the reference frequency curve and the abnormal frequency curve respectively; Determine the fitting curve corresponding to the first global maximum; Determine the frequency peak value corresponding to the second maximum value in the fitting curve; The significance of equipment defects of pressure-bearing special equipment is calculated by using the frequency peaks, peak numbers and deformation degrees corresponding to the reference frequency curve and the abnormal frequency curve.

[0047] Taking the reference frequency curve as an example, obtain the overall maximum value in the reference frequency curve F (for the sake of distinction, it is called the first overall maximum value here), use polynomial fitting to obtain the first overall maximum value, obtain the fitting curve, obtain the second overall maximum value of the fitting curve, and determine the frequency corresponding to the second maximum value. The fitting curve reflects the distribution of frequency, and the obtained second maximum value reflects the peak value of the frequency, avoiding the interference of local peaks. The peak value is obtained by It is a two-dimensional coordinate. It should be noted that there may be multiple peaks, and the number of peaks can be expressed as .

[0048] Similarly, the frequency peak corresponding to the abnormal frequency curve is obtained and the peak number .

[0049] Compare the consistency of the reference frequency curve and the abnormal frequency curve. If the two frequency curves are similar in different frequency segment intervals, the frequency distribution of the corresponding IMF components is basically consistent, and there is no obvious difference in the shape of the frequency distribution, then it means that the frequency segment interval is more likely to be a device defect; otherwise, it means that the segment is more likely to be affected by noise.

[0050] Specifically, the significance of equipment defects of pressure-bearing special equipment can be determined by the following methods: Indicates the initial significance of equipment defects and reflects the possibility of equipment defects; Represents the i-th frequency peak of the reference frequency curve; represents the jth frequency peak of the abnormal frequency curve, The norm of the difference between the two; Indicates taking the minimum norm; Indicates the standard deviation of deformation degree of different frequency segment intervals under the reference frequency bandwidth; and Respectively represent the number of peaks corresponding to the reference frequency curve and the abnormal frequency curve; is the positive correlation normalization function.

[0051] If there is an obvious difference in peak distribution between the abnormal frequency curve and the reference frequency curve in a certain frequency segmentation interval, and the number of peaks in its frequency distribution increases significantly, then the abnormal frequency curve reflects the real defect signal of the pressure-bearing special equipment in this frequency segmentation interval.

[0052] In order to more comprehensively and accurately measure the significance of equipment defects reflected by the overall abnormal frequency curve, the following methods can be used: The final equipment defect significance of pressure-bearing special equipment; Indicates the initial equipment defect significance; It represents the mean of all deformation degrees, reflecting the interference of environmental noise on the abnormal frequency curve. The greater the interference, the lower the accuracy of defect signal judgment of pressure-bearing equipment.

[0053] Set the equipment defect significance under normal equipment operation Correspondingly, a value greater than 1 can be judged as an equipment defect anomaly, and a value less than 1 can be judged as a noise anomaly.

[0054] Step S5, determining the importance of reconstructing the IMF component signal by using the correlation between the original acoustic wave signal and the IMF segmented signal and the significance of the equipment defect; Specifically, the step S5 includes: The reconstruction importance of the IMF component signal is calculated using the Pearson correlation coefficient between the original acoustic wave signal and the IMF segmented signal at the same segmented position and the significance of equipment defects.

[0055] Based on the above process, the characteristic performance of IMF segmented abnormal signals for equipment defects is determined. The IMF segmented abnormal signals are compared with the original sound wave signals at the same segmented position. If there is a strong noise performance in the same segmented position ( <1), the environmental noise signal needs to be removed. The noise signal obtained in the IMF reconstruction process should exclude the interference of the corresponding IMF component signal and reduce the similarity with the original sound wave signal. If there is a strong equipment defect performance in the same segment position ( >1), although the similarity between the above signals is weak, they still show the real structural defects of pressure-bearing equipment. Such signals should be retained, so the similarity between the corresponding IMF component signal and the original signal should be amplified; Specifically, the following methods can be used to determine which IMF component signals need to be retained and which need to be removed: represents the reconstruction importance of the i-th IMF component signal; represents the Pearson correlation coefficient between the j-th segment of the original sound wave signal and the segmented signal of the j-th segment of the i-th IMF component signal, and the segmented division of the original sound wave signal and the signal division of the i-th IMF component are at the same corresponding position; The significance of equipment defects for pressure-bearing special equipment.

[0056] Step S6: using the reconstruction importance, determine the IMF component signal that needs to be removed or retained to reconstruct the original sound wave signal.

[0057] Specifically, the step S6 includes: The IMF component signals whose reconstruction importance is less than a preset importance threshold are removed, and the IMF component signals whose reconstruction importance is greater than or equal to the preset importance threshold are retained to reconstruct the original sound wave signal.

[0058] The importance of reconstruction of each IMF component signal is obtained. The importance threshold can be set to 0.8 (adjustable). IMF component signals greater than or equal to 0.8 participate in the reconstruction of acoustic emission detection data (original sound wave signal), and IMF component signals less than 0.8 do not participate in the reconstruction of acoustic emission detection data, thereby completing the selection of intrinsic mode functions. Finally, the retained IMF component signals are reconstructed to obtain the denoised sound wave reconstruction signal.

[0059] In addition, supplementarily, the specific equipment defect detection steps reflected by the sound wave signal of pressure-bearing special equipment can be as follows: 1. Feature extraction Time domain features: Calculate the time domain statistical features of the reconstructed signal, such as mean, variance, root mean square, peak, kurtosis, etc. These features can reflect the strength and fluctuation of the signal.

[0060] Frequency domain features: Perform frequency domain analysis such as Fourier transform on the reconstructed signal to extract frequency domain features such as center frequency, frequency bandwidth, and spectrum peak to understand the frequency distribution characteristics of the signal.

[0061] Time-frequency domain characteristics: Use time-frequency analysis methods such as wavelet transform and short-time Fourier transform to obtain time-frequency domain characteristics, such as time-frequency energy distribution, time-frequency peak, etc., to more comprehensively describe the changes of signals at different times and frequencies.

[0062] 2. Construct feature vector The extracted time domain, frequency domain, and time-frequency domain features are combined to form a multi-dimensional feature vector to comprehensively characterize the characteristics of the reconstructed signal.

[0063] 3. Defect identification and classification Establish a fault model or database: collect the acoustic emission signal data of pressure-bearing special equipment with known defect types and degrees, process and extract features according to the above steps, and establish a corresponding defect feature model or database, which includes feature vectors and corresponding defect information under different defect states.

[0064] Select classification algorithm: Use appropriate classification algorithm, such as support vector machine (SVM), artificial neural network (ANN), decision tree, etc., to compare and analyze the extracted feature vector of the signal to be detected with the fault model or database.

[0065] Model training and validation: Use known defect data to train and validate the classification algorithm and adjust the model parameters so that it can accurately identify different defect types and degrees.

[0066] Defect detection and diagnosis: The reconstructed acoustic emission signal of the actual pressure-bearing special equipment that has been processed and feature extracted is input into the trained classification model, and the model outputs the corresponding defect type, location, severity and other diagnostic results.

[0067] Result evaluation and verification: The defect detection results are evaluated and verified through actual testing, anatomical verification, and comparison with other non-destructive testing methods to ensure the accuracy and reliability of the test results. If the results are inaccurate or unreliable, the signal processing process, feature extraction method, classification model, etc. need to be re-examined for optimization and improvement.

[0068] The present invention obtains IMF segmented signals by segmenting each IMF component signal after decomposing the original sound wave signal of the pressure-bearing special equipment, analyzing the acoustic emission data characteristics of each segment, comparing the stability of the change of the characteristics in the time series, obtaining the distortion of the signal, combining the different performances of equipment defects and noise in frequency, obtaining the performance ability of each IMF segmented signal for equipment defects and the performance of noise, obtaining the significance of equipment defects, using it as a weight, adjusting the correlation threshold judgment between the IMF component signal and the original sound wave signal, completing the screening of the IMF component, more accurately realizing the removal of noise signals and the retention of defect signals of pressure-bearing special equipment, and significantly improving the accuracy of noise reduction and reconstruction of acoustic emission signals. At the same time, based on the implementation of the present invention, online real-time detection of pressure-bearing special equipment can be achieved, improving detection efficiency and reducing detection costs.

[0069] Embodiment 2: The embodiment of the present invention also provides a data collection and processing device for acoustic emission monitoring of pressure-bearing special equipment. The data collection and processing device for acoustic emission monitoring of pressure-bearing special equipment can be a data calculation and processing device such as a computer, a server, a programmable logic controller, or a combination of multiple devices.

[0070] like Figure 5 As shown, Figure 5 It is a structural schematic diagram of the hardware operating environment of the acoustic emission monitoring data collection and processing equipment for pressure-bearing special equipment involved in the embodiment of the present invention.

[0071] like Figure 5 As shown, the acoustic emission monitoring data acquisition and processing device for pressure-bearing special equipment may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, and a communication bus 1002. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display (Display), an input unit such as a control panel, and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WIFI interface). The memory 1005 may be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001. The memory 1005 as a computer storage medium may include a program for collecting and processing acoustic emission monitoring data for pressure-bearing special equipment.

[0072] Those skilled in the art will understand that Figure 5The hardware structure shown in the figure does not constitute a limitation of the device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0073] Continue to refer to Figure 5 , Figure 5 The memory 1005 as a computer-readable storage medium may include an operating system, a user interface module, a network communication module, and a pressure-bearing special equipment acoustic emission monitoring data acquisition and processing program.

[0074] exist Figure 5 In the embodiment, the network communication module is mainly used to connect to the server and can communicate data with the server; and the processor 1001 can call the acoustic emission monitoring data collection and processing program for pressure-bearing special equipment stored in the memory 1005, and execute the steps in the above embodiments.

[0075] The hardware structure of the above-mentioned equipment for collecting and processing acoustic emission monitoring data of pressure-bearing special equipment is used to implement various embodiments of the method for collecting and processing acoustic emission monitoring data of pressure-bearing special equipment of the present invention.

[0076] In addition, the present invention also provides a pressure-bearing special equipment acoustic emission monitoring data collection and processing system, please refer to Figure 6 The acoustic emission monitoring data acquisition and processing system for pressure-bearing special equipment includes: The signal decomposition module A10 is used to determine the IMF component signal of the original sound wave signal emitted by the pressure-bearing special equipment and the IMF segmented signal obtained by dividing the original sound wave signal; The signal processing module A20 is used to determine the signal authenticity of the IMF segmented signal, and determine the distortion degree of the IMF segmented signal by using the signal authenticity; determine the corresponding reference frequency curve and abnormal frequency curve by using the distortion degree and spectrum curve of the IMF segmented signal; determine the significance of equipment defects of pressure-bearing special equipment by using the reference frequency curve and the abnormal frequency curve and their respective corresponding frequency peaks; determine the importance of reconstruction of the IMF component signal by using the correlation between the original sound wave signal and the IMF segmented signal and the significance of the equipment defects; The sound wave reconstruction module A30 is used to determine the IMF component signal that needs to be removed or retained to reconstruct the original sound wave signal by using the reconstruction importance.

[0077] Furthermore, the signal processing module A20 is also used for: Get the RMS and average signal levels of the IMF segmented signal; Using the RMS and average signal levels, the signal authenticity is calculated.

[0078] Furthermore, the signal processing module A20 is also used for: Determine the difference in signal authenticity between each IMF segment signal; The distortion degree of IMF segmented signal is determined by using the difference in the true degree of the signal.

[0079] Furthermore, the signal processing module A20 is also used for: Determine an IMF segment normal signal and an IMF segment abnormal signal corresponding to the IMF segment signal; The reference frequency curve of the IMF component signal is calculated by using the distortion degree and spectrum curve of the IMF segmented normal signal; The abnormal frequency curve of the IMF component signal is calculated using the distortion degree and spectrum curve of the IMF segmented abnormal signal.

[0080] Furthermore, the signal processing module A20 is also used for: Input the IMF segmented signal into the box plot to obtain the corresponding IMF segmented normal signal and IMF segmented abnormal signal; The IMF segmented normal signal and the IMF segmented abnormal signal are respectively subjected to short-time Fourier transform to obtain a frequency spectrum curve of the IMF segmented normal signal and a frequency spectrum curve of the IMF segmented abnormal signal.

[0081] Furthermore, the signal processing module A20 is also used for: Determining the degree of deformation between the reference frequency curve and the abnormal frequency curve with respect to the frequency distribution; The significance of equipment defects of pressure-bearing special equipment is calculated by using the frequency peaks and deformation degrees corresponding to the reference frequency curve and the abnormal frequency curve.

[0082] Furthermore, the signal processing module A20 is also used for: Determine a reference frequency bandwidth of a reference frequency curve and a frequency segment interval into which the reference frequency bandwidth is divided; Determine the difference in cumulative amount between the reference frequency curve and the abnormal frequency curve in each same frequency segment interval; The difference between each cumulative amount is used to determine the degree of deformation of the reference frequency curve and the abnormal frequency curve in the frequency distribution.

[0083] Furthermore, the signal processing module A20 is also used for: Obtaining first total maximum values ​​corresponding to the reference frequency curve and the abnormal frequency curve respectively; Determine the fitting curve corresponding to the first global maximum; Determine the frequency peak value corresponding to the second maximum value in the fitting curve; The significance of equipment defects of pressure-bearing special equipment is calculated by using the frequency peaks, peak numbers and deformation degrees corresponding to the reference frequency curve and the abnormal frequency curve.

[0084] Furthermore, the signal processing module A20 is also used for: The reconstruction importance of the IMF component signal is calculated using the Pearson correlation coefficient between the original acoustic wave signal and the IMF segmented signal at the same segmented position and the significance of equipment defects.

[0085] Furthermore, the acoustic wave reconstruction module A30 is also used for: The IMF component signals whose reconstruction importance is less than a preset importance threshold are removed, and the IMF component signals whose reconstruction importance is greater than or equal to the preset importance threshold are retained to reconstruct the original sound wave signal.

[0086] The specific implementation of the acoustic emission monitoring data collection and processing system for pressure-bearing special equipment of the present invention is basically the same as the various embodiments of the acoustic emission monitoring data collection and processing method for pressure-bearing special equipment mentioned above, and will not be repeated here.

[0087] In addition, the present invention also provides a computer-readable storage medium. The computer-readable storage medium of the present invention stores a program for collecting and processing acoustic emission monitoring data for pressure-bearing special equipment, wherein when the program for collecting and processing acoustic emission monitoring data for pressure-bearing special equipment is executed by a processor, the steps of the method for collecting and processing acoustic emission monitoring data for pressure-bearing special equipment as described above are implemented.

[0088] Among them, the method implemented when the pressure-bearing special equipment acoustic emission monitoring data collection and processing program is executed can refer to the various embodiments of the pressure-bearing special equipment acoustic emission monitoring data collection and processing method of the present invention, and will not be repeated here.

[0089] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0090] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0091] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0092] The above description is only a preferred embodiment of the present invention, and does not limit the protection scope of the present invention. All equivalent structural / method transformations made by using the contents of the present invention specification and drawings under the inventive concept of the present invention, or direct / indirect application in other related technical fields are included in the protection scope of the present invention.

Claims

1. A method for collecting and processing acoustic emission monitoring data of pressure-bearing special equipment, characterized in that: The method comprises: Determine the IMF component signal of the original sound wave signal emitted by the pressure-bearing special equipment and the IMF segmented signal divided therefrom; Determine the signal authenticity of the IMF segmented signal, and use the signal authenticity to determine the distortion degree of the IMF segmented signal; Using the distortion degree and spectrum curve of the IMF segmented signal, the corresponding reference frequency curve and abnormal frequency curve are determined; Determine the significance of equipment defects of pressure-bearing special equipment by using the reference frequency curve, abnormal frequency curve and their corresponding frequency peaks; The importance of reconstructing the IMF component signals is determined by using the correlation between the original acoustic wave signal and the IMF segmented signal and the significance of the equipment defects. The reconstruction importance is used to determine the IMF component signals that need to be removed or retained to reconstruct the original sound wave signal.

2. The method for collecting and processing acoustic emission monitoring data of pressure-bearing special equipment according to claim 1 is characterized in that: Determining the signal authenticity of the IMF segmented signal includes: Get the RMS and average signal levels of the IMF segmented signal; Using the RMS and average signal levels, the signal authenticity is calculated.

3. The method for collecting and processing acoustic emission monitoring data of pressure-bearing special equipment according to claim 1 is characterized in that: Determining the distortion degree of the IMF segmented signal by using the signal authenticity degree includes: Determine the difference in signal authenticity between each IMF segment signal; The distortion degree of IMF segmented signal is determined by using the difference in the true degree of the signal.

4. The method for collecting and processing acoustic emission monitoring data of pressure-bearing special equipment according to claim 1 is characterized in that: The method of using the distortion degree and the spectrum curve of the IMF segmented signal to determine the corresponding reference frequency curve and the abnormal frequency curve includes: Determine an IMF segment normal signal and an IMF segment abnormal signal corresponding to the IMF segment signal; The reference frequency curve of the IMF component signal is calculated by using the distortion degree and spectrum curve of the IMF segmented normal signal; The abnormal frequency curve of the IMF component signal is calculated using the distortion degree and spectrum curve of the IMF segmented abnormal signal.

5. The method for collecting and processing acoustic emission monitoring data of pressure-bearing special equipment according to claim 4 is characterized in that: The determining of the IMF segment normal signal and the IMF segment abnormal signal corresponding to the IMF segment signal includes: Input the IMF segmented signal into the box plot to obtain the corresponding IMF segmented normal signal and IMF segmented abnormal signal; The IMF segmented normal signal and the IMF segmented abnormal signal are respectively subjected to short-time Fourier transform to obtain a frequency spectrum curve of the IMF segmented normal signal and a frequency spectrum curve of the IMF segmented abnormal signal.

6. The method for collecting and processing acoustic emission monitoring data of pressure-bearing special equipment according to claim 1 is characterized in that: The use of the reference frequency curve and the abnormal frequency curve and their corresponding frequency peaks to determine the significance of equipment defects of pressure-bearing special equipment includes: Determining the degree of deformation between the reference frequency curve and the abnormal frequency curve with respect to the frequency distribution; The significance of equipment defects of pressure-bearing special equipment is calculated by using the frequency peaks and deformation degrees corresponding to the reference frequency curve and the abnormal frequency curve.

7. The method for collecting and processing acoustic emission monitoring data of pressure-bearing special equipment according to claim 6 is characterized in that: The step of determining the degree of deformation between the reference frequency curve and the abnormal frequency curve with respect to the frequency distribution includes: Determine a reference frequency bandwidth of a reference frequency curve and a frequency segment interval into which the reference frequency bandwidth is divided; Determine the difference in cumulative amount between the reference frequency curve and the abnormal frequency curve in each same frequency segment interval; The difference between each cumulative amount is used to determine the degree of deformation of the reference frequency curve and the abnormal frequency curve in the frequency distribution.

8. The method for collecting and processing acoustic emission monitoring data of pressure-bearing special equipment according to claim 6 is characterized in that: The equipment defect significance of the pressure-bearing special equipment is calculated by using the frequency peak value and deformation degree corresponding to the reference frequency curve and the abnormal frequency curve, including: Obtaining first total maximum values ​​corresponding to the reference frequency curve and the abnormal frequency curve respectively; Determine the fitting curve corresponding to the first global maximum; Determine the frequency peak value corresponding to the second maximum value in the fitting curve; The significance of equipment defects of pressure-bearing special equipment is calculated by using the frequency peaks, peak numbers and deformation degrees corresponding to the reference frequency curve and the abnormal frequency curve.

9. The method for collecting and processing acoustic emission monitoring data of pressure-bearing special equipment according to claim 1 is characterized in that: The method of determining the importance of reconstructing the IMF component signal by utilizing the correlation between the original acoustic wave signal and the IMF segmented signal and the significance of the equipment defects comprises: The reconstruction importance of the IMF component signal is calculated using the Pearson correlation coefficient between the original acoustic wave signal and the IMF segmented signal at the same segmented position and the significance of equipment defects.

10. The method for collecting and processing acoustic emission monitoring data of pressure-bearing special equipment according to claim 1 is characterized in that: The method of utilizing the reconstruction importance to determine the IMF component signal that needs to be removed or retained to reconstruct the original sound wave signal includes: The IMF component signals whose reconstruction importance is less than a preset importance threshold are removed, and the IMF component signals whose reconstruction importance is greater than or equal to the preset importance threshold are retained to reconstruct the original sound wave signal.

Images