Acoustic emission waveform classification method and device based on multi-criteria scoring mechanism, equipment, medium and program product

Abstract

The application provides a kind of acoustic emission waveform classification method, device, equipment, medium and program product based on multi-criteria scoring mechanism, it is related to rock mechanics monitoring technical field.The method comprises: obtaining acoustic emission signal;The acoustic emission signal is preprocessed, and acoustic emission waveform is obtained;At least two waveform indexes of each acoustic emission waveform are calculated, and each waveform index and corresponding index threshold are compared to obtain the waveform index comparison result of each acoustic emission waveform;According to the waveform index comparison result, scoring is carried out, and the scoring result of each acoustic emission waveform is obtained;Based on the scoring result of each acoustic emission waveform, the type of each acoustic emission waveform is determined.The embodiments of the application are used to solve the defects that the judgment basis is single and the deployment is complex in the prior art, and the acoustic emission waveform classification is realized by scoring through multi-criteria in a visual and adjustable manner.

Description

Technical Field

[0001] This invention relates to the field of rock mechanics monitoring technology, and in particular to a method, device, equipment, medium, and program product for classifying acoustic emission waveforms based on a multi-criteria scoring mechanism. Background Technology

[0002] Acoustic emission (AE) technology is widely used in fields such as rock mass fracture monitoring and early warning of dynamic disasters in mines. However, in the field environment, AE signals are often affected by low signal-to-noise ratio, background noise fluctuations, and instrument mis-triggers, resulting in a large number of non-fracture events or low-quality waveforms in the acquired data, which seriously affects the accuracy of subsequent event localization and mechanism analysis.

[0003] Existing AE signal recognition methods mostly rely on empirical amplitude threshold methods or subjective judgment methods, lacking systematic quantitative criteria and easily affected by human error. While using complex machine learning models has higher accuracy, it lacks transparency, is difficult to deploy quickly, and has complex parameter tuning, failing to meet the actual needs of industrial sites for "adjustable parameters, interpretable results, and efficient operation".

[0004] Therefore, how to classify acoustic emission waveforms is a technical problem that urgently needs to be solved. Summary of the Invention

[0005] This invention provides a method, apparatus, device, medium, and program product for acoustic emission waveform classification based on a multi-criteria scoring mechanism, which solves the defects of existing technologies that rely on a single judgment criterion and are complex to deploy, and realizes acoustic emission waveform classification in a visual and adjustable manner by scoring through multiple criteria.

[0006] In a first aspect, the present invention provides an acoustic emission waveform classification method based on a multi-criteria scoring mechanism, comprising the following steps: Acquire acoustic emission signals; The acoustic emission signal is preprocessed to obtain the acoustic emission waveform; Calculate at least two waveform indicators for each acoustic emission waveform, and compare each waveform indicator with its corresponding threshold to obtain the waveform indicator comparison results for each acoustic emission waveform; The waveform indicators are compared to obtain a score for each acoustic emission waveform. Based on the scoring results of each acoustic emission waveform, the type of each acoustic emission waveform is determined.

[0007] Preferably, according to the acoustic emission waveform classification method based on a multi-criteria scoring mechanism provided by the present invention, the preprocessing of the acoustic emission signal to obtain the acoustic emission waveform includes: The original waveform of the acoustic emission signal is read, the pre-trigger region of the original waveform is trimmed, and the waveform length of the trimmed original waveform is unified to obtain the acoustic emission waveform.

[0008] Preferably, in the acoustic emission waveform classification method based on a multi-criteria scoring mechanism provided by the present invention, the waveform indicators include at least two of the following: signal-to-noise ratio, peak intensity, kurtosis, local energy ratio, and active time; The signal-to-noise ratio (SNR) represents the ratio of the overall root mean square value of the acoustic emission signal to the logarithm of the background noise segment of the acoustic emission signal, used to measure the clarity of the acoustic emission signal intensity relative to the background noise; the peak intensity represents the point of maximum absolute amplitude in the acoustic emission waveform, used to reflect the instantaneous intensity of the event energy; the kurtosis represents the ratio of the fourth central moment of the waveform to the square of the variance, used to describe the instantaneous pulse characteristics of a real acoustic emission event; the local energy ratio represents the energy ratio of the main energy segment to the remaining background segment in the metric signal; and the active time represents the continuous time segment in the acoustic emission waveform that exceeds 30% of the peak amplitude.

[0009] Preferably, according to the acoustic emission waveform classification method based on a multi-criteria scoring mechanism provided by the present invention, the step of scoring each acoustic emission waveform based on the waveform index comparison results to obtain a score result for each waveform includes: If the waveform index indicated by the waveform index comparison result is greater than or equal to the corresponding index threshold, the score of the corresponding waveform index is recorded. The scores of all waveform indicators are summed to obtain the score for each acoustic emission waveform.

[0010] Preferably, according to the acoustic emission waveform classification method based on a multi-criteria scoring mechanism provided by the present invention, determining the type of each acoustic emission waveform based on the scoring result of each acoustic emission waveform includes: Obtain the score threshold set by the user based on the graphical user interface; The scoring result of each acoustic emission waveform is compared with the score threshold. If the score of the acoustic emission waveform is greater than or equal to the score threshold, the corresponding acoustic emission waveform is determined to be a valid waveform. If the score of the acoustic emission waveform is less than the score threshold, the corresponding acoustic emission waveform is determined to be an invalid waveform.

[0011] Preferably, in the acoustic emission waveform classification method based on a multi-criteria scoring mechanism provided by the present invention, after the step of determining the type of each acoustic emission waveform based on the scoring result of each acoustic emission waveform, the method further includes: Based on the type of acoustic emission waveform, the acoustic emission waveforms are classified, and the classified acoustic emission waveforms are displayed through the graphical user interface. Export different types of acoustic emission waveforms in a preset text format.

[0012] Secondly, the present invention also provides an acoustic emission waveform classification device based on a multi-criteria scoring mechanism, comprising the following modules: The acquisition module is used to acquire acoustic emission signals; The preprocessing module is used to preprocess the acoustic emission signal to obtain the acoustic emission waveform; The calculation module is used to calculate at least two waveform indicators for each acoustic emission waveform, and compare each waveform indicator with the corresponding indicator threshold to obtain the waveform indicator comparison result for each acoustic emission waveform. The scoring module is used to score based on the waveform index comparison results to obtain a score result for each acoustic emission waveform; The classification module is used to determine the type of each acoustic emission waveform based on the scoring results of each waveform.

[0013] Thirdly, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the acoustic emission waveform classification method based on the multi-criteria scoring mechanism described above.

[0014] Fourthly, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the acoustic emission waveform classification method based on a multi-criteria scoring mechanism as described above.

[0015] Fifthly, the present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the acoustic emission waveform classification method based on a multi-criteria scoring mechanism as described above.

[0016] This invention provides a method, apparatus, device, medium, and program product for acoustic emission waveform classification based on a multi-criteria scoring mechanism. The method involves: acquiring acoustic emission signals; preprocessing the acoustic emission signals to obtain acoustic emission waveforms; calculating at least two waveform indices for each acoustic emission waveform and comparing each waveform indices with their corresponding threshold values ​​to obtain a waveform index comparison result for each acoustic emission waveform; scoring each acoustic emission waveform based on the waveform index comparison results to obtain a score result for each acoustic emission waveform; and determining the type of each acoustic emission waveform based on its score result. This addresses the shortcomings of existing technologies that rely on a single judgment criterion and involve complex deployments, enabling acoustic emission waveform classification in a visualized and adjustable manner through multi-criteria scoring. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0018] Figure 1 This is a flowchart illustrating the acoustic emission waveform classification method based on a multi-criteria scoring mechanism provided by the present invention.

[0019] Figure 2 This is one of the schematic diagrams for acoustic emission waveform recognition provided by the present invention.

[0020] Figure 3 This is the second schematic diagram of acoustic emission waveform recognition provided by the present invention.

[0021] Figure 4 This is the third schematic diagram of acoustic emission waveform recognition provided by the present invention.

[0022] Figure 5 This is a schematic diagram comparing the quantity of acoustic emission signals and noise signals provided by the present invention.

[0023] Figure 6 This is a schematic diagram of the acoustic emission waveform classification device based on a multi-criteria scoring mechanism provided by the present invention.

[0024] Figure 7 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0026] The following is combined Figures 1-7 This invention describes a method, apparatus, device, medium, and program product for classifying acoustic emission waveforms based on a multi-criteria scoring mechanism. It addresses the shortcomings of existing technologies that rely on a single judgment criterion and have complex deployments, and enables acoustic emission waveform classification in a visualized and adjustable manner by scoring based on multiple criteria.

[0027] Figure 1 This is one of the flowcharts illustrating an acoustic emission waveform classification method based on a multi-criteria scoring mechanism provided by the present invention, such as... Figure 1As shown, the method may include, but is not limited to, steps S100 to S500: S100, acquire acoustic emission signals; S200, the acoustic emission signal is preprocessed to obtain the acoustic emission waveform; S300, calculate at least two waveform indicators for each acoustic emission waveform, and compare each waveform indicator with the corresponding indicator threshold to obtain the waveform indicator comparison result for each acoustic emission waveform; S400, score each acoustic emission waveform based on the waveform index comparison results; S500 determines the type of each acoustic emission waveform based on the scoring results of each waveform.

[0028] In step S100 of some embodiments, an acoustic emission signal is acquired.

[0029] Understandably, the selection and placement of sensors involves using high-sensitivity piezoelectric acoustic emission sensors (PZT), which are attached to the surface of the component under test or embedded in key internal parts to ensure the capture of elastic waves generated by the propagation of minute cracks.

[0030] Data acquisition system configuration: Connect to a multi-channel acoustic transmitter, set the sampling rate to ≥1MHz (must be higher than the highest frequency component of the signal), and synchronously record timestamps and spatial coordinate information.

[0031] Trigger condition setting: Enable threshold trigger mode, start acquisition only when the signal amplitude exceeds the background noise baseline, reduce the amount of invalid data.

[0032] Effective acoustic emission signals can be acquired by selecting and arranging sensors, configuring the data acquisition system, and setting trigger conditions.

[0033] In step S200 of some embodiments, the acoustic emission signal is preprocessed to obtain an acoustic emission waveform.

[0034] It is understood that the acoustic emission waveform is obtained by reading the original waveform of the acoustic emission signal, trimming the pre-trigger region of the original waveform, and unifying the waveform length of the trimmed original waveform.

[0035] It should be noted that wavelet threshold denoising / FIR low-pass filtering can be used for denoising, and moving average method can be used for trend removal. Difference downsampling to an appropriate resolution can be used for resampling. Finally, normalization is used to eliminate the influence of differences in the sensitivity of different sensors to obtain the acoustic emission waveform.

[0036] Read the original waveform of the acoustic emission signal, remove the "quiet period" data (pre-trigger buffer) automatically generated by the instrument at the signal front end, and retain only the response part of the real physical event. A dynamic threshold method can be used: 1. Find the first sampling point that exceeds the baseline + 3σ, 2. Backtrack N points as a new starting point to trim the pre-trigger area of ​​the original waveform.

[0037] Furthermore, the pre-trigger zone is the silent period before the sensor is impacted, and it needs to be precisely cut off to focus on the high-frequency vibration signal at the moment of rupture.

[0038] Furthermore, by ensuring that event waveforms of different durations have the same dimension, it facilitates batch feature extraction and neural network input. Specifically, when the current length > the target length L, a head truncation method is used to retain the first L sampling points, prioritizing the preservation of the initial high-energy release phase. When the current length < the target length L, a zero-padding method is used: zero values ​​are padded to L at the end to maintain the waveform's end-attenuation characteristics.

[0039] In some embodiments of the present invention, the waveform metrics include at least two of the following: signal-to-noise ratio, peak intensity, kurtosis, local energy ratio, and active time; The signal-to-noise ratio (SNR) represents the ratio of the overall root mean square value of the acoustic emission signal to the logarithm of the background noise segment of the acoustic emission signal, used to measure the clarity of the acoustic emission signal intensity relative to the background noise; the peak intensity represents the point of maximum absolute amplitude in the acoustic emission waveform, used to reflect the instantaneous intensity of the event energy; the kurtosis represents the ratio of the fourth central moment of the waveform to the square of the variance, used to describe the instantaneous pulse characteristics of a real acoustic emission event; the local energy ratio represents the energy ratio of the main energy segment to the remaining background segment in the metric signal; and the active time represents the continuous time segment in the acoustic emission waveform that exceeds 30% of the peak amplitude.

[0040] Furthermore, the signal-to-noise ratio (SNR) is defined as the logarithm of the overall root mean square (RMS) value of the signal to the RMS value of the background noise segment, expressed in dB.

[0041] Physical meaning: It measures the clarity of a signal strength relative to background noise and is the basis for judging the identifiability of a signal.

[0042] Calculation formula: in, , where 𝑥(i) is the acoustic emission signal and n is the signal length. Indicates the root mean square of the signal. Indicates the root mean square of the background. This indicates the signal-to-noise ratio.

[0043] (2) Definition of peak amplitude: The amplitude point with the largest absolute value in the waveform signal.

[0044] Physical meaning: It reflects the instantaneous intensity of the event's energy. Low amplitude values ​​often indicate background disturbances or instrument noise. By traversing the waveform array, the sampling point with the largest absolute value is found, which is the peak amplitude.

[0045] (3) Definition of kurtosis: The ratio of the fourth central moment of a waveform to the square of its variance, describing its "sharpness". Physical meaning: Real acoustic emission (AE) events have instantaneous pulse characteristics and high kurtosis, while background noise tends to have a normal distribution and low kurtosis.

[0046] Calculation formula: In the formula, The values ​​represent kurtosis, waveform mean μ, and standard deviation σ.

[0047] (4) Definition of local energy ratio (EnergyRatio): It is used to measure the energy ratio between the main energy segment and the remaining background segment in a signal.

[0048] Physical meaning: AE events have concentrated energy, resulting in local energy mutations. High energy ratio is a characteristic of valid events.

[0049] Calculation formula: Among them, the main energy window Remaining energy window , The point of maximum amplitude is L, which is half the length of the local energy window. This represents the local energy ratio.

[0050] (5) Definition of Active Time: The continuous time segment in the waveform that exceeds 30% of the peak amplitude.

[0051] Physical meaning: The AE signal exhibits a short-duration excitation pattern, with a short and concentrated effective waveform duration, and its active time is representative within a certain range.

[0052] Calculation formula: In the formula, Indicates the active time. End time, Indicates the start time.

[0053] In step S300 of some embodiments, at least two waveform indicators for each acoustic emission waveform are calculated, and each waveform indicator is compared with the corresponding indicator threshold to obtain the waveform indicator comparison result for each acoustic emission waveform.

[0054] Understandably, this involves extracting five waveform indicators from each acoustic emission waveform, calculating the numerical expression corresponding to its physical meaning, and using these as the basis for classification criteria. The waveform indicators are as described above and will not be repeated here.

[0055] Each waveform indicator is compared with its corresponding threshold to obtain the waveform indicator comparison result for each acoustic emission waveform. Taking the comparison of signal-to-noise ratio (SNR) and SNR threshold as an example, if the SNR is greater than or equal to the SNR threshold, the first comparison result is obtained.

[0056] If the signal-to-noise ratio is less than the signal-to-noise ratio threshold, a second comparison result is obtained where the signal-to-noise ratio is less than the signal-to-noise ratio threshold.

[0057] Similarly, other waveform indicators can be compared with their corresponding waveform indicator thresholds to obtain the corresponding waveform indicator comparison results.

[0058] Furthermore, each waveform indicator has a different threshold, which users can flexibly set according to their needs.

[0059] In step S400 of some embodiments, a score is given based on the waveform index comparison result to obtain a score result for each acoustic emission waveform.

[0060] It is understood that, in some embodiments of the present invention, the step of scoring based on the waveform index comparison results to obtain a score result for each acoustic emission waveform includes: If the waveform index indicated by the waveform index comparison result is greater than or equal to the corresponding index threshold, the score of the corresponding waveform index is recorded. The scores of all waveform indicators are summed to obtain the score for each acoustic emission waveform.

[0061] If the waveform index indicated by the waveform index comparison result is greater than or equal to the corresponding index threshold, it is recorded as 1 point; if the waveform index indicated by the waveform index comparison result is less than the corresponding index threshold, it is recorded as 0 points.

[0062] The scores for all waveform indicators are calculated to obtain the score for each acoustic emission waveform.

[0063] In step S500 of some embodiments, the type of each acoustic emission waveform is determined based on the scoring result of each acoustic emission waveform.

[0064] Understandably, this involves obtaining the score threshold set by the user based on the graphical user interface. The scoring result of each acoustic emission waveform is compared with the score threshold. If the score of the acoustic emission waveform is greater than or equal to the score threshold, the corresponding acoustic emission waveform is determined to be a valid waveform. If the score of the acoustic emission waveform is less than the score threshold, the corresponding acoustic emission waveform is determined to be an invalid waveform.

[0065] In an embodiment of the present invention, for example, if the signal-to-noise ratio is 1 point, the peak intensity is 1 point, the kurtosis is 0 points, the local energy ratio is 1 point, and the active time is 1 point, then the total score is 4 points. The total score range is set to 5 points, and the score threshold is set to 3 points.

[0066] Each waveform indicator is scored either 0 or 1, with a total score ranging from 0 to 5. Based on the set score thresholds (e.g., a total score ≥ 3 is considered valid), the acoustic emission signals are classified.

[0067] If the total score of the scoring results is greater than or equal to the score threshold, the corresponding acoustic emission waveform is determined to be a valid waveform.

[0068] If the total score of the acoustic emission waveform is less than the score threshold, the corresponding acoustic emission waveform is determined to be an invalid waveform.

[0069] Furthermore, to enhance the system's adaptability, an automatic threshold segmentation method based on statistical feature distribution is adopted to achieve self-learning and optimization of the classification criterion threshold.

[0070] The threshold determination method of this approach, taking Statistically Optimized Variance Segmentation (SOVS) as an example, is based on the following principle: A statistical histogram is constructed based on the numerical distribution of a certain criterion (such as signal-to-noise ratio) in the current dataset. By traversing all possible split points, the data is divided into two groups, and the variance and its weighted sum within each group are calculated. The split point that maximizes the inter-group variability and minimizes the intra-group dispersion is then selected as the optimal threshold.

[0071] This method requires no prior knowledge or manually set empirical parameters; it relies entirely on the statistical regularities of the data itself to automatically optimize the criteria boundaries. It is particularly suitable for samples exhibiting significant bimodal distribution characteristics. The automatic segmentation results can be directly used to determine signal validity or provide a reference for manually setting thresholds, enhancing the method's universality and engineering adaptability.

[0072] In some embodiments of the present invention, after the step of determining the type of each acoustic emission waveform based on the scoring result of each acoustic emission waveform, the method further includes: Based on the type of acoustic emission waveform, the acoustic emission waveforms are classified, and the classified acoustic emission waveforms are displayed through the graphical user interface. Export different types of acoustic emission waveforms in a preset text format.

[0073] In some embodiments, all waveform classification results are output in CSV (text format) format and simultaneously saved in MAT format for subsequent modeling or machine learning.

[0074] Figure 2 This is one of the schematic diagrams for acoustic emission waveform recognition provided by the present invention. Figure 3 This is the second schematic diagram of acoustic emission waveform recognition provided by the present invention. Figure 4 This is the third schematic diagram of acoustic emission waveform recognition provided by the present invention. Figure 5 This is a schematic diagram comparing the quantity of acoustic emission signals and noise signals provided by the present invention. (Combined with...) Figures 2 to 5 As shown, in the rock acoustic emission monitoring experiment, a large amount of AE (acoustic emission) data with a sampling rate of 10 MHz was collected, with each data point containing approximately 5000 points. Without filtering, some signals exhibited the following problems: background noise at the beginning, electrical noise from the amplification instrument at the end, very small peak values, and kurtosis close to a Gaussian distribution.

[0075] The method of this invention is applied as follows: (1) GUI interface settings: SNR threshold is set to 20 dB; peak threshold is set to 0.08; kurtosis is set to 3.5; local energy ratio is set to 1.2; active time is set to 5 μs; total score threshold is set to 4.

[0076] (2) After analyzing 200 waveforms, the method provided by this invention can automatically identify 86 valid waveforms and 114 invalid waveforms; the data quality is significantly improved and the subsequent positioning error is reduced by about 40%.

[0077] All waveform classification results and score details are saved in summary.csv, and classification tags are saved in classification.mat, which will be used for the next step of event location reconstruction and mechanism identification.

[0078] The embodiments provided by this invention can achieve at least the following technical effects: (1) The structure is clear and highly interpretable, making it easy for field engineers to understand; (2) The parameters are adjustable and can be quickly adapted to different mining areas and equipment conditions; (3) Significantly improves classification accuracy and data availability, and filters out invalid waveforms; (4) Integrate a GUI interface to enable automatic batch data classification and report export; (5) It can be used as a high-quality sample screening system before training AI models.

[0079] This invention provides a method, apparatus, device, medium, and program product for acoustic emission waveform classification based on a multi-criteria scoring mechanism. The method involves: acquiring acoustic emission signals; preprocessing the acoustic emission signals to obtain acoustic emission waveforms; calculating at least two waveform indices for each acoustic emission waveform and comparing each waveform indices with their corresponding threshold values ​​to obtain a waveform index comparison result for each acoustic emission waveform; scoring each acoustic emission waveform based on the waveform index comparison results to obtain a score result for each acoustic emission waveform; and determining the type of each acoustic emission waveform based on its score result. This addresses the shortcomings of existing technologies that rely on a single judgment criterion and involve complex deployments, enabling acoustic emission waveform classification in a visualized and adjustable manner through multi-criteria scoring.

[0080] The acoustic emission waveform classification device based on a multi-criteria scoring mechanism provided by the present invention will be described below. The acoustic emission waveform classification device based on a multi-criteria scoring mechanism described below can be referred to in correspondence with the acoustic emission waveform classification method based on a multi-criteria scoring mechanism described above.

[0081] like Figure 6 The diagram shown is a structural schematic of an acoustic emission waveform classification device based on a multi-criteria scoring mechanism provided by the present invention. The acoustic emission waveform classification device based on a multi-criteria scoring mechanism includes the following modules: Acquisition module 610 is used to acquire acoustic emission signals; Preprocessing module 620 is used to preprocess the acoustic emission signal to obtain an acoustic emission waveform; The calculation module 630 is used to calculate at least two waveform indicators for each acoustic emission waveform, and compare each waveform indicator with the corresponding indicator threshold to obtain the waveform indicator comparison result for each acoustic emission waveform. The scoring module 640 is used to score based on the waveform index comparison results to obtain a score result for each acoustic emission waveform; The classification module 650 is used to determine the type of each acoustic emission waveform based on the scoring results of each acoustic emission waveform.

[0082] Preferably, the acoustic emission waveform classification device based on a multi-criteria scoring mechanism provided by the present invention is specifically used to read the original waveform of the acoustic emission signal, trim the pre-trigger region of the original waveform, and unify the waveform length of the trimmed original waveform to obtain the acoustic emission waveform.

[0083] Preferably, the acoustic emission waveform classification device based on a multi-criteria scoring mechanism provided by the present invention is specifically used for waveform indicators that include at least two of the following: signal-to-noise ratio, peak intensity, kurtosis, local energy ratio, and active time; The signal-to-noise ratio (SNR) represents the ratio of the overall root mean square value of the acoustic emission signal to the logarithm of the background noise segment of the acoustic emission signal, used to measure the clarity of the acoustic emission signal intensity relative to the background noise; the peak intensity represents the point of maximum absolute amplitude in the acoustic emission waveform, used to reflect the instantaneous intensity of the event energy; the kurtosis represents the ratio of the fourth central moment of the waveform to the square of the variance, used to describe the instantaneous pulse characteristics of a real acoustic emission event; the local energy ratio represents the energy ratio of the main energy segment to the remaining background segment in the metric signal; and the active time represents the continuous time segment in the acoustic emission waveform that exceeds 30% of the peak amplitude.

[0084] Preferably, the acoustic emission waveform classification device based on a multi-criteria scoring mechanism provided by the present invention is specifically used to record the score of the corresponding waveform index if the waveform index indicated by the waveform index comparison result is greater than or equal to the corresponding index threshold. The scores of all waveform indicators are summed to obtain the score for each acoustic emission waveform.

[0085] Preferably, the acoustic emission waveform classification device based on a multi-criteria scoring mechanism provided by the present invention is specifically used to obtain the score threshold set by the user based on a graphical user interface; The scoring result of each acoustic emission waveform is compared with the score threshold. If the score of the acoustic emission waveform is greater than or equal to the score threshold, the corresponding acoustic emission waveform is determined to be a valid waveform. If the score of the acoustic emission waveform is less than the score threshold, the corresponding acoustic emission waveform is determined to be an invalid waveform.

[0086] Preferably, the acoustic emission waveform classification device based on a multi-criteria scoring mechanism provided by the present invention is specifically used to classify acoustic emission waveforms based on the type of acoustic emission waveforms, and to display the classified acoustic emission waveforms through the graphical user interface. Export different types of acoustic emission waveforms in a preset text format.

[0087] This invention provides a method, apparatus, device, medium, and program product for acoustic emission waveform classification based on a multi-criteria scoring mechanism. The method involves: acquiring acoustic emission signals; preprocessing the acoustic emission signals to obtain acoustic emission waveforms; calculating at least two waveform indices for each acoustic emission waveform and comparing each waveform indices with their corresponding threshold values ​​to obtain a waveform index comparison result for each acoustic emission waveform; scoring each acoustic emission waveform based on the waveform index comparison results to obtain a score result for each acoustic emission waveform; and determining the type of each acoustic emission waveform based on its score result. This addresses the shortcomings of existing technologies that rely on a single judgment criterion and involve complex deployments, enabling acoustic emission waveform classification in a visualized and adjustable manner through multi-criteria scoring.

[0088] Figure 7 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 7 As shown, the electronic device may include a processor 710, a communications interface 720, a memory 730, and a communication bus 740, wherein the processor 710, the communications interface 720, and the memory 730 communicate with each other through the communication bus 740. The processor 710 can call logical instructions in the memory 730 to execute an acoustic emission waveform classification method based on a multi-criteria scoring mechanism. The method includes: acquiring an acoustic emission signal; preprocessing the acoustic emission signal to obtain an acoustic emission waveform; calculating at least two waveform indices for each acoustic emission waveform and comparing each waveform indices with a corresponding index threshold to obtain a waveform index comparison result for each acoustic emission waveform; scoring according to the waveform index comparison result to obtain a score result for each acoustic emission waveform; and determining the type of each acoustic emission waveform based on the score result for each acoustic emission waveform.

[0089] Furthermore, the logical instructions in the aforementioned memory 730 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0090] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer is able to execute the acoustic emission waveform classification method based on a multi-criteria scoring mechanism provided by the above methods. The method includes: acquiring an acoustic emission signal; preprocessing the acoustic emission signal to obtain an acoustic emission waveform; calculating at least two waveform indices for each acoustic emission waveform and comparing each waveform indices with a corresponding index threshold to obtain a waveform index comparison result for each acoustic emission waveform; scoring according to the waveform index comparison result to obtain a score result for each acoustic emission waveform; and determining the type of each acoustic emission waveform based on the score result for each acoustic emission waveform.

[0091] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon. When executed by a processor, the computer program implements the acoustic emission waveform classification method based on a multi-criteria scoring mechanism provided by the methods described above. The method includes: acquiring an acoustic emission signal; preprocessing the acoustic emission signal to obtain an acoustic emission waveform; calculating at least two waveform indices for each acoustic emission waveform and comparing each waveform indice with a corresponding index threshold to obtain a waveform index comparison result for each acoustic emission waveform; scoring according to the waveform index comparison result to obtain a score result for each acoustic emission waveform; and determining the type of each acoustic emission waveform based on the score result for each acoustic emission waveform.

[0092] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0093] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0094] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for classifying acoustic emission waveforms based on a multi-criteria scoring mechanism, characterized in that, include: Acquire acoustic emission signals; The acoustic emission signal is preprocessed to obtain the acoustic emission waveform; Multiple waveform metrics are calculated for each acoustic emission waveform, and each metric is compared with its corresponding threshold to obtain the waveform metric comparison results for each acoustic emission waveform. The waveform metrics include: signal-to-noise ratio (SNR), peak intensity, kurtosis, local energy ratio, and active time. Specifically, the SNR represents the ratio of the overall root mean square value of the acoustic emission signal to the logarithm of the background noise segment of the acoustic emission signal, used to measure the clarity of the acoustic emission signal intensity relative to the background noise; the peak intensity represents the point of maximum absolute amplitude in the acoustic emission waveform, used to reflect the instantaneous intensity of the event energy; the kurtosis represents the ratio of the fourth-order central moment of the waveform to the square of the variance, used to describe the instantaneous pulse characteristics of a real acoustic emission event; the local energy ratio represents the energy ratio of the main energy segment to the remaining background segment in the metric signal; and the active time represents the continuous time segment in the acoustic emission waveform that exceeds 30% of the peak amplitude. The indicator threshold is determined using an automatic threshold segmentation method based on statistical feature distribution. The determination of the indicator threshold includes: Based on the numerical distribution of a certain waveform indicator in the current dataset, construct the corresponding statistical histogram; By traversing all possible split points, the data is divided into two groups, and the variance and corresponding weighted sum within each group are calculated. Then, the split point that maximizes the difference between groups and minimizes the dispersion within groups is selected as the threshold of the waveform index. Scoring is performed based on the waveform index comparison results to obtain a score for each acoustic emission waveform; the scoring process for each acoustic emission waveform based on the waveform index comparison results includes: If the waveform index indicated by the waveform index comparison result is greater than or equal to the corresponding index threshold, then the corresponding record is scored as 1 point. If the waveform index indicated by the waveform index comparison result is less than the corresponding index threshold, the corresponding record will be scored as 0. The scores of all waveform indicators corresponding to each acoustic emission waveform are summed to obtain the score result of each acoustic emission waveform. Based on the scoring results of each acoustic emission waveform, the type of each acoustic emission waveform is determined; the determination of the type of each acoustic emission waveform based on the scoring results of each acoustic emission waveform includes: Obtain the score threshold set by the user based on the graphical user interface; The scoring result of each acoustic emission waveform is compared with the score threshold. If the score of the acoustic emission waveform is greater than or equal to the score threshold, the corresponding acoustic emission waveform is determined to be a valid waveform. If the score of the acoustic emission waveform is less than the score threshold, the corresponding acoustic emission waveform is determined to be an invalid waveform.

2. The acoustic emission waveform classification method based on a multi-criteria scoring mechanism according to claim 1, characterized in that, The preprocessing of the acoustic emission signal to obtain the acoustic emission waveform includes: The original waveform of the acoustic emission signal is read, the pre-trigger region of the original waveform is trimmed, and the waveform length of the trimmed original waveform is unified to obtain the acoustic emission waveform.

3. The acoustic emission waveform classification method based on a multi-criteria scoring mechanism according to claim 1, characterized in that, After the step of determining the type of each acoustic emission waveform based on the scoring result of each acoustic emission waveform, the method further includes: Based on the type of acoustic emission waveform, the acoustic emission waveforms are classified, and the classified acoustic emission waveforms are displayed through the graphical user interface. Export different types of acoustic emission waveforms in a preset text format.

4. An acoustic emission waveform classification device based on a multi-criteria scoring mechanism, applied to the acoustic emission waveform classification method based on a multi-criteria scoring mechanism as described in any one of claims 1 to 3, characterized in that, include: The acquisition module is used to acquire acoustic emission signals; The preprocessing module is used to preprocess the acoustic emission signal to obtain the acoustic emission waveform; The calculation module is used to calculate at least two waveform indicators for each acoustic emission waveform, and compare each waveform indicator with the corresponding indicator threshold to obtain the waveform indicator comparison result for each acoustic emission waveform. The scoring module is used to score based on the waveform index comparison results to obtain a score result for each acoustic emission waveform; The classification module is used to determine the type of each acoustic emission waveform based on the scoring results of each waveform.

5. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the program, it implements the acoustic emission waveform classification method based on a multi-criteria scoring mechanism as described in any one of claims 1 to 3.

6. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the acoustic emission waveform classification method based on the multi-criteria scoring mechanism as described in any one of claims 1 to 3.

7. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the acoustic emission waveform classification method based on the multi-criteria scoring mechanism as described in any one of claims 1 to 3.

Images