A method and system for detecting multimodal mechanical waves based on boundary bounce characteristics

Abstract

This invention discloses a multimodal mechanical wave detection method and system based on boundary bounce characteristics, belonging to the field of nondestructive testing technology. The method includes: collecting and preprocessing the waveforms, frequencies, and amplitudes of multiple modal mechanical waves using sensors; analyzing the reflection characteristics of these waves when they encounter boundaries during propagation within a target object; calculating the boundary bounce values ​​of the multiple modal mechanical waves; selecting the mechanical wave with the highest boundary bounce value as the depth waveform feature; constructing a relational model; inputting the depth waveform feature into the relational model; predicting the severity of defects; and generating an early warning scheme. The method effectively removes noise interference and improves signal clarity, laying the foundation for accurate analysis of the boundary bounce characteristics of mechanical waves and providing strong data support for subsequent defect assessment. It enables quantitative assessment and real-time monitoring of internal corrosion defects in target objects, improving the practicality and engineering application value of the detection system.

Description

Technical Field

[0001] This invention relates to the field of nondestructive testing technology, specifically to a multimodal mechanical wave detection method and system based on boundary bounce characteristics. Background Technology

[0002] In recent years, mechanical wave detection technology has been widely used in non-destructive testing, structural health monitoring, and material characterization. Mechanical waves, including acoustic waves, elastic waves, and ultrasonic waves, have attracted much attention because they can penetrate the interior of materials and respond sensitively to defects, internal stresses, and structural changes. In practical applications, different modes of mechanical waves can provide rich detection information due to their different propagation characteristics and interactions with material boundaries. In particular, multimodal mechanical wave detection technology, by integrating the characteristics of multiple wave modes, has made it possible to accurately detect complex structures and heterogeneous materials. However, with the increasing application demands and the need to improve detection accuracy, in-depth research on the propagation characteristics of mechanical waves inside target objects and how to extract key waveform features have become current research hotspots. Current research focuses on waveform signal processing, propagation path simulation, and multimodal data fusion, laying the theoretical foundation and practical basis for the further development of mechanical wave detection technology.

[0003] Although multimodal mechanical wave detection technology has significant advantages in complex media environments, existing methods still have some limitations and shortcomings. Current technologies typically focus on single-mode waves, lacking comprehensive analysis of multimodal wave characteristics. This limitation leads to the loss of some important information during the detection process, especially the waveform change characteristics during boundary reflection, which cannot be fully utilized. When mechanical waves interact with the boundary of a target object, the characteristics of the reflected waves can reflect the material boundary properties and internal structure. However, current technologies have only superficially studied this characteristic and have not yet formed a systematic analytical method. Furthermore, the lack of a scientifically effective quantitative index in the detection and optimization of multimodal waves makes it difficult to select the optimal wave mode with high detection sensitivity in complex detection environments, thus limiting the robustness and accuracy of the detection results. Therefore, improving the accuracy and practicality of mechanical wave detection is an urgent problem to be solved in current technological development. Summary of the Invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by this invention is that existing multimodal mechanical wave detection technologies cannot effectively utilize boundary bounce characteristics for analysis, lack effective screening of waveforms sensitive to defects, and how to select the most representative depth waveform features from multiple modal mechanical waves to achieve accurate detection and evaluation of internal defects.

[0006] To address the aforementioned technical problems, this invention provides the following technical solution: a multimodal mechanical wave detection method based on boundary bounce characteristics, comprising: collecting and preprocessing the waveforms, frequencies, and amplitudes of multiple modal mechanical waves using sensors; analyzing the reflection characteristics of multiple modal mechanical waves when they encounter boundaries during propagation within a target object; calculating the boundary bounce values ​​of multiple modal mechanical waves; selecting the mechanical wave with the highest boundary bounce value as the depth waveform feature; constructing a relational model; inputting the depth waveform feature into the relational model; predicting the severity of defects; and generating an early warning scheme.

[0007] As a preferred embodiment of the multimodal mechanical wave detection method based on boundary bounce characteristics described in this invention, the step of using sensors to collect waveforms, frequencies, and amplitudes of multiple modes of mechanical waves includes selecting a MEMS sensor, configuring the sensor's sampling frequency and sampling time, setting a data acquisition time window, and collecting signal data of longitudinal waves, transverse waves, surface waves, and plate waves propagating inside the target object.

[0008] As a preferred embodiment of the multimodal mechanical wave detection method based on boundary bounce characteristics described in this invention, the preprocessing process includes using a Butterworth filter to eliminate noise interference from multiple modal mechanical waves, resulting in a denoised signal x. filtered (t) is used to normalize the signal so that all signal values ​​fall within the same range, and the normalized value x is calculated. norm (t), represented as:

[0009]

[0010] Where, x min It is the minimum value in the denoised signal, x max It is the maximum value in the denoised signal, x norm (t) is the normalized value.

[0011] As a preferred embodiment of the multimodal mechanical wave detection method based on boundary bounce characteristics described in this invention, the analysis of the reflection behavior of multiple modal mechanical waves when they encounter a boundary during propagation inside the target object includes applying multimodal mechanical waves at different locations on the target object, recording the response intensity of the waveform using a high-speed camera and a laser Doppler vibrometer, simulating the response intensity of multiple modal waves at corrosion defects using the finite element analysis software COMSOL Multiphysics, and acquiring the background noise signal Q in the absence of corrosion defects, calculating the standard deviation σ of the background noise as an indicator of the noise level.

[0012] The reflection behavior of the waveform at different boundaries is recorded, and a multi-scale analysis method is introduced to analyze the boundary bounce characteristics at different scales from macroscopic to microscopic. This includes using wavelet transform to remove noise while retaining the main features of the waveform in the true reflection characteristics. The field strength S(t,s) of the denoised reflected wave is calculated and expressed as:

[0013]

[0014] Where S(t,s) is the denoised reflected wave field intensity, ψ is the wavelet basis function, s is the scale parameter, t is the time parameter, and x is the time parameter. norm (τ) is the original signal. This is an integral operation where dτ is an infinitesimal increment of the time variable τ. It normalizes the waveform characteristic signal data to the same order of magnitude, and then calculates the normalized signal S. norm (t,s) is represented as:

[0015]

[0016] Among them, S min It is the minimum value in the signal after wavelet transform, S max S is the maximum value in the signal after wavelet transform. norm (t,s) represents the normalized signal.

[0017] Collect background noise signal Q, calculate the standard deviation σ of the background noise as an indicator of noise level, including calculating the mean μ and the variance σ. 2 The standard deviation σ is calculated, and the background noise level is assessed based on the calculated σ. When σ exceeds the preset threshold σ1, it indicates that the background noise level is too high. The background noise signal is then re-acquired, and an adaptive filter is used for further denoising. The denoised background noise signal W(t) is calculated and expressed as:

[0018] W(t) = QH adapt (J)·E(t)

[0019] Where W(t) is the denoised background noise signal, H adapt (J) is the transfer function of the adaptive filter, E(t) is the estimated noise signal, and the standard deviation σ2 of the denoised background noise signal is recalculated as follows:

[0020]

[0021] Where, σ 2 μ represents the standard deviation of the denoised background noise signal. clean The average value of the denoised background noise signal is (W(t)). i )-μ clean ) 2The square of the difference between each denoised background noise signal value and the average value. For the summation symbol, W(t) i (i) represents the value of the denoised background noise signal at time point i. For the operation of averaging, N is the length of the signal, and i is each time point.

[0022] As a preferred embodiment of the multimodal mechanical wave detection method based on boundary bounce characteristics described in this invention, the step of selecting the mechanical wave with the highest boundary bounce value as the depth waveform feature includes setting the boundary bounce value to R(t,s), expressed as:

[0023]

[0024] Where R(t,s) is the boundary bounce value, and S norm (t,s) represents the normalized reflected wave field intensity. The mechanical wave with the highest boundary bounce value is selected as the depth waveform feature, and the depth waveform feature F is calculated. depth , represented as:

[0025]

[0026] Among them, F depth For depth waveform features, This means finding the values ​​of t and s that maximize R(t,s) across all time scales.

[0027] As a preferred embodiment of the multimodal mechanical wave detection method based on boundary bounce characteristics described in this invention, the step of constructing a relationship model based on corrosion defects and depth waveform characteristics, inputting the depth waveform characteristics into the relationship model, and predicting the severity of the defects includes assuming the relationship model is a linear regression model, calculating the output model y, which is expressed as:

[0028] y=w1F depth,1 +w2F depth,2 +w3F depth,3 +b

[0029] Where w1, w2, and w3 are weight parameters, b is the bias term, and w1F depth,1 +w2F depth,2 +w3F depth,3 It is the depth waveform feature vector, y is the model output, F depth,1 F depth,2 and F depth,3 These are the various components of the depth waveform feature vector.

[0030] As a preferred solution of the multi-modal mechanical wave detection method based on the boundary bounce characteristics according to the present invention, the following is provided: The generation of the warning plan includes inputting the newly collected depth waveform features into the trained random forest model to obtain a prediction result, setting warning thresholds L1 and L2 according to the prediction result, and generating a warning message. If y < L1, a warning message for minor defects is generated, suggesting regular inspection and maintenance. If L1 ≤ y ≤ L2, a warning message for medium defects is generated, suggesting immediate detailed inspection and taking necessary repair measures. If y ≥ L2, a warning message for serious defects is generated, suggesting immediate stoppage of use and emergency repair or replacement.

[0031] Another object of the present invention is to provide a multi-modal mechanical wave detection system based on the boundary bounce characteristics, which can analyze the reflection characteristics when multi-modal mechanical waves encounter boundaries during propagation inside the target object, calculate the boundary bounce values of the multi-modal mechanical waves, and select the mechanical wave with the highest boundary bounce value as the depth waveform feature, solving the problems of insufficient in-depth analysis of reflection characteristics and inaccurate calculation methods of boundary bounce values in current non-destructive testing technologies.

[0032] As a preferred solution of the multi-modal mechanical wave detection system based on the boundary bounce characteristics according to the present invention, the following is provided: It includes a data preprocessing module, a boundary bounce analysis module, and a defect prediction and warning module.

[0033] The data preprocessing module is used to collect the waveforms, frequencies, and amplitudes of multi-modal mechanical waves by using sensors and perform preprocessing; the boundary bounce analysis module is used to analyze the reflection characteristics when multi-modal mechanical waves encounter boundaries during propagation inside the target object, calculate the boundary bounce values of the multi-modal mechanical waves, and select the mechanical wave with the highest boundary bounce value as the depth waveform feature; the defect prediction and warning module is used to construct a relationship model, input the depth waveform features into the relationship model, predict the severity of the defect, and generate a warning plan.

[0034] A computer device includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps of the multi-modal mechanical wave detection method based on the boundary bounce characteristics.

[0035] A computer-readable storage medium stores a computer program thereon, and when the computer program is executed by a processor, the steps of the multi-modal mechanical wave detection method based on the boundary bounce characteristics are implemented.

[0036] The beneficial effects of this invention are as follows: The multimodal mechanical wave detection method based on boundary bounce characteristics provided by this invention uses sensors to collect the waveforms, frequencies, and amplitudes of multiple modal mechanical waves and preprocesses them, effectively removing noise interference and improving signal clarity. This lays the foundation for accurately analyzing the boundary bounce characteristics of mechanical waves. The method analyzes the reflection characteristics of multiple modal mechanical waves when they encounter boundaries while propagating inside a target object, calculates the boundary bounce values ​​of multiple modal mechanical waves, and selects the mechanical wave with the highest boundary bounce value as the depth waveform feature. This effectively identifies which modal of mechanical wave is most sensitive to boundary bounce, thereby selecting the most representative depth waveform feature. It effectively removes noise and retains the true reflection characteristics, realizing the accurate detection of mechanical waves within materials. A deep understanding of the internal propagation behavior of materials provides strong data support for subsequent defect assessment. By constructing a relational model and inputting deep waveform features into the model, the severity of defects can be predicted, and early warning schemes can be generated. Complex waveform data is transformed into easily understandable defect severity indicators, providing a scientific basis for maintenance decisions. By setting early warning thresholds and generating corresponding early warning information, potential defects can be detected in advance, allowing for timely maintenance measures. This enables quantitative assessment and real-time monitoring of internal corrosion defects in target objects, improving the practicality and engineering application value of the detection system. This invention achieves better results in terms of data acquisition accuracy, defect detection precision, and the practicality of the early warning system. Attached Figure Description

[0037] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0038] Figure 1 The first embodiment of the present invention provides an overall flowchart of a multimodal mechanical wave detection method based on boundary bounce characteristics.

[0039] Figure 2 The following is an overall flowchart of a multimodal mechanical wave detection system based on boundary bounce characteristics, provided for the third embodiment of the present invention. Detailed Implementation

[0040] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0041] Example 1, referring to Figure 1 As an embodiment of the present invention, a multimodal mechanical wave detection method based on boundary bounce characteristics is provided, comprising:

[0042] S1: Use sensors to collect and preprocess the waveforms, frequencies, and amplitudes of various modal mechanical waves.

[0043] Furthermore, sensors are used to collect waveforms, frequencies, and amplitudes of various modes of mechanical waves, including selecting MEMS sensors, configuring the sensor's sampling frequency and sampling time, setting the data acquisition time window, and collecting signal data of longitudinal waves, transverse waves, surface waves, and plate waves propagating inside the target object.

[0044] It should be noted that the preprocessing process includes using a Butterworth filter to eliminate noise interference from multiple modes of mechanical waves, resulting in a denoised signal x. filtered (t) is used to normalize the signal so that all signal values ​​fall within the same range, and the normalized value x is calculated. norm (t), represented as:

[0045]

[0046] Where, x min It is the minimum value in the denoised signal, x max It is the maximum value in the denoised signal, x norm (t) is the normalized value.

[0047] It should also be noted that by employing high-precision sensors to collect waveforms, frequencies, and amplitudes of multiple modal mechanical waves and implementing effective preprocessing, the integrity and quality of the raw data are ensured. The selection of MEMS sensors and the configuration of sampling parameters allow for adjustments to the sampling frequency and time window according to different detection needs, thus adapting to various complex detection environments and improving the adaptability of the detection. The filtering and normalization techniques applied during preprocessing effectively remove noise and interference from the signal, enabling subsequent analysis to be based on a cleaner signal and improving the accuracy of data analysis. The normalized signal obtained through preprocessing provides a unified benchmark for comparative analysis between different modal mechanical waves, helping to reveal the differences in the propagation of each modal wave within the material. This lays a solid foundation for subsequent reflection characteristic analysis and boundary bounce value calculation, ensuring the reliability and efficiency of the entire detection process.

[0048] S2: Analyze the reflection characteristics of various modes of mechanical waves when they encounter the boundary while propagating inside the target object, calculate the boundary bounce value of various modes of mechanical waves, and select the mechanical wave with the highest boundary bounce value as the depth waveform feature.

[0049] Furthermore, the analysis of the reflection behavior of multiple modal mechanical waves when they encounter boundaries during propagation inside the target object includes applying multimodal mechanical waves at different locations on the target object, recording the response intensity of the waveforms using a high-speed camera and a laser Doppler vibrometer, simulating the response intensity of multiple modal waves at corrosion defects using the finite element analysis software COMSOL Multiphysics, and acquiring background noise signal q in the absence of corrosion defects, calculating the standard deviation σ of the background noise as an indicator of the noise level.

[0050] The reflection behavior of the waveform at different boundaries is recorded, and a multi-scale analysis method is introduced to analyze the boundary bounce characteristics at different scales from macro to micro. This includes using wavelet transform to remove noise while retaining the main features of the waveform in the true reflection characteristics. The field strength S(t,S) of the denoised reflected wave is calculated and expressed as:

[0051]

[0052] Where s(t,s) is the denoised reflected wave field intensity, ψ is the wavelet basis function, s is the scale parameter, t is the time parameter, and x is the time parameter. norm (τ) is the original signal. This is an integral operation where dτ is an infinitesimal increment of the time variable τ. It normalizes the waveform characteristic signal data to the same order of magnitude, and then calculates the normalized signal S. norm (t,s) is represented as:

[0053]

[0054] Among them, S min It is the minimum value in the signal after wavelet transform, S max S is the maximum value in the signal after wavelet transform. norm (t,s) represents the normalized signal.

[0055] Collect background noise signal Q, calculate the standard deviation σ of the background noise as an indicator of noise level, including calculating the mean μ and the variance σ. 2 The standard deviation σ is calculated, and the background noise level is assessed based on the calculated σ. When σ exceeds the preset threshold σ1, it indicates that the background noise level is too high. The background noise signal is then re-acquired, and an adaptive filter is used for further denoising. The denoised background noise signal W(t) is calculated and expressed as:

[0056] W(t) = QH adapt (J)·E(t)

[0057] Where W(t) is the denoised background noise signal, H adapt(J) is the transfer function of the adaptive filter, E(t) is the estimated noise signal, and the standard deviation σ2 of the denoised background noise signal is recalculated as follows:

[0058]

[0059] Where, σ 2 μ represents the standard deviation of the denoised background noise signal. clean The average value of the denoised background noise signal is (W(t)). i )-μ clean ) 2 The square of the difference between each denoised background noise signal value and the average value. For the summation symbol, W(t) i (i) represents the value of the denoised background noise signal at time point i. For the operation of averaging, N is the length of the signal, and i is each time point.

[0060] It should be noted that selecting the mechanical wave with the highest boundary bounce value as the depth waveform feature includes setting the boundary bounce value to R(t,s), expressed as:

[0061]

[0062] Where R(t,s) is the boundary bounce value, and S norm (t,s) represents the normalized reflected wave field intensity. The mechanical wave with the highest boundary bounce value is selected as the depth waveform feature, and the depth waveform feature F is calculated. depth , represented as:

[0063]

[0064] Among them, F depth For depth waveform features, This means finding the values ​​of t and s that maximize R(t,s) across all time scales.

[0065] It should also be noted that by applying multimodal mechanical waves to different locations of the target object and recording the waveform response using a high-speed camera and a laser Doppler vibrometer, comprehensive capture of the mechanical wave reflection behavior is achieved, solving the problem of insufficient depth in the reflection characteristic analysis in existing technologies. By using finite element analysis software and multi-scale analysis methods, the boundary bounce characteristics are analyzed at different scales from macro to micro, effectively identifying small or complex defects and improving the sensitivity and resolution of defect detection. By calculating and comparing the boundary bounce values ​​of different modal mechanical waves, the most representative depth waveform features are selected, thus providing a direct basis for defect depth assessment. By introducing an adaptive filter for further noise reduction, the accuracy of signal processing is improved, ensuring the accuracy of boundary bounce value calculation.

[0066] S3: Build a relationship model, input the depth waveform features into the relationship model, predict the severity of the defect, and generate a warning plan.

[0067] Furthermore, build a relationship model based on the corrosion defect and the depth waveform features, input the depth waveform features into the relationship model, and predict the severity of the defect. The relationship model is set as a linear regression model, and the output model y of the model is calculated and expressed as:

[0068] y = w1F depth,1 + w2F depth,2 + w3F depth,3 + b

[0069] where, w1, w2, w3 are weight parameters, b is a bias term, w1F depth,1 + w2F depth,2 + w3F depth,3 is the depth waveform feature vector, y is the output of the model, and F depth,1 、F depth,2 and F depth,3 are the respective components of the depth waveform feature vector.

[0070] It should be noted that generating a warning plan includes inputting the newly collected depth waveform features into the trained random forest model to obtain a prediction result, setting warning thresholds L1 and L2 according to the prediction result, and generating a warning message. If y < L1, a warning message for a minor defect is generated, and regular inspection and maintenance are recommended. If L1 ≤ y ≤ L2, a warning message for a medium defect is generated, and a detailed inspection is recommended immediately, and necessary repair measures are taken. If y ≥ L2, a warning message for a serious defect is generated, and it is recommended to stop using immediately and perform emergency repair or replacement.

[0071] It should also be noted that by building a linear regression model or other suitable models, complex waveform data can be transformed into an intuitive assessment of the severity of defects, making the detection results easier to understand and apply. Modeling the relationship between depth waveform features and corrosion defects provides a method for quantitatively analyzing the severity of defects. Compared with traditional qualitative analysis, the prediction results are more reliable and specific. By setting warning thresholds and generating warning messages, early detection and real-time monitoring of potential defects are achieved, providing timely and effective information support for maintenance decisions. The generation of warning plans not only improves the practicality of the detection system but also optimizes the preventive ability in actual engineering applications, helping to reduce losses and risks caused by the failure to detect defects in a timely manner.

[0072] Example 2 is an embodiment of the present invention, which provides a multimodal mechanical wave detection method based on boundary bounce characteristics. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0073] First, six different types of test objects were selected, each with representative material properties. The test equipment included MEMS sensors, a high-speed camera, a laser Doppler vibrometer, and the finite element analysis software COMSOL Multiphysics. During the data acquisition phase, the sensors were configured to operate at a frequency of 1000 Hz and a sampling time of 5 seconds to collect signal data of longitudinal waves, transverse waves, surface waves, and plate waves propagating within the target objects. To ensure data quality, Butterworth filters were used to preprocess the acquired signals to eliminate noise interference, and normalization was applied to ensure that the signal values ​​fell within the same range. Regarding the calculation of boundary bounce values... This invention employs the denoised reflected wave field strength as the basis for calculating the boundary bounce value, selects the mechanical wave with the highest boundary bounce value as the depth waveform feature, and provides a calculation method based on normalized reflected wave field strength, enabling the depth waveform feature to more accurately reflect defect information. Finally, by constructing a relational model and inputting the depth waveform feature into the model, the severity of the defect is predicted, and an early warning scheme is generated. This not only considers the relationship between the depth waveform feature and the severity of the defect but also introduces a random forest model to improve the accuracy and reliability of the prediction. Experimental results show that this invention has advantages in improving signal quality, accurately calculating boundary bounce values, and generating early warning schemes.

[0074] Example 3, referring to Figure 2 As an embodiment of the present invention, a multimodal mechanical wave detection system based on boundary bounce characteristics is provided, including a data preprocessing module, a boundary bounce analysis module, and a defect prediction and early warning module.

[0075] The data preprocessing module is used to collect and preprocess the waveforms, frequencies, and amplitudes of various modal mechanical waves using sensors; the boundary bounce analysis module is used to analyze the reflection characteristics of various modal mechanical waves when they encounter boundaries while propagating inside a target object, calculate the boundary bounce values ​​of various modal mechanical waves, and select the mechanical wave with the highest boundary bounce value as the depth waveform feature; the defect prediction and early warning module is used to build a relational model, input the depth waveform features into the relational model, predict the severity of defects, and generate early warning schemes.

[0076] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, 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 of the various embodiments of this 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.

[0077] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0078] More specific examples (a non-exhaustive list) of computer-readable media include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0079] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc. It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

[0080] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A multimodal mechanical wave detection method based on boundary bounce characteristics, characterized in that, include: Sensors are used to collect and preprocess the waveforms, frequencies, and amplitudes of various modal mechanical waves. The reflection characteristics of various mechanical waves when they encounter the boundary during propagation inside the target object are analyzed. The boundary bounce values ​​of various mechanical waves are calculated, and the mechanical wave with the highest boundary bounce value is selected as the depth waveform feature. A relational model is constructed, and deep waveform features are input into the relational model to predict the severity of defects and generate early warning schemes. The method of using sensors to collect waveforms, frequencies, and amplitudes of multiple modes of mechanical waves includes selecting MEMS sensors, configuring the sensor's sampling frequency and sampling time, setting the data acquisition time window, and collecting signal data of longitudinal waves, transverse waves, surface waves, and plate waves propagating inside the target object. The analysis of the reflection behavior of multi-mode mechanical waves when they encounter boundaries during propagation inside a target object includes applying multi-mode mechanical waves at different locations on the target object, recording the response intensity of the waveforms using a high-speed camera and a laser Doppler vibrometer, simulating the response intensity of multi-mode waves at corrosion defects using the finite element analysis software COMSOL Multiphysics, and collecting background noise signals in the absence of corrosion defects to calculate the standard deviation of the background noise as an indicator of the noise level. The reflection behavior of waveforms at different boundaries is recorded, and a multi-scale analysis method is introduced to analyze the boundary bounce characteristics at different scales from macro to micro. This includes using wavelet transform to remove noise while preserving the main features of the waveform in the true reflection characteristics, and calculating the field strength of the reflected wave after noise removal. , represented as: ， in, It is the intensity of the reflected wave field after noise reduction. These are wavelet basis functions. It is a scale parameter. It is a time parameter. It is the original signal. For an integral operation, For time variables An infinitesimal increment normalizes the waveform characteristic signal data to the same order of magnitude, and the normalized signal is then calculated. , represented as: ， in, It is the minimum value in the signal after wavelet transform. It is the maximum value in the signal after wavelet transform. The signal is normalized. Acquire background noise signal Calculate the standard deviation of background noise Indicators of noise level include calculating the average value. Calculate the variance Calculate the standard deviation According to the calculation Assess the level of background noise when Exceeding the preset threshold If the background noise level is too high, the background noise signal is re-acquired, and an adaptive filter is used for further denoising. The denoised background noise signal is then calculated. , is represented as: ， in, It is the background noise signal after denoising. It is the transfer function of the adaptive filter. The noise signal is estimated; the standard deviation of the denoised background noise signal is recalculated. , represented as: ， in, The standard deviation of the denoised background noise signal. The average value of the background noise signal after denoising. The square of the difference between each denoised background noise signal value and the average value. For summation, The background noise signal after denoising is at the 1st... The value at each point in time. For the operation of calculating the average, The length of the signal, For each point in time; The step of selecting the mechanical wave with the highest boundary rebound value as the depth waveform feature includes setting the boundary rebound value as... , represented as: ， in, The boundary rebound value, To determine the normalized reflected wave field strength, the mechanical wave with the highest boundary bounce value is selected as the depth waveform feature, and the depth waveform feature is calculated. , is represented as: ， in, For depth waveform features, This means finding the solution across all times and scales. The largest and The value; A relationship model is constructed based on corrosion defects and depth waveform characteristics. The depth waveform characteristics are input into the relationship model to predict the severity of the defects. This includes assuming the relationship model is a linear regression model and calculating the model's output. , represented as: , in, These are weight parameters. It is a bias term. It is a depth waveform feature vector. For the output of the model, These are the various components of the depth waveform feature vector.

2. The multimodal mechanical wave detection method based on boundary bounce characteristics as described in claim 1, characterized in that: The preprocessing process includes using a Butterworth filter to eliminate noise interference from multiple modes of mechanical waves, resulting in a denoised signal. The signal is normalized so that all signal values ​​fall within the same range, and the normalized value is calculated. , is represented as: ， in, It is the minimum value in the denoised signal. It is the maximum value in the denoised signal. It is the normalized value.

3. The multimodal mechanical wave detection method based on boundary bounce characteristics as described in claim 2, characterized in that: The early warning generation scheme includes inputting newly acquired depth waveform features into a trained linear regression model to obtain prediction results, setting early warning thresholds L1 and L2 based on the prediction results, and generating early warning information. If this occurs, a warning message for minor defects will be generated, suggesting regular inspection and maintenance. If this occurs, a warning message for a moderate defect will be generated, suggesting an immediate detailed inspection and the implementation of necessary repair measures. If a serious defect is detected, a warning message will be generated, recommending that the product be stopped immediately and that emergency repairs or replacements be carried out.

4. A system employing the multimodal mechanical wave detection method based on boundary bounce characteristics as described in any one of claims 1 to 3, characterized in that: It includes a data preprocessing module, a boundary bounce analysis module, and a defect prediction and early warning module; The data preprocessing module is used to collect and preprocess the waveforms, frequencies, and amplitudes of various modal mechanical waves using sensors. The boundary bounce analysis module is used to analyze the reflection characteristics of various modes of mechanical waves when they encounter the boundary while propagating inside the target object, calculate the boundary bounce value of various modes of mechanical waves, and select the mechanical wave with the highest boundary bounce value as the depth waveform feature. The defect prediction and early warning module is used to construct a relational model, input deep waveform features into the relational model, predict the severity of defects, and generate an early warning scheme.

5. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the multimodal mechanical wave detection method based on boundary bounce characteristics as described in any one of claims 1 to 3.

6. A 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 steps of the multimodal mechanical wave detection method based on boundary bounce characteristics as described in any one of claims 1 to 3.

Images